AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He
feat(planning): make custom design directions editable
hugohe35ea343ece9b1
diff --git a/docs/technical-design.md b/docs/technical-design.mdindex ed8499e4..44b40669 100644--- a/docs/technical-design.md+++ b/docs/technical-design.md@@ -478,7 +478,7 @@ without interaction, while the Stage-1 communication recommendation is authoredwithout reading those candidates or any template content. The UI confirms thatcommunication contract and the switchable free-design/template choice together;only afterward does the agent install/fuse a non-free selection. Strategist uses-one dependency-ordered two-stage gate. Its `delivery_context` recommendation distinguishes presenter-led, reader-led, hybrid, and recorded/self-running use in one prose field, names the primary context, and records any secondary use; hybrid never stands alone without its lead mode. The prose boxes remain editable and none requires a non-empty answer: confirmation persists the current text exactly, and a cleared value stays empty instead of falling back to the recommendation. Final Stage 2 is authored once from that contract. Strategist first creates exactly three complete, viable, project-fit solutions, then projects each into the lower mode, visual style, color, typography, icon, and generated-image-rendering controls; it does not assemble the three solutions afterward from independent component picks or force them into safe / shifted / bold archetypes. Image source remains an independent judgment, so every solution already has a rendering candidate even when AI imagery is initially not recommended. A top card applies its immutable bundle, lower controls may diverge, and clicking a card again restores that bundle; final state stores only the current flattened components. The same stage confirms reading mode, page count, conditional AI acquisition, formula policy, generation mode, the Design Spec review toggle, and whether the agent should proactively generate speaker notes, custom animations, or narration audio. Only after Stage 1 is confirmed, when a template is installed, does Strategist read the project-local workspace and current content, derive **how to apply it**, and expose that plan as editable `template_application` prose; Stage 2 never reselects a template, and the internal reuse/adherence modes stay hidden. Reading mode decides how meaning is carried by page, visuals, presenter, and notes; its cards do not present px values. The browser may apply the deterministic `reading mode → body baseline → unpinned role sizes` dependency locally, while manual size edits pin visible values. It never regenerates Stage 2. The three proactive values are fallback policies, not capability bans: the latest explicit user instruction wins, then final Stage 2, then the fixed defaults `true / false / false`. Strategist still records non-binding Motion suggestions when useful; a suggestion alone does not activate custom-animation execution. Generated images inherit the selected deck color anchors directly; there is no independent image-palette choice. Final state has two equivalent carriers: the default UI path reads `confirm_ui/result.json` exactly once after the final wait, while an explicit chat-only or delegated path retains an equivalent final confirmation summary and may produce no `result.json`. Both paths first resolve and persist every effective production outcome into one `design_spec.md` and complete Gate 1 fidelity. With refinement off, lock authoring proceeds immediately. With `refine_spec: true`, the pipeline stops before `spec_lock.md`; the user may revise any part of that same Design Spec through normal chat for any number of rounds, and explicit approval then releases Gate 2 lock authoring. No second Design Spec or parallel lock is maintained. Normal lock authoring and downstream execution do not reread either confirmation channel. Required manual assets may still introduce their own conditional blocking points, so this is not an exclusive claim over every runtime gate. Project validation requires the compact `audience` / `objective` / `core_message` anchor set under `spec_lock.md ## communication` plus an `Audience move` in every §IX Slide block.+one dependency-ordered two-stage gate. Its `delivery_context` recommendation distinguishes presenter-led, reader-led, hybrid, and recorded/self-running use in one prose field, names the primary context, and records any secondary use; hybrid never stands alone without its lead mode. The prose boxes remain editable and none requires a non-empty answer: confirmation persists the current text exactly, and a cleared value stays empty instead of falling back to the recommendation. Final Stage 2 is authored once from that contract. Strategist first creates exactly three complete, viable, project-fit solutions, then projects each into a custom mode, custom visual style, color, typography, icon, and custom generated-image rendering; the fixed catalogs remain conservative lower-level single-select alternatives. It does not assemble the three solutions afterward from independent component picks or force them into safe / shifted / bold archetypes. Before reference selection it reads only the three catalog indexes; after each solution's bases are frozen, it reads only the deduplicated selected detail files and completes the custom behaviors. Image source remains an independent judgment, so every solution already has a rendering candidate even when AI imagery is initially not recommended. A top card applies its immutable bundle, each projected custom card becomes editable in place after selection, and all lower controls may diverge; clicking the top card again restores its authored bundle, while final state stores only the edited current components. The same stage confirms reading mode, page count, conditional AI acquisition, formula policy, generation mode, the Design Spec review toggle, and whether the agent should proactively generate speaker notes, custom animations, or narration audio. Only after Stage 1 is confirmed, when a template is installed, does Strategist read the project-local workspace and current content, derive **how to apply it**, and expose that plan as editable `template_application` prose; Stage 2 never reselects a template, and the internal reuse/adherence modes stay hidden. Reading mode decides how meaning is carried by page, visuals, presenter, and notes; its cards do not present px values. The browser may apply the deterministic `reading mode → body baseline → unpinned role sizes` dependency locally, while manual size edits pin visible values. It never regenerates Stage 2. The three proactive values are fallback policies, not capability bans: the latest explicit user instruction wins, then final Stage 2, then the fixed defaults `true / false / false`. Strategist still records non-binding Motion suggestions when useful; a suggestion alone does not activate custom-animation execution. Generated images inherit the selected deck color anchors directly; there is no independent image-palette choice. Final state has two equivalent carriers: the default UI path reads `confirm_ui/result.json` exactly once after the final wait, while an explicit chat-only or delegated path retains an equivalent final confirmation summary and may produce no `result.json`. Both paths first resolve and persist every effective production outcome into one `design_spec.md` and complete Gate 1 fidelity. With refinement off, lock authoring proceeds immediately. With `refine_spec: true`, the pipeline stops before `spec_lock.md`; the user may revise any part of that same Design Spec through normal chat for any number of rounds, and explicit approval then releases Gate 2 lock authoring. No second Design Spec or parallel lock is maintained. Normal lock authoring and downstream execution do not reread either confirmation channel. Required manual assets may still introduce their own conditional blocking points, so this is not an exclusive claim over every runtime gate. Project validation requires the compact `audience` / `objective` / `core_message` anchor set under `spec_lock.md ## communication` plus an `Audience move` in every §IX Slide block.The three proactive values confirmed in final Stage 2 remain independent rawevidence. In particular, enabling narration may enable the effective Speaker@@ -514,7 +514,7 @@ Why both? `design_spec.md` preserves the complete confirmed solution and rationaThe view omits universal SVG/icon prohibitions already owned by the always-loaded Executor core and retains only project-specific forbidden rows. It selects images from the current page brief, explicit image-resource page assignments, and mirror prototype references. Images assigned elsewhere are excluded; any unresolved legacy image remains in a compatibility subset, and `confirmed-none` appears only when every locked image has a deterministic assignment elsewhere.-The lock is also the per-page routing table. Beyond global colors and typography, it carries `page_rhythm` (`anchor` / `dense` / `breathing`), `page_visualizations` (the selected page-local `chart|table/<key>` reference, which triggers reading the corresponding family SVG and §VII Usage but does not lock the final information model, type, or geometry), image rows with placement/cropping contracts, and the locked `mode` / `visual_style` values that select which rules are applied from the complete catalogs already loaded for each valid Executor context. Qualitative Structure is described directly in §IX and generated from those relationships; it has no §VII row, `page_visualizations` key, or catalog SVG. Legacy `page_charts` remains readable but is not written by new planning; a historical Structure bare key is retained only as semantic intent without an SVG reference. A selected custom direction also carries its resolved `mode_behavior` / `visual_style_behavior`. When it actually combines or borrows catalog entries, the lock records their exact ids in optional `mode_references` / `visual_style_references` / `image_rendering_references`; those ids preserve provenance and constrain synthesis to the declared bases rather than triggering broad or additional reads. A genuinely novel custom omits the corresponding reference field. `template_reuse_scope: mirror|layout` locks additionally carry `page_layouts` (which input template SVG each page inherits), unique `pptx_masters` / `pptx_layouts` definitions, and `page_pptx_layouts` assignments. `template_reuse_scope: style`, free-design, and brand-only projects use `pptx_structure.mode: flat` and omit those sections entirely rather than writing empty values. Empty entries elsewhere are meaningful signals: no catalog reference or no image is often a design decision rather than missing data.+The lock is also the per-page routing table. Beyond global colors and typography, it carries `page_rhythm` (`anchor` / `dense` / `breathing`), `page_visualizations` (the selected page-local `chart|table/<key>` reference, which triggers reading the corresponding family SVG and §VII Usage but does not lock the final information model, type, or geometry), image rows with placement/cropping contracts, and the locked `mode` / `visual_style` values. Each role reads the compact catalog index while deciding, freezes the selected ids, and only then reads one preset file or the exact custom references; unselected detail files never enter that role context. Qualitative Structure is described directly in §IX and generated from those relationships; it has no §VII row, `page_visualizations` key, or catalog SVG. Legacy `page_charts` remains readable but is not written by new planning; a historical Structure bare key is retained only as semantic intent without an SVG reference. A selected custom direction also carries its resolved `mode_behavior` / `visual_style_behavior`. When it actually combines or borrows catalog entries, the lock records their exact ids in optional `mode_references` / `visual_style_references` / `image_rendering_references`; those ids preserve provenance, constrain synthesis to the declared bases, and route the only permitted detail-file reads. A genuinely novel custom omits the corresponding reference field. `template_reuse_scope: mirror|layout` locks additionally carry `page_layouts` (which input template SVG each page inherits), unique `pptx_masters` / `pptx_layouts` definitions, and `page_pptx_layouts` assignments. `template_reuse_scope: style`, free-design, and brand-only projects use `pptx_structure.mode: flat` and omit those sections entirely rather than writing empty values. Empty entries elsewhere are meaningful signals: no catalog reference or no image is often a design decision rather than missing data.`page-context v2` remains an on-demand projector. Each invocation emits a compact global anchor set bound to `lock_source.sha256`, the current §IX/resource/routing delta, and scoped path/SHA fingerprints for large references; the projection is not a color/font allowlist or a replacement authority. It is used only for explicit diagnostics/telemetry or an unresolved page/template/visualization path-SHA question. A bounded exact repair in a valid uncompacted context may use targeted fragment readback plus validation; fresh, compacted, external, unknown, structural, or mismatched changes require one complete Design Spec and lock read. Flat pages have no prototype reference; structured pages use the authoritative complete SVG. Manifests and text-slot sidecars remain derived tool diagnostics and are never injected into page authoring.@@ -587,7 +587,7 @@ Several architectural decisions shape this phase:**External refs during development, two divergent embedding strategies for downstream outputs.** While editing in `svg_output/`, images are external file references for fast iteration and single-point replacement. `svg_final/` then Base64-inlines ordinary bitmaps and supported SVG resources, while retaining external EMF/WMF references for native PPTX passthrough; an individual inline failure increments the processing-error count, but it does not rewrite authored source or fail the finalizer as a whole. Native PPTX instead copies bitmaps or Office vectors into the package media folder and uses `<a:srcRect>` for supported bitmap cropping. The split exists because the preview and compiler serve different responsibilities: one is a derived visual reference, while the other produces editable DrawingML through the project converter. `svg_final/` is not an unconditionally portable no-external-dependency interchange format or a compatibility source for PowerPoint Convert to Shape.-**One rendering lock, inherited deck anchors, and per-image composition.** Before deciding whether to recommend AI imagery, Stage 2 authors one complete deck-wide rendering candidate inside each of its three coordinated design directions. The source decision is separate: the UI hides rendering controls until AI is selected, then reveals those existing candidates without another recommendation pass. Only confirmed AI usage promotes the selected candidate into the execution contract. Image colors are not a second user decision: Image_Generator starts from the core HEX roles in `spec_lock.md colors`, reads only the selected rendering entry or exact custom bases, then interprets them with the completed Design Spec and each resource's `type` or hero-page composition. Rendering may derive coherent tints, material colors, lighting transitions, and atmospheric hues while preserving the core role meanings; it must not replace the deck identity with an unrelated image-only palette. A repeated derived tone may be promoted into a named lock role.+**One rendering lock, inherited deck anchors, and per-image composition.** Before deciding whether to recommend AI imagery, Stage 2 authors one complete custom deck-wide rendering candidate inside each of its three coordinated design directions. It uses the rendering index to freeze any bases before reading only those selected detail files. The source decision is separate: the UI hides rendering controls until AI is selected, then reveals the three editable custom candidates followed by the fixed rendering catalog without another recommendation pass. Only confirmed AI usage promotes the selected current value into the execution contract. Image colors are not a second user decision: Image_Generator starts from the core HEX roles in `spec_lock.md colors`, reads only the selected rendering entry or exact custom bases, then interprets them with the completed Design Spec and each resource's `type` or hero-page composition. Rendering may derive coherent tints, material colors, lighting transitions, and atmospheric hues while preserving the core role meanings; it must not replace the deck identity with an unrelated image-only palette. A repeated derived tone may be promoted into a named lock role.---diff --git a/skills/ppt-master/references/executor-base.md b/skills/ppt-master/references/executor-base.mdindex 027aa301..98551adb 100644--- a/skills/ppt-master/references/executor-base.md+++ b/skills/ppt-master/references/executor-base.md@@ -18,7 +18,7 @@ Always-loaded Executor authority for flat SVG page authoring and behavior sharedEvaluate branches from each object's actual information model, not only from a Chart/Table reference. A catalog family selects construction guidance but never native readiness; `Native-ready` is an independent object-level decision. Page-local qualitative geometry also never implies package-level `pptx_structure.mode: structured`.-> Narrative skeleton and visual aesthetic come from the locked values applied against the complete [`modes/`](./modes/_index.md) and [`visual-styles/`](./visual-styles/_index.md) catalogs already loaded for this Executor context. Optional `*_references` identify actual custom synthesis bases; they are not load triggers. [`shared-standards-core.md`](./shared-standards-core.md) supplies the technical boundary plus the fallback visual-quality and leading defaults when those authorities are silent.+> Narrative skeleton and visual aesthetic come from the locked values routed through the [`modes/`](./modes/_index.md) and [`visual-styles/`](./visual-styles/_index.md) indexes. Executor reads one locked preset file or only the exact `*_references` of a custom synthesis; an unreferenced novel custom reads none. [`shared-standards-core.md`](./shared-standards-core.md) supplies the technical boundary plus the fallback visual-quality and leading defaults when those authorities are silent.**Hard rule — Shape-first page authority**: Every visible object intended for the exported slide MUST exist in the final page SVG or be explicitly referenced by it. Templates and `spec_lock.md` guide construction; they are not export-time overlays for missing visible content. Optional native Chart/Table metadata belongs to an independently selected object and never replaces this visible fallback during authoring; [`native-data-interface.md`](./native-data-interface.md) alone defines that metadata and its export activation.diff --git a/skills/ppt-master/references/image-renderings/_index.md b/skills/ppt-master/references/image-renderings/_index.mdindex 5c412536..87347771 100644--- a/skills/ppt-master/references/image-renderings/_index.md+++ b/skills/ppt-master/references/image-renderings/_index.md@@ -10,7 +10,7 @@ A **rendering** is a visual style family: line quality, texture, depth, material## 1. Catalog (20 renderings)-Each rendering keeps its own authoritative file with: style paragraph, line / texture / depth notes, deck HEX usage, and a fewshot prompt snippet. Before Default Stage 2 or Quick resolves image usage, the design-decision owner reads this index plus all 20 sibling rendering files once as one deterministic batch and prepares three project-relevant rendering candidates. Whether AI imagery is recommended remains a separate source decision. Image_Generator later reads this index plus only the confirmed preset entry or exact `image_rendering_references`; a novel `custom` may omit references.+Each rendering keeps its own authoritative file with: style paragraph, line / texture / depth notes, deck HEX usage, and a fewshot prompt snippet. Read this index alone while choosing a direction. Only after a preset or custom bases are fixed may the active role read the selected sibling files: one file for a preset, every exact `image_rendering_references` file for a catalog-based custom, and none for a novel custom. Never glob the directory or read an unselected sibling. Whether AI imagery is recommended remains a separate source decision; Image_Generator follows the same selected-only rule.### 1.1 Modern / commercial (the corporate-PPT main field)@@ -54,7 +54,7 @@ Each rendering keeps its own authoritative file with: style paragraph, line / te### 1.5 Escape hatch — `custom`-Every coordinated Stage-2 direction carries one complete image-rendering candidate even when `recommend.image_usage` does not include `ai`. The UI keeps rendering controls hidden until the current source selection includes AI, then exposes the three already-authored project candidates without another backend recommendation. A candidate may use `rendering: custom` plus a complete behavior paragraph. A template-backed proposal must honor inherited identity and the confirmed template-application plan.+Every coordinated Stage-2 direction carries one complete `rendering: custom` candidate even when `recommend.image_usage` does not include `ai`. The UI keeps rendering controls hidden until the current source selection includes AI, then exposes the three already-authored project candidates without another backend recommendation. The 20 fixed renderings remain lower-level single-select alternatives. A template-backed proposal must honor inherited identity and the confirmed template-application plan.**Hard rule — `rendering_behavior` prose**:@@ -62,7 +62,7 @@ Every coordinated Stage-2 direction carries one complete image-rendering candida|---|---|| Length | One paragraph, 2-5 sentences || Axes covered | line / texture / depth / material / mood (same as preset files) |-| Catalog basis | When existing renderings are combined or borrowed, name every exact id and read every named file before synthesis |+| Catalog basis | Freeze every exact id from this index, then read only those named files before synthesis |```yaml- image_rendering: customdiff --git a/skills/ppt-master/references/modes/_index.md b/skills/ppt-master/references/modes/_index.mdindex 5040f90e..f79495c1 100644--- a/skills/ppt-master/references/modes/_index.md+++ b/skills/ppt-master/references/modes/_index.md@@ -8,7 +8,7 @@ A **mode** is the deck's **narrative + persuasion skeleton** — how the argumen## 1. Catalog (5 modes)-Each mode keeps its own authoritative file with: narrative skeleton, page-structure tendencies, speaker-notes register, and a page skeleton example. Every Default and Quick Generate run reads this index plus all five sibling mode files once as one deterministic batch before choosing or realizing a direction. Keep the files separate and preserve their boundaries in the batch; exact `mode_references` identify the sources actually used by a custom direction, not which files enter context.+Each mode keeps its own authoritative file with: narrative skeleton, page-structure tendencies, speaker-notes register, and a page skeleton example. Read this index alone while choosing a direction. Only after a preset or custom bases are fixed may the active role read the selected sibling files: one file for a preset, every exact `mode_references` file for a catalog-based custom, and none for a novel custom. Never glob the directory or read an unselected sibling.| Mode | Narrative skeleton | Best for ||---|---|---|@@ -18,7 +18,7 @@ Each mode keeps its own authoritative file with: narrative skeleton, page-struct| [`showcase`](./showcase.md) | Visual-led impact; big imagery / numbers; emotional rhythm | Launches, brand reveals, event / promo decks || [`briefing`](./briefing.md) | Neutral, complete, scannable; topic titles, even weight, no thesis | Status updates, reference decks, catalogs, meeting packs, FAQs |-> The five are **argument strategies, not a taxonomy of communication purposes**. A presentation may inform + align + request a decision at once; that composite intent stays as open prose in Default's Stage-1 communication contract or Quick's active brief. Default Stage 2 or the Quick main agent chooses the mode that best carries the dominant body-page spine, or one concrete `custom` act sequence when no preset can serve the stated priority / sequence.+> The five are **argument strategies, not a taxonomy of communication purposes**. A presentation may inform + align + request a decision at once; that composite intent stays as open prose in Default's Stage-1 communication contract or Quick's active brief. Default uses this index to map each whole solution intent into one project-specific custom behavior; Quick resolves one preset or custom direction directly.>> **A mode is a lens, not a mandate over an explicitly preserved structure.** Default applies the confirmed `content_divergence`; Quick applies the equivalent user-stated or active-context boundary to a supplied outline. An ordinary source outline is a Reference that the mode may regroup, reorder, or retitle while preserving its facts and intended relationships. Preserve page order, titles, or wording only when the user presents the outline as the final page plan or explicitly requests that boundary. When the user gives no structure, the mode does the structural lifting. To keep reshaping light, `briefing` imposes the least skeleton.@@ -53,8 +53,8 @@ Each mode keeps its own authoritative file with: narrative skeleton, page-struct| Active profile | Use ||---|---|-| Default Generate | Strategist and Executor each read this index plus every sibling mode file once per valid role context. Strategist authors the candidate directions, records the confirmed mode in `design_spec.md`, and projects it to `spec_lock.md`; Executor applies that selected value from the already-loaded catalog. |-| Quick Generate | The current main agent reads this index plus every sibling mode file once, resolves the best-fit preset or one warranted custom behavior without interaction, and retains the full catalog in active context without Design Spec/lock. |+| Default Generate | Strategist reads only this index while mapping three whole solution intents, freezes each custom direction's exact bases, then reads only their deduplicated detail files. Executor reads the confirmed preset file or exact custom references. |+| Quick Generate | The current main agent reads only this index while deciding, then reads the resolved preset or exact custom bases and keeps that one direction in active context without Design Spec/lock. |**Resolution scope**: deck-wide (one mode per deck). The five are the catalog you select from; if the structure is genuinely mixed, pick the mode of the body pages and let pages vary within it, or use a warranted `custom` blend (§4). Default recommends and confirms; Quick decides directly.@@ -64,14 +64,14 @@ Each mode keeps its own authoritative file with: narrative skeleton, page-struct`custom` holds **any bespoke narrative direction the five don't give as-is** — and what *kind* of thing it is doesn't matter. It might be a nameable cadence (dialectic 正反合, myth-vs-reality, countdown / Top-N, Socratic), a deliberate multi-act fusion of several modes, or the user's own feel for how the deck should carry (confrontational here, detached there). Don't try to taxonomize it.-**Default candidate**: Each coordinated Stage-2 direction may use one preset or one visible, non-empty `custom` cadence / fusion / posture. A custom direction carries editable `mode_behavior` and fits any installed template capacity. The Strategist crystallizes the confirmed current value in the Design Spec first, then projects its behavior and actual catalog basis to `spec_lock.md`. The full catalog is already loaded; references preserve provenance and synthesis intent rather than trigger extra reads.+**Default candidates**: All three coordinated Stage-2 directions use literal `custom` plus a visible, non-empty `mode_behavior`. A direction may specialize one preset, fuse several modes, or define a novel cadence; it fits any installed template capacity. The fixed five remain lower-level single-select alternatives. Strategist crystallizes the confirmed current value in the Design Spec first, then projects its behavior and actual catalog basis to `spec_lock.md`.-**Quick custom**: do not display a candidate set. Use `custom` only when no single preset supplies the dominant spine, resolve its behavior from the fully loaded catalog in active context, and persist nothing.+**Quick custom**: do not display a candidate set. Use `custom` only when a project-specific specialization or fusion serves the deck better than one preset; retain the behavior and exact bases in active context and persist nothing.-**Mandatory — name every catalog source actually used**: If a custom direction combines or borrows existing modes, name their exact ids after comparing the complete catalog. A `pyramid` + `narrative` fusion therefore writes `mode_references: pyramid, narrative` beside `mode_behavior`; Quick retains those bases only in active context. Do not add loosely related references after the fact. A genuinely new cadence names no catalog source.+**Mandatory — select before detail reading**: Use this index to freeze every catalog source actually used, then read only those exact files before writing the behavior. A `pyramid` + `narrative` fusion therefore reads those two files and writes `mode_references: pyramid, narrative` beside `mode_behavior`; Quick retains those bases only in active context. Do not open candidates for comparison after this gate or add loosely related references after the fact. A genuinely new cadence names and reads no catalog source.> **One value per deck — fusion is *one* `custom`, not several modes.** A deck always resolves a single `mode`. A multi-mode blend is expressed as **one** custom behavior whose paragraph describes the acts — never as several simultaneous modes.>-> **First ask whether it's really fusion.** A resolved mode is a *tendency*, not a cage: a `narrative` deck can still carry one analytical (pyramid-style) page, an `instructional` deck one showcase reveal — that is leaning within a dominant mode, and needs **no** `custom`. Reach for `custom` only when there is genuinely no single dominant spine.+> **Custom need not mean fusion.** A Default recommendation can specialize one dominant preset for this project's act sequence, title voice, rhythm, and register. Quick or a lower-level manual choice may still use the fixed preset directly.-**The one thing to avoid**: selecting `custom` as a *dodge* — defaulting to it because picking among the five takes judgment. Default's custom candidate is mandatory; selecting it is not. Quick creates no candidate. When a preset genuinely fits, keep that preset selected. A user-stated direction remains authoritative the same way a user-supplied outline is — see the lens-not-mandate note in §1.+**Forbidden — empty customization**: Do not relabel an index row as `custom`. The behavior must state the project-specific cadence, posture, title voice, page rhythm, or act sequence that the fixed preset alone does not encode. A user-stated direction remains authoritative the same way a user-supplied outline is — see the lens-not-mandate note in §1.diff --git a/skills/ppt-master/references/strategist-image.md b/skills/ppt-master/references/strategist-image.mdindex 64b82596..93a180b4 100644--- a/skills/ppt-master/references/strategist-image.md+++ b/skills/ppt-master/references/strategist-image.md@@ -4,7 +4,7 @@Always-on Stage-2 rendering-candidate extension plus conditional formula assets, confirmed image elaboration, and `design_spec.md §VIII` resource planning.-**Trigger**: Load before every fresh Stage-2 direction set and apply §2 after reading the complete image-rendering catalog. [`strategist.md`](./strategist.md) independently owns source recommendation. A confirmed non-`none` source activates the applicable resource-planning sections; confirmed `none` without formulas stops before resources, while a formula-only path applies §3 and §4 formula rows only. Rendering candidates are authored once before confirmation and never backfilled from a later source toggle.+**Trigger**: Load before every fresh Stage-2 direction set. Apply §2 first from the rendering index, freeze each direction's exact bases, and only then read the deduplicated selected detail files before completing its behavior. [`strategist.md`](./strategist.md) independently owns source recommendation. A confirmed non-`none` source activates the applicable resource-planning sections; confirmed `none` without formulas stops before resources, while a formula-only path applies §3 and §4 formula rows only. Rendering candidates are authored once before confirmation and never backfilled from a later source toggle.---@@ -20,9 +20,9 @@ For illustration, apply this precedence: confirmed `none` → explicit user inte## 2. AI Image Strategy — always propose three; lock only for confirmed `ai`-Read [`image-renderings/_index.md`](./image-renderings/_index.md) plus all 20 sibling rendering files once as one deterministic, boundary-preserving batch before constructing Stage 2. First author exactly three complete, project-fit solution directions, then project one complete `image_strategy` into each direction regardless of `recommend.image_usage`. Each candidate carries localized `name`, `rendering`, `visual`, and `mood`; `custom` also carries non-empty localized `behavior`. Mood includes a recognizable real-world analogy. All three must credibly serve their owning whole solution, but they need not use different rendering ids or span artificial safe / shifted / bold extremes. Image colors always inherit that direction's deck HEX roles; never add an image palette or alter deck colors to rescue a rendering.+Before any rendering detail, read only [`image-renderings/_index.md`](./image-renderings/_index.md). First author exactly three complete, project-fit solution intents; use the index to freeze each intent's exact rendering bases, then read once only the deduplicated referenced sibling files. Project one complete `image_strategy` into each direction regardless of `recommend.image_usage`. Every candidate carries localized `name`, `rendering: custom`, `visual`, `mood`, and non-empty localized `behavior`. Mood includes a recognizable real-world analogy. All three must credibly serve their owning whole solution, but they need not use different bases or span artificial safe / shifted / bold extremes. Image colors always inherit that direction's deck HEX roles; never add an image palette or alter deck colors to rescue a rendering.-A direction may use a preset or a `custom` synthesis. If a custom candidate combines or borrows existing renderings, name every exact id in its visible behavior after comparing the complete catalog; if it is genuinely novel, name no catalog basis. Under a template it obeys inherited identity and application. Only a confirmed custom locks its edited behavior as `image_rendering_behavior`; when catalog material is actually used, also project the exact ids as `image_rendering_references`, otherwise omit that field. Unselected candidates remain recommendation-only. Do not write a separate fourth `custom_candidates.image_strategy`; ignore legacy `image_palette`.+Every direction is a `custom` rendering. If it specializes, combines, or borrows existing renderings, name every exact index-selected id in its visible behavior and read only those files after selection; if it is genuinely novel, name no basis and read none. Under a template it obeys inherited identity and application. Only a confirmed custom locks its edited behavior as `image_rendering_behavior`; when catalog material is actually used, also project the exact ids as `image_rendering_references`, otherwise omit that field. Unselected candidates remain recommendation-only. Do not write a separate fourth `custom_candidates.image_strategy`; ignore legacy `image_palette`.The UI hides these candidates while AI is not selected. If the user adds AI, it reveals the already-authored three without another backend recommendation; source selection never creates or rewrites rendering candidates. After confirmation, Image_Generator reads only the selected preset or exact custom references and must not blend unselected candidate identities.diff --git a/skills/ppt-master/references/strategist.md b/skills/ppt-master/references/strategist.mdindex 59f0a62c..e10eafc3 100644--- a/skills/ppt-master/references/strategist.md+++ b/skills/ppt-master/references/strategist.md@@ -36,15 +36,15 @@ solution + production gate:| **1 — communication contract + template choice** | `primary_language` · `c` audience · open-ended communication intent · audience outcome · core message / delivery context (primary + optional secondary) / artifact afterlife · `content_divergence` (all prose fields may be blank) · `a` canvas · explicit `free_design` or `templates` choice and selected roots | confirmed together; candidate workspaces do not influence the communication recommendation || **2 — final solution + production** (authored once from the user's *actual* Stage 1) | reading mode (`delivery_purpose`, PPT only) · `d` mode + visual style · `b` page count · `e` color · `f` icon · `g` typography · `h` image source + generated-image rendering · conditional natural-language template application · formula policy · conditional AI-image acquisition path · generation mode · refine-spec toggle · proactive speaker notes / custom animations / narration audio | derived as one coherent plan from the confirmed contract; internal template exporter modes remain hidden |-Do not force communication intent into one catalog label; Stage 1 records composite intent in prose. Editable prose fields are recommendation drafts, not required inputs: confirmation preserves current text and blanks; never repopulate a cleared field. Stage 2 confirms narrative spine, reading density, page budget, visual system, image direction, production mechanics, and how any installed template should be used. It never chooses or installs a template. Inspect only project-local template spec/prototypes, present one editable application plan, and keep exporter reuse/adherence internal. First author exactly three complete, project-fit solution directions from the confirmed contract and source; only then project each direction into mode, visual style, color, type, icons, and generated-image rendering for lower-level adjustment. All three must be viable and meaningfully distinguishable as whole solutions, but do not force safe / shifted / bold archetypes, different catalog ids, or artificial extremes. Every direction carries a complete generated-image rendering candidate even when AI imagery is not recommended; `recommend.image_usage` independently decides whether AI is proposed. Generated images inherit deck colors—there is no second image palette. Proactive defaults are speaker notes `true`, custom animations `false`, and narration audio `false`; a prior explicit user instruction overrides the matching recommendation, and effective narration audio requires effective speaker notes. Author each stage once; same-stage edits update only visible browser state through documented deterministic dependencies, without another AI/backend recommendation. Launch/derive/wait mechanics live in [`generate-pptx.md`](../workflows/generate-pptx.md) Step 4; item specs keep `a`–`h`.+Do not force communication intent into one catalog label; Stage 1 records composite intent in prose. Editable prose fields are recommendation drafts, not required inputs: confirmation preserves current text and blanks; never repopulate a cleared field. Stage 2 confirms narrative spine, reading density, page budget, visual system, image direction, production mechanics, and how any installed template should be used. It never chooses or installs a template. Inspect only project-local template spec/prototypes, present one editable application plan, and keep exporter reuse/adherence internal. First author exactly three complete, project-fit solution directions from the confirmed contract and source; only then project each direction into mode, visual style, color, type, icons, and generated-image rendering for lower-level adjustment. Every direction projects a project-specific `custom` mode, `custom` visual style, and `custom` generated-image rendering; the fixed catalogs remain conservative lower-level single-select alternatives. All three must be viable and distinguishable as whole solutions, but do not force safe / shifted / bold archetypes, different catalog bases, or artificial extremes. Every direction carries a complete generated-image rendering candidate even when AI imagery is not recommended; `recommend.image_usage` independently decides whether AI is proposed. Generated images inherit deck colors—there is no second image palette. Proactive defaults are speaker notes `true`, custom animations `false`, and narration audio `false`; a prior explicit user instruction overrides the matching recommendation, and effective narration audio requires effective speaker notes. Author each stage once; same-stage edits update only visible browser state through documented deterministic dependencies, without another AI/backend recommendation. Launch/derive/wait mechanics live in [`generate-pptx.md`](../workflows/generate-pptx.md) Step 4; item specs keep `a`–`h`.**Hard rule — Stage-1 source boundary**: Build the communication recommendation only from the current user request, source facts, conversation constraints, and project-initialization state. Author it before loading index summaries for a chat listing, and do not read any candidate spec, prototype, asset, or template-owned canvas. The same Stage-1 surface may display template controls, but their values are confirmation state, not recommendation evidence. Do not load or apply [`strategist-template.md`](./strategist-template.md) until Stage 1 is confirmed and the selected workspace has been installed for Stage 2.-> **Execution discipline**: Step 3 is non-interactive candidate preparation. Stage 1 is the first BLOCKING checkpoint and closes communication plus template/free-design choice in one confirmation. Install/fuse any selection and complete its handoff before authoring final Stage 2. After final confirmation, proceed without another pause unless spec refinement is enabled.+> **Execution discipline**: Step 3 is non-interactive candidate preparation. Stage 1 is the first BLOCKING checkpoint and closes communication plus template/free-design choice in one confirmation. Its receipt is intermediate and MUST NOT end the task or produce a final chat reply. In the same active run, install/fuse any selection, complete its handoff, author fresh Stage 2, and enter the final confirmation wait. After final confirmation, proceed without another pause unless spec refinement is enabled.>> **One opt-in exception**: present the refinement line with the split-mode note ([`generate-pptx.md`](../workflows/generate-pptx.md) Step 4). Only explicit opt-in runs [`refine-spec`](../workflows/stages/refine-spec.md): write the Design Spec once, pass Gate 1, then stop before the lock for unrestricted chat revision. Never enter it unprompted.-> **Default presentation surface — Confirm UI.** Before the first actual confirmation phase, apply [`confirm_ui.md`](../scripts/docs/confirm_ui.md)'s sticky per-run surface decision; its explicit chat branch skips every UI command, and a chat selection after UI launch follows its in-run switch procedure. Chat-question tools alone do not select a branch. In the UI branch, `template_options.json` and `recommendations.stage1.json` open one Stage-1 page; its single submission writes the pure Strategist `result.json` plus the sidecar `template_selection.json`. After installation/free-design closure, `template_handoff.json` gates `.stage2.json`. The chat/delegated branch keeps equivalent state without fabricating those receipts. Replace only the active unconfirmed stage and print the URL plus combined Stage-1 summary/fallback without treating that handoff as confirmation. Stage 1 writes canonical BCP-47 `primary_language` apart from UI `lang`; Strategist projects it through Design Spec §I to lock communication. Stage 2 carries exactly three immutable `design_directions`, each with a unique stable id and complete mode, visual style, six-role HEX palette, primary-language heading/body typography plus an English companion only for non-English decks, icons, and generated-image rendering. A direction card applies its whole bundle; lower controls may then diverge, and clicking that card again restores the authored bundle. The final result stores only the current component values, never the direction id as execution authority. Step 4 retains final confirmation from the selected channel for Design Spec authoring. `confirm_ui.md` owns selection-surface and staged-confirmation lifecycle.+> **Default presentation surface — Confirm UI.** Before the first actual confirmation phase, apply [`confirm_ui.md`](../scripts/docs/confirm_ui.md)'s sticky per-run surface decision; its explicit chat branch skips every UI command, and a chat selection after UI launch follows its in-run switch procedure. Chat-question tools alone do not select a branch. In the UI branch, `template_options.json` and `recommendations.stage1.json` open one Stage-1 page; its single submission writes the pure Strategist `result.json` plus the sidecar `template_selection.json`. After installation/free-design closure, `template_handoff.json` gates `.stage2.json`. The chat/delegated branch keeps equivalent state without fabricating those receipts. Replace only the active unconfirmed stage and print the URL plus combined Stage-1 summary/fallback without treating that handoff as confirmation. Stage 1 writes canonical BCP-47 `primary_language` apart from UI `lang`; Strategist projects it through Design Spec §I to lock communication. Stage 2 carries exactly three immutable `design_directions`, each with a unique stable id, `custom` mode, `custom` visual style, six-role HEX palette, primary-language heading/body typography plus an English companion only for non-English decks, icons, and `custom` generated-image rendering. A direction card applies its whole bundle; lower controls may then diverge through the three projected custom candidates or the fixed single-select catalogs, and clicking that card again restores the authored bundle. The final result stores only the current component values, never the direction id as execution authority. Step 4 retains final confirmation from the selected channel for Design Spec authoring. `confirm_ui.md` owns selection-surface and staged-confirmation lifecycle.**Confirmed-value semantics**: confirmation preserves both the value and the owning field's semantic type. Apply the type to the affected property, not automatically to the whole object:@@ -123,37 +123,37 @@ When authoring §IX, translate every purpose named in `communication_intent` intTwo independent layers, each locks one preset or `custom`. Output: `d. Mode: <mode> + Visual style: <visual_style>`.-> **Top-down direction construction.** Author the three complete solution directions before selecting their component values; do not assemble three apparent solutions afterward from independent mode/style/color recommendations. Each direction may use presets, `custom`, or repeated fixed values. A `custom` component carries visible, non-empty behavior prose and exact references only when it actually synthesizes catalog material. The three direction projections are the project-specific component candidates shown above the complete base catalogs; they are not a separate fourth Custom proposal. Never write bespoke prose as the enum value.+> **Top-down custom direction construction.** Author three complete solution intents from the confirmed project contract and source before selecting any catalog basis; do not assemble three apparent solutions from independent mode/style/rendering picks. At that point only the three indexes may be in context. Use their summaries to freeze the exact reference ids for each direction, then read once only the deduplicated union of those referenced detail files and author the final behaviors. Every direction MUST serialize `mode: custom`, `visual_style: custom`, and `image_strategy.rendering: custom`, each with visible, non-empty behavior prose. A catalog-based custom names only its actual bases; a genuinely novel custom names none and reads no detail file. These three projections are the project-specific choices above the conservative fixed catalogs, not a fourth Custom proposal. Never glob a catalog, read an unselected sibling, or write bespoke prose as an enum value.#### Layer 1 — Communication mode-🚧 **GATE**: read [`modes/_index.md`](./modes/_index.md) plus all five sibling mode files once as one deterministic, boundary-preserving batch before authoring the three directions.+🚧 **GATE**: before choosing a basis, read only [`modes/_index.md`](./modes/_index.md). After the three direction intents exist and their mode reference ids are frozen, read only those exact sibling files once; a novel mode reads none.The deck's **narrative + persuasion skeleton** — how the argument is organized and advanced. Lock one preset from `pyramid` / `narrative` / `instructional` / `showcase` / `briefing`, or `custom` with behavior.**Source**:- User supplied their own outline / structure → preserve its facts and intended relationships, then apply the confirmed `content_divergence`. Treat an ordinary source outline as a Reference: regroup, reorder, or retitle when the communication contract benefits. Treat it as authoritative only when the user presents it as the final page plan or explicitly asks to preserve page order, titles, or wording; record that promoted boundary in `design_spec.md`. Still lock a mode for register, voice, and any permitted reshaping. `briefing` imposes the least if no particular "讲法" is intended.-- Beautify / re-layout profile ([`beautify-pptx.md`](../workflows/profiles/beautify-pptx.md)) → the extracted source content is authoritative and **verbatim**, one step stricter than the user-outline case above. Each source slide becomes exactly one `§IX` page in source order; transcribe every content block word-for-word — never reshape / re-primary / condense / merge / split / reword. Lock `mode: briefing`; color (e) and typography (g) are whatever the user confirmed in the beautify plan — the source identity (theme or observed) by default, or a content / brand-aware alternative the beautify plan offered and the user picked — locked as truth (the beautify plan already ran the recommendation through the confirm UI, so do not re-recommend here). Charts / tables / images are regenerated from their extracted data in the inherited style: record only selected catalog references in §VII, keep unmatched chart/table plans in their §IX page blocks, and route pictures to §VIII. Data values stay frozen and the rendering is the deck's own; visuals are never carried over verbatim. Layout, hierarchy, rhythm, and visual rendering are what gets redesigned.-- A bespoke direction the five don't give — a nameable cadence (dialectic 正反合, myth-vs-reality, countdown, Socratic), a multi-act fusion of modes, or the user's own feel (confrontational here, detached there). Either the user asks, **or you recommend it** when a fusion / bespoke direction genuinely serves the deck better than a single preset (a recommendation the user confirms, like every lock). The *kind* doesn't matter → `mode: custom` + a `mode_behavior:` paragraph that **crystallizes the intent** (act sequence or posture shifts, title voice, page rhythm, register) concretely enough for the Executor to follow per page; it reads only `spec_lock.md`, never the chat. If the direction uses existing modes, retain those exact ids as its catalog basis; if it is genuinely new, do not invent a basis. One deck locks **one** value — a fusion is one `custom` describing the acts, never several modes. Avoid only the *dodge*: don't default to `custom` when a preset genuinely fits, and prefer a dominant mode + page-level variation when one mode leads.-- No user structure or cadence → derive each whole solution from the confirmed `communication_intent`, `audience_outcome`, source texture, and delivery context, then project its mode. Composite intent does not automatically require `custom`: choose the dominant spine of the body pages when one exists; use a concrete `custom` act sequence only when no single spine can serve the stated priority / sequence. The three whole solutions may share a mode when that is honestly best; distinguish them through the fields that materially change the outcome instead of forcing different mode ids.+- Beautify / re-layout profile ([`beautify-pptx.md`](../workflows/profiles/beautify-pptx.md)) → the extracted source content is authoritative and **verbatim**, one step stricter than the user-outline case above. Each source slide becomes exactly one `§IX` page in source order; transcribe every content block word-for-word — never reshape / re-primary / condense / merge / split / reword. All three custom mode behaviors preserve that 1:1 boundary and may share `briefing` as their sole basis; do not manufacture narrative variation. Color (e) and typography (g) are whatever the user confirmed in the beautify plan — the source identity (theme or observed) by default, or a content / brand-aware alternative the beautify plan offered and the user picked — locked as truth. Charts / tables / images are regenerated from their extracted data in the inherited style: record only selected catalog references in §VII, keep unmatched chart/table plans in their §IX page blocks, and route pictures to §VIII. Data values stay frozen and the rendering is the deck's own; visuals are never carried over verbatim. Layout, hierarchy, rhythm, and visual rendering are what gets redesigned.+- Each direction crystallizes one project-specific cadence / posture in `mode_behavior`: it may specialize one preset, fuse several modes into a multi-act sequence, or be genuinely novel. A catalog-based direction retains only the exact ids it actually uses; a novel direction invents no basis. One deck locks one `custom` value, never several simultaneous modes.+- No user structure or cadence → derive each whole solution from the confirmed `communication_intent`, `audience_outcome`, source texture, and delivery context, then project its custom mode. The three directions may share a catalog basis when that is honestly best; distinguish them through project-specific behavior or other fields instead of forcing different bases.-Record the confirmed mode and rationale in `design_spec.md` first, including the exact catalog basis when a selected custom uses one. Then project `- mode:` to `spec_lock.md`; for `custom`, also project `- mode_behavior:` and, only when catalog material is actually used, `- mode_references: <id>, <id>`. Executor has the complete mode catalog in its execution context; references preserve provenance and synthesis intent, while an unreferenced novel custom follows the behavior directly.+Record the confirmed mode and rationale in `design_spec.md` first, including the exact catalog basis when a selected custom uses one. Then project `- mode:` to `spec_lock.md`; for `custom`, also project `- mode_behavior:` and, only when catalog material is actually used, `- mode_references: <id>, <id>`. Executor reads only those exact references; an unreferenced novel custom follows the behavior directly.#### Layer 2 — Visual style-🚧 **GATE**: read [`visual-styles/_index.md`](./visual-styles/_index.md) plus all 18 sibling style files once as one deterministic, boundary-preserving batch before authoring the three directions.+🚧 **GATE**: before choosing a basis, read only [`visual-styles/_index.md`](./visual-styles/_index.md). After the three direction intents exist and their style reference ids are frozen, read only those exact sibling files once; a novel style reads none.The deck's **visual aesthetic** — shape language, decoration density, whitespace rhythm, typographic character, texture. Anchors downstream fields e (Color), f (Icon), g (Typography), h (Image). Lock one preset from the catalog, or `custom`.**Source**:-- User named a style (chat / template / beautify) → it is truth: map to the closest preset (or `custom` with a `visual_style_behavior` paragraph) and repeat that fixed value across all three directions. Keep the three whole solutions meaningful by varying only fields the user left open.-- No user description → author three project-fit whole solutions first, then project each solution's complete visual aesthetic. A projected value may be one preset or a `custom` synthesis; the directions may share catalog bases when their overall systems still differ meaningfully. Do not force different style ids, a safe-to-bold ladder, or one deliberately extreme option merely to manufacture variety. Give each direction a localized name and concise real-world outcome note; the Confirm UI derives three project-specific style candidates from those directions and then exposes all 18 base styles for manual selection.+- User named a style (chat / template / beautify) → it is truth: retain it as the required basis or inherited anchor in every custom behavior. Keep the three whole solutions meaningful by varying only fields the user left open; when visual variation is forbidden, the three style behaviors may be identical.+- No user description → author three project-fit whole solutions first, then project one complete custom aesthetic for each. Directions may share catalog bases when their overall systems still differ meaningfully. Do not force different bases, a safe-to-bold ladder, or one deliberately extreme option merely to manufacture variety. Give each direction a localized name and concise real-world outcome note; the Confirm UI exposes the three project-specific styles above all 18 fixed manual alternatives.-**Forbidden — a non-catalog name as `visual_style`**: the value MUST be an `id` from the visual-styles catalog or literal `custom`; bespoke prose belongs only in `visual_style_behavior`. A name that is **not** in that catalog is not a visual style — most often it is an image-rendering name from the `_index` "Paired rendering" column (`flat`, `vector-illustration`, `digital-dashboard`, `3d-isometric`, `corporate-photo`, …), which names the §h *illustration* family, not the deck's layout aesthetic. Do not borrow it. (Names that are intentionally **both** a style and its paired rendering — `glassmorphism`, `blueprint`, `editorial`, `dark-tech` — are valid styles because they *are* in the catalog.) Generic baseline words — `flat` / flat-design / 扁平 / modern / clean / simple / minimal — are **not** custom-worthy either: the whole system is flat by default (shadows discouraged), so map them to the closest preset (flat + grid → `swiss-minimal`; flat + rounded → `soft-rounded`; flat + dense → `brutalist`). Reserve a custom lock for an aesthetic no preset covers.+**Forbidden — a non-catalog name as `visual_style`**: every direction recommendation uses literal `custom` for `visual_style`; bespoke prose belongs only in `visual_style_behavior`, while optional `visual_style_references` contain only first-column catalog ids. A name from the `_index` "Paired rendering" column (`flat`, `vector-illustration`, `digital-dashboard`, `3d-isometric`, `corporate-photo`, …) is an image-rendering id, not a style reference. Generic words such as flat / modern / clean / simple / minimal are also insufficient behavior: use the index to choose an exact basis when applicable, then state the project-specific shape language, composition, density, whitespace, typography, and texture.**Carries no color.** A visual style governs how the deck's HEX (locked at `e`) is *used* — never which colors, same discipline as [`image-renderings`](./image-renderings/_index.md). When the deck has AI images, prefer the style's paired rendering so layout and illustration share one aesthetic.-Record the confirmed visual style and rationale in `design_spec.md` first, including the exact catalog basis when a selected custom uses one. Then project `- visual_style:` to `spec_lock.md`; for `custom`, also project `- visual_style_behavior:` and, only when catalog material is actually used, `- visual_style_references: <id>, <id>`. Executor has the complete style catalog in its execution context; references preserve provenance and synthesis intent, while an unreferenced novel custom follows the behavior directly.+Record the confirmed visual style and rationale in `design_spec.md` first, including the exact catalog basis when a selected custom uses one. Then project `- visual_style:` to `spec_lock.md`; for `custom`, also project `- visual_style_behavior:` and, only when catalog material is actually used, `- visual_style_references: <id>, <id>`. Executor reads only those exact references; an unreferenced novel custom follows the behavior directly.**Conditional template workspace**: When the Stage-1 template choice has been installed into `<project_path>/templates/`, read [`strategist-template.md`](./strategist-template.md) before completing Stage 2. Read the installed project-local spec and prototypes only; never reopen the library/external source root. The module owns the editable natural-language application plan, confirmed-value consumption, AI-authored prototype selection, internal reuse/adherence derivation, inherited design precedence, and structured-lock planning. This plan decides how to use the installed template, never which template to select. Bare names, style words, and free-design projects do not trigger it.@@ -214,7 +214,7 @@ See [`../templates/icons/README.md`](../templates/icons/README.md) for the curre### g. Typography Plan Confirmation (Font + Size)-🚧 **GATE**: The complete visual-style catalog is already loaded. Apply the projected preset's §2 Typography character, or resolve a custom synthesis under `visual_style_behavior` and its exact `visual_style_references`. The title carries the character; the body may remain neutral.+🚧 **GATE**: Apply the chosen custom behavior and only the detail files already loaded from its exact `visual_style_references`. The title carries the character; the body may remain neutral.**Family selection**:@@ -271,7 +271,7 @@ Formula policy and formula-asset planning are conditional. [`strategist-image.md**Always-on decision module; conditional resource extension**:-1. Before authoring Stage-2 directions, read [`strategist-image.md`](./strategist-image.md) plus [`image-renderings/_index.md`](./image-renderings/_index.md) and all 20 sibling rendering files once as one deterministic, boundary-preserving batch. Author one complete rendering candidate inside each direction before deciding whether `recommend.image_usage` includes AI.+1. Before authoring Stage-2 directions, read [`strategist-image.md`](./strategist-image.md) plus only [`image-renderings/_index.md`](./image-renderings/_index.md). After the three whole-direction intents exist and their rendering reference ids are frozen, read only those exact sibling files once and author one complete custom rendering inside each direction before deciding whether `recommend.image_usage` includes AI.2. Independently derive `recommend.image_usage` from source needs. Confirmed non-`none` sources activate the module's resource-planning sections and the image layout references; formulas activate the formula sections even when usage is `none`. Confirmed `none` without formulas writes no image rows, but does not erase the three recommendation-only rendering candidates.The module owns formula policy, AI rendering alternatives, acquisition paths, resource rows, prompt depth, page roles, and placement intent.@@ -393,7 +393,7 @@ Confirmation `d` locks two independent catalog items:- **Mode** — narrative skeleton: [`modes/_index.md`](./modes/_index.md) → `pyramid` / `narrative` / `instructional` / `showcase` / `briefing`.- **Visual style** — aesthetic: [`visual-styles/_index.md`](./visual-styles/_index.md) → presets + `custom`.-Strategist reads each index plus every sibling entry once as a deterministic batch before authoring the three complete directions. Executor independently reads both complete catalogs once in its execution context, then applies the confirmed value; `*_references` record only the actual basis of a custom synthesis (see [`generate-pptx`](../workflows/generate-pptx.md) Step 6).+Strategist first reads only the three indexes, freezes the bases for the three whole directions, then reads only the deduplicated referenced detail files before authoring their custom behaviors. Executor reads one locked preset file or the exact references of a selected custom; neither role globs a catalog (see [`generate-pptx`](../workflows/generate-pptx.md) Step 6).---diff --git a/skills/ppt-master/references/visual-styles/_index.md b/skills/ppt-master/references/visual-styles/_index.mdindex 664a5d8e..dd9d1ab9 100644--- a/skills/ppt-master/references/visual-styles/_index.md+++ b/skills/ppt-master/references/visual-styles/_index.md@@ -10,7 +10,7 @@ A **visual style** is how the deck **looks** — shape language, decoration dens## 1. Catalog-Each style keeps its own authoritative file with: shape & decoration, typography character, color-usage discipline (no HEX), texture / elevation, and the paired image-rendering. Every Default and Quick Generate run reads this index plus all 18 sibling style files once as one deterministic batch before choosing or realizing a direction. Keep the files separate and preserve their boundaries in the batch; exact `visual_style_references` identify the sources actually used by a custom direction, not which files enter context. The catalog mirrors [`image-renderings`](../image-renderings/_index.md): each style's "Paired rendering" names the illustration family that shares its aesthetic.+Each style keeps its own authoritative file with: shape & decoration, typography character, color-usage discipline (no HEX), texture / elevation, and the paired image-rendering. Read this index alone while choosing a direction. Only after a preset or custom bases are fixed may the active role read the selected sibling files: one file for a preset, every exact `visual_style_references` file for a catalog-based custom, and none for a novel custom. Never glob the directory or read an unselected sibling. The catalog mirrors [`image-renderings`](../image-renderings/_index.md): each style's "Paired rendering" names the illustration family that shares its aesthetic.> The **`visual_style` value is only ever a first-column `id`** (`swiss-minimal`, `editorial`, …). The "Paired rendering" column lists **image-rendering** names (`flat`, `minimalist-swiss`, `digital-dashboard`, …) — never treat one of those as the `visual_style`. Default records rendering under confirmation h; Quick keeps the selected rendering only in active context and any required image manifest.>@@ -92,11 +92,11 @@ Each style keeps its own authoritative file with: shape & decoration, typography## 3. Escape hatch — `custom`-Each coordinated Default Stage-2 direction authors one complete visual aesthetic after comparing the full catalog. It may resolve to a preset or to a visible, non-empty `custom` synthesis whose paragraph names shape language, composition geometry, decoration density, whitespace, typographic character, and texture — **no HEX, no color names as values**. A template-backed synthesis stays inside the inherited identity and confirmed application plan. Record the confirmed current aesthetic in the Design Spec first, then project `- visual_style: custom` plus `- visual_style_behavior:` when applicable. Do not create a separate fourth AI-custom proposal beside the three coordinated directions.+Each coordinated Default Stage-2 direction authors one visible, non-empty `custom` aesthetic whose paragraph names project-specific shape language, composition geometry, decoration density, whitespace, typographic character, and texture — **no HEX, no color names as values**. Use this index to freeze any catalog bases before reading their detail files. A template-backed synthesis stays inside the inherited identity and confirmed application plan. Record the confirmed current aesthetic in the Design Spec first, then project `- visual_style: custom` plus `- visual_style_behavior:`. The 18 fixed styles remain lower-level single-select alternatives; do not create a fourth AI-custom proposal.-Quick does not display a candidate spectrum. It compares the fully loaded catalog, resolves the best-fit preset or one warranted custom behavior directly, and persists nothing.+Quick does not display a candidate spectrum. It reads this index, resolves one preset or custom behavior, then reads only the selected detail files and persists nothing.-**Mandatory — name every catalog source actually used**: If a custom direction combines or borrows existing styles, name their exact ids after comparing the complete catalog. Default persists those ids as `visual_style_references`; Quick retains them only in active context. Do not attach references merely because they are adjacent in the catalog. A genuinely new aesthetic names no catalog source.+**Mandatory — select before detail reading**: Freeze every catalog source actually used from this index, then read only those exact files before writing the behavior. Default persists those ids as `visual_style_references`; Quick retains them only in active context. Do not open candidates for comparison after this gate or attach references merely because they are adjacent. A genuinely new aesthetic names and reads no catalog source.---@@ -104,7 +104,7 @@ Quick does not display a candidate spectrum. It compares the fully loaded catalo| Active profile | Use ||---|---|-| Default Generate | Strategist and Executor each read this index plus every sibling style file once per valid role context. Strategist authors three coordinated project directions, records the confirmed current style in `design_spec.md`, and projects it to `spec_lock.md`; Executor applies that selected value from the already-loaded catalog. |-| Quick Generate | The current main agent reads this index plus every sibling style file once, resolves one project-specific direction without interaction, and retains the full catalog in active context without Design Spec/lock. |+| Default Generate | Strategist reads only this index while mapping three whole solution intents, freezes each custom direction's exact bases, then reads only their deduplicated detail files. Executor reads the confirmed preset file or exact custom references. |+| Quick Generate | The current main agent reads only this index while deciding, then reads the resolved preset or exact custom bases and retains that one direction without Design Spec/lock. |**Resolution scope**: deck-wide (one style per deck). It anchors taste as a **reference**, not a whitelist — pages may deviate with reason.diff --git a/skills/ppt-master/scripts/confirm_ui/server.py b/skills/ppt-master/scripts/confirm_ui/server.pyindex 78ec11f9..6b1b51e9 100644--- a/skills/ppt-master/scripts/confirm_ui/server.py+++ b/skills/ppt-master/scripts/confirm_ui/server.py@@ -1520,7 +1520,7 @@ def _stage2_design_directions_error(*,main_language: object = '',) -> Optional[str]:- """Require exactly three complete top-down Stage 2 design systems."""+ """Require exactly three complete top-down custom Stage 2 design systems."""main_language = main_language or _recommendation_language(recommendations)directions = recommendations.get('design_directions')if isinstance(directions, dict):@@ -1544,13 +1544,13 @@ def _stage2_design_directions_error(for field in ('mode', 'visual_style', 'icons'):if not isinstance(candidate.get(field), str) or not candidate[field].strip():return f'{label}.{field} must be non-empty'- if candidate['mode'] == 'custom' and not _localized_text_present(- candidate, 'mode_behavior'- ):+ if candidate['mode'] != 'custom':+ return f'{label}.mode must be custom'+ if not _localized_text_present(candidate, 'mode_behavior'):return f'{label}.mode=custom requires non-empty localized mode_behavior'- if candidate['visual_style'] == 'custom' and not _localized_text_present(- candidate, 'visual_style_behavior'- ):+ if candidate['visual_style'] != 'custom':+ return f'{label}.visual_style must be custom'+ if not _localized_text_present(candidate, 'visual_style_behavior'):return (f'{label}.visual_style=custom requires non-empty localized ''visual_style_behavior'@@ -1573,17 +1573,15 @@ def _stage2_design_directions_error(rendering = str(image_strategy.get('rendering') or '').strip()if not rendering:return f'{label}.image_strategy.rendering must be non-empty'- if rendering != 'custom' and rendering not in _ai_rendering_ids():- return f'{label}.image_strategy.rendering is not a known preset: {rendering}'+ if rendering != 'custom':+ return f'{label}.image_strategy.rendering must be custom'for prose_field in ('name', 'visual', 'mood'):if not _localized_text_present(image_strategy, prose_field):return (f'{label}.image_strategy requires non-empty localized 'f'{prose_field}')- if rendering == 'custom' and not _localized_text_present(- image_strategy, 'behavior'- ):+ if not _localized_text_present(image_strategy, 'behavior'):return (f'{label}.image_strategy.rendering=custom requires non-empty ''localized behavior'@@ -2206,6 +2204,11 @@ def _wait_result_status()return 2logger.info('confirmation stage=%s received: %s', target_stage, result_file)+ if target_stage == 'stage1':+ logger.info(+ '[NEXT] Stage 1 is intermediate: complete the template handoff, '+ 'author fresh Stage 2, then wait for final confirmation.'+ )return 0if _result_stage_number(current_stage) > _result_stage_number(target_stage):logger.error(diff --git a/skills/ppt-master/scripts/confirm_ui/static/app.js b/skills/ppt-master/scripts/confirm_ui/static/app.jsindex 3118a926..eba3f7ad 100644--- a/skills/ppt-master/scripts/confirm_ui/static/app.js+++ b/skills/ppt-master/scripts/confirm_ui/static/app.js@@ -68,7 +68,7 @@direction_active: "Applied",direction_adjusted: "Adjusted",direction_reset_hint: "Click to apply or restore this complete direction.",- scheme_component_options: "Projected options from the three complete directions",+ scheme_component_options: "Project-specific custom choices · select a card to edit",sec_template_application: "Template application",template_application_hint: "The AI recommends how to apply the installed template to this deck. Revise the plan directly in natural language.",placeholder_template_application: "Describe which template pages or prototypes to use, skip, repeat, or reorder; what must stay; and what may be replaced or reorganized.",@@ -250,7 +250,7 @@direction_active: "適用中",direction_adjusted: "調整済み",direction_reset_hint: "クリックすると、この全体案を適用または元の状態に戻します。",- scheme_component_options: "3つの全体案から展開した候補",+ scheme_component_options: "プロジェクト専用カスタム案 · カードを選んで編集",sec_template_application: "テンプレートの適用方法",template_application_hint: "AIが現在の内容に合わせたテンプレートの使い方を提案します。自然言語で直接修正できます。",placeholder_template_application: "使用・省略・反復・並べ替えするページやプロトタイプ、保持する要素、差し替え・再構成できる内容を記述します。",@@ -432,7 +432,7 @@direction_active: "已应用",direction_adjusted: "已调整",direction_reset_hint: "点击可应用或恢复这套完整方案。",- scheme_component_options: "由三套完整方案分解出的候选",+ scheme_component_options: "项目专属自定义方案 · 选中卡片后可编辑",sec_template_application: "模板应用方式",template_application_hint: "AI 会根据当前内容推荐如何使用已安装模板;你可以直接用自然语言修改。",placeholder_template_application: "说明使用、跳过、重复或重排哪些模板页面/原型,哪些内容必须保留,哪些可以替换或重组。",@@ -688,6 +688,7 @@var STATE = {};var ACTIVE_DIRECTION_ID = "";var ACTIVE_DIRECTION_BASELINE = "";+ var ACTIVE_COMPONENT_DIRECTION_IDS = {};var refreshDesignDirectionState = function () {};var DIRECTION_COMPONENT_PAINTERS = [];@@ -1966,15 +1967,18 @@function applyDesignDirection(candidate, index, shouldRender) {candidate = candidate || {};+ var directionId = designDirectionId(candidate, index);if (candidate.mode) {STATE.mode = candidate.mode;STATE.mode_behavior = candidate.mode === "custom" ?directionBehavior(candidate, "mode") : "";+ ACTIVE_COMPONENT_DIRECTION_IDS.mode = directionId;}if (candidate.visual_style) {STATE.visual_style = candidate.visual_style;STATE.visual_style_behavior = candidate.visual_style === "custom" ?directionBehavior(candidate, "visual_style") : "";+ ACTIVE_COMPONENT_DIRECTION_IDS.visual_style = directionId;}if (candidate.color) {STATE.color = {@@ -1995,8 +1999,9 @@if (candidate.icons) STATE.icons = normalizeRecId("icons", candidate.icons);if (candidate.image_strategy) {STATE.image_strategy = normalizedImageStrategy(candidate.image_strategy);+ ACTIVE_COMPONENT_DIRECTION_IDS.image_strategy = directionId;}- ACTIVE_DIRECTION_ID = designDirectionId(candidate, index);+ ACTIVE_DIRECTION_ID = directionId;ACTIVE_DIRECTION_BASELINE = directionStateSignature(candidate);if (shouldRender !== false) renderAll();}@@ -2064,7 +2069,7 @@host.appendChild(sec);}- function directionComponentSelected(candidate, field) {+ function directionComponentMatchesAuthored(candidate, field) {if (field === "mode") {return STATE.mode === candidate.mode &&(candidate.mode !== "custom" ||@@ -2083,7 +2088,13 @@return false;}- function applyDirectionComponent(candidate, field) {+ function directionComponentSelected(candidate, field, index) {+ var activeId = ACTIVE_COMPONENT_DIRECTION_IDS[field];+ if (activeId) return activeId === designDirectionId(candidate, index);+ return directionComponentMatchesAuthored(candidate, field);+ }++ function applyDirectionComponent(candidate, field, index) {if (field === "mode") {STATE.mode = candidate.mode;STATE.mode_behavior = candidate.mode === "custom" ?@@ -2095,9 +2106,32 @@} else if (field === "image_strategy") {STATE.image_strategy = normalizedImageStrategy(candidate.image_strategy || {});}+ ACTIVE_COMPONENT_DIRECTION_IDS[field] = designDirectionId(candidate, index);renderAll();}+ function directionComponentIsCustom(candidate, field) {+ if (field === "image_strategy") {+ return candidate && candidate.image_strategy &&+ candidate.image_strategy.rendering === "custom";+ }+ return candidate && candidate[field] === "custom";+ }++ function setDirectionComponentBehavior(field, value) {+ if (field === "mode") {+ STATE.mode = "custom";+ STATE.mode_behavior = value;+ } else if (field === "visual_style") {+ STATE.visual_style = "custom";+ STATE.visual_style_behavior = value;+ } else if (field === "image_strategy") {+ STATE.image_strategy = normalizedImageStrategy(STATE.image_strategy || {});+ STATE.image_strategy.rendering = "custom";+ STATE.image_strategy.behavior = value;+ }+ }+function directionComponentValueLabel(candidate, field) {var value = candidate && candidate[field];if (field === "image_strategy") {@@ -2118,6 +2152,13 @@return localized(candidate, "note") || "";}+ function directionComponentEditableBehavior(candidate, field) {+ if (field === "image_strategy") {+ return normalizedImageStrategy(candidate.image_strategy || {}).behavior || "";+ }+ return directionBehavior(candidate, field);+ }+function renderDirectionComponentCandidates(parent, field) {var candidates = designDirectionCandidates().filter(function (candidate) {return candidate && candidate[field];@@ -2142,18 +2183,60 @@card.appendChild(preview);}var note = directionComponentNote(candidate, field);- if (note) card.appendChild(el("div", "color-note", note));+ var noteNode = note ? el("div", "color-note", note) : null;+ if (noteNode) card.appendChild(noteNode);+ var editor = null;+ if (directionComponentIsCustom(candidate, field)) {+ editor = el("textarea", "text-input scheme-component-editor");+ setNaturalInputDirection(editor);+ editor.rows = 4;+ editor.value = directionComponentEditableBehavior(candidate, field);+ editor.placeholder = t(field === "mode" ? "mode_behavior_placeholder" :+ (field === "visual_style" ? "visual_style_behavior_placeholder" :+ "image_strategy_custom_placeholder"));+ editor.style.display = "none";+ editor.addEventListener("click", function (event) {+ event.stopPropagation();+ });+ editor.addEventListener("input", function () {+ setDirectionComponentBehavior(field, editor.value);+ if (field === "image_strategy") refreshImageStrategyPreview();+ refreshDesignDirectionState();+ refreshDirectionComponentStates();+ });+ card.appendChild(editor);+ }card.addEventListener("click", function () {- applyDirectionComponent(candidate, field);+ applyDirectionComponent(candidate, field, index);+ });+ entries.push({+ candidate: candidate,+ index: index,+ card: card,+ note: noteNode,+ editor: editor});- entries.push({ candidate: candidate, card: card });grid.appendChild(card);});var paint = function () {entries.forEach(function (entry) {- entry.card.classList.toggle(- "selected", directionComponentSelected(entry.candidate, field)+ var selected = directionComponentSelected(+ entry.candidate, field, entry.index);+ var adjusted = selected &&+ !directionComponentMatchesAuthored(entry.candidate, field);+ entry.card.classList.toggle("selected", selected);+ entry.card.classList.toggle("adjusted", adjusted);+ if (entry.editor) {+ entry.editor.style.display = selected ? "block" : "none";+ if (selected && document.activeElement !== entry.editor) {+ var current = field === "mode" ? STATE.mode_behavior :+ (field === "visual_style" ? STATE.visual_style_behavior :+ ((STATE.image_strategy || {}).behavior || ""));+ entry.editor.value = current;+ }+ }+ if (entry.note) entry.note.style.display = selected ? "none" : "block";});};DIRECTION_COMPONENT_PAINTERS.push(paint);@@ -2172,6 +2255,7 @@function renderCurrentDirectionCustomEditor(parent, field, stateKey, placeholderKey) {if (STATE[field] !== "custom") return null;+ if (ACTIVE_COMPONENT_DIRECTION_IDS[field]) return null;var source = currentDirectionCustomCandidate(field, stateKey);if (!source && customCandidateBehavior(field)) return null;var block = el("div", "subfield direction-custom-editor");@@ -2205,7 +2289,10 @@enumField(sec, CAT.modes, recOrFirst("mode", CAT.modes),function () { return STATE.mode; }, function (v) {STATE.mode = v;+ ACTIVE_COMPONENT_DIRECTION_IDS.mode = "";if (v !== "custom") STATE.mode_behavior = "";+ refreshDesignDirectionState();+ refreshDirectionComponentStates();if (directionCustomEditor) {directionCustomEditor.style.display = v === "custom" ? "block" : "none";}@@ -2236,7 +2323,10 @@enumField(sec, CAT.visual_styles, recOrFirst("visual_style", CAT.visual_styles),function () { return STATE.visual_style; }, function (v) {STATE.visual_style = v;+ ACTIVE_COMPONENT_DIRECTION_IDS.visual_style = "";if (v !== "custom") STATE.visual_style_behavior = "";+ refreshDesignDirectionState();+ refreshDirectionComponentStates();if (directionCustomEditor) {directionCustomEditor.style.display = v === "custom" ? "block" : "none";}@@ -3199,6 +3289,7 @@function selectImageStrategy(idx) {if (!strategyCands[idx]) return;STATE.image_strategy = normalizedImageStrategy(strategyCands[idx]);+ ACTIVE_COMPONENT_DIRECTION_IDS.image_strategy = "";presetSelect.value = String(idx);if (customCard) customCard.classList.remove("selected");if (currentCustomEditor) currentCustomEditor.style.display = "none";@@ -3297,10 +3388,13 @@selectCustomImageStrategy = function () {STATE.image_strategy = normalizedImageStrategy(customStrategy);+ ACTIVE_COMPONENT_DIRECTION_IDS.image_strategy = "";presetSelect.value = "";customCard.classList.add("selected");syncCustomStrategy(true);refreshImageStrategyPreview();+ refreshDesignDirectionState();+ refreshDirectionComponentStates();};customInput.addEventListener("click", function (event) { event.stopPropagation(); });@@ -3317,7 +3411,8 @@strategySub.appendChild(customCard);}- if (!customCard && STATE.image_strategy &&+ if (!customCard && !ACTIVE_COMPONENT_DIRECTION_IDS.image_strategy &&+ STATE.image_strategy &&STATE.image_strategy.rendering === "custom") {var customEditorField = el("div", "subfield image-strategy-current-custom");customEditorField.appendChild(el("div", "subfield-label", t("custom")));diff --git a/skills/ppt-master/scripts/confirm_ui/static/style.css b/skills/ppt-master/scripts/confirm_ui/static/style.cssindex 4db9c44b..3fb78fc2 100644--- a/skills/ppt-master/scripts/confirm_ui/static/style.css+++ b/skills/ppt-master/scripts/confirm_ui/static/style.css@@ -495,6 +495,16 @@ textarea.text-input { resize: vertical; line-height: 1.5; }flex: 1 0 calc((100% - 20px) / 3);min-width: 190px;}+.scheme-component-card.adjusted {+ border-color: #d97706;+ background: #fffbeb;+}+.scheme-component-editor {+ margin-top: 8px;+ min-height: 84px;+ resize: vertical;+ cursor: text;+}.scheme-component-card .design-direction-preview { margin-top: 8px; }.design-direction-preview {width: 100%;diff --git a/skills/ppt-master/scripts/docs/confirm_ui.md b/skills/ppt-master/scripts/docs/confirm_ui.mdindex 0f467f35..b82a9636 100644--- a/skills/ppt-master/scripts/docs/confirm_ui.md+++ b/skills/ppt-master/scripts/docs/confirm_ui.md@@ -307,15 +307,17 @@ its file time is newer than the handoff.The following fields belong to the Strategist stages, not to thetemplate-selection receipt.-- **Enumerable + custom** — canvas / icons retain blank manual inputs. Mode and visual style first show the three project-specific values projected from the complete directions, then the full base catalog. Any projected `custom` variant keeps its own visible identity and behavior even though a selected result writes literal `custom` plus its behavior sibling.+- **Enumerable + custom** — canvas / icons retain blank manual inputs. Mode and visual style first show three project-specific `custom` values projected from the complete directions, then the full fixed base catalog as conservative single-select alternatives. Selecting a projected card expands its behavior editor in place; edits change only the current value, while clicking the owning whole-direction card restores the authored text.- **Visual examples for hard-to-name choices** — the full-screen confirmation page loads real SVG page samples from `static/style_previews/` for `visual_style`, and renders real sample SVGs from `templates/icons` for `icons`. These thumbnails make style and icon-library choices visually comparable before the user locks them. Preview copy is fixed role text (big title / section title / body / points), not project content from recommendation files, so users compare visual treatment rather than copywriting. These previews are a confirmation aid only: they do not add fields to recommendation stage files or `result.json`, and they do not replace the later Step 6 live preview.- **Image usage multi-select** — image sources are selected as one or more catalog ids: `ai` = AI-generated, `web` = Web-sourced, `provided` = User-provided, `placeholder` = Placeholder, `none` = No images. `none` is exclusive. A confirmed non-`none` set is the allowed acquisition-source boundary, not a requirement to use every selected source; only explicit `image_notes` wording can require a source, asset, or page role. Recommendation and result values may be a legacy single string, but new files should use an array. When several sources are recommended, write the source ids to `recommend.image_usage` and write the actual usage strategy to `image_notes`, not a custom prose value.- **Closed enumerable** — PPT reading mode (`delivery_purpose` compatibility key), formula policy / generation mode / refine spec, plus AI source only when image usage includes `ai`. These have no Custom box; out-of-catalog values snap back to the recommended option.- **Proactive execution booleans** — Final Stage 2 carries top-level `proactive_speaker_notes`, `proactive_custom_animations`, and `proactive_narration_audio` values. Defaults are `true`, `false`, and `false`, respectively. They control what the Agent does proactively only when the user has not explicitly instructed otherwise; the latest explicit user instruction always wins. These three values are raw confirmation evidence: the UI and server neither couple nor rewrite them, and every boolean combination is valid. When narration audio is enabled, Strategist later resolves the effective Speaker Notes outcome to enabled and records `Narration Audio dependency` as its Design Spec provenance. Disabling proactive custom animation does not suppress the Strategist's advisory motion recommendations.- **Open prose** — `audience`, `communication_intent`, `audience_outcome`, `core_message`, `delivery_context`, `artifact_afterlife`, `content_divergence`, and `page_count`. `communication_intent` may carry several purposes plus priority / sequence; common paths appear only as help text. `delivery_context` states one primary presenter-led / reader-led / hybrid / recorded-self-running context plus optional secondary use; a hybrid recommendation names which context leads. `content_divergence` is the source-treatment axis. `page_count` may be a range here; Strategist resolves the exact §IX roster, leaving Executor no pagination latitude.-- **Coordinated generative directions** — `design_directions` carries exactly three complete candidates authored top-down from the project contract. Each has a unique stable id and bundles mode, visual style, color, typography, icon id, and generated-image rendering regardless of recommended image source. All three must be viable and meaningfully distinguishable as whole solutions; they do not need different catalog ids or forced safe / shifted / bold archetypes. The page can still render legacy top-level `color`, `typography`, and `image_strategy` candidates, but new staged recommendations use the coordinated bundle.+- **Coordinated generative directions** — `design_directions` carries exactly three complete candidates authored top-down from the project contract. Each has a unique stable id and bundles `custom` mode, `custom` visual style, color, typography, icon id, and `custom` generated-image rendering regardless of recommended image source. All three must be viable as whole solutions; they do not need different catalog bases or forced safe / shifted / bold archetypes. The page can still render legacy top-level `color`, `typography`, and `image_strategy` candidates, but new staged recommendations use the coordinated bundle.-Direction-local custom projections apply to mode, visual style, and generated-image rendering; a selected custom value cannot be blank. Legacy standalone `custom_candidates` remain readable but are optional and are not authored in new files. Color / typography keep their existing manual Custom cards. Image usage uses source ids plus `image_notes`; closed sets have no Custom path.+Direction-local custom projections apply to mode, visual style, and generated-image rendering; all three are editable after selection and a selected custom value cannot be blank. The original recommendation remains immutable so a whole-direction click can reset every edited component. Legacy standalone `custom_candidates` remain readable but are optional and are not authored in new files. Color / typography keep their existing manual Custom cards. Image usage uses source ids plus `image_notes`; closed sets have no Custom path.++**Stage-2 catalog read gate.** Before choosing component bases, Strategist reads only `modes/_index.md`, `visual-styles/_index.md`, and `image-renderings/_index.md`. It authors the three whole solution intents first, freezes every basis id from those indexes, and only then reads the deduplicated selected detail files before completing the custom behaviors. Unselected sibling files never enter context; a novel custom reads none.**Stage-1 current-value contract.** Each editable prose box starts with the Strategist's recommendation, if one exists. The user may retain, revise, or clear it; no Stage-1 prose field has a non-empty validation gate. On confirmation, the browser submits the current strings and the server preserves them through every later stage and the final `result.json`, including `""`. Blank means no explicit user constraint and may cause downstream default judgment, but it never causes the initial recommendation to be restored. A profile-declared `locked: true` field is read-only and remains the sole exception.@@ -446,8 +448,9 @@ corresponding direct values (`formula_policy`, `generation_mode`, boolean"lang": "zh","recommend": {"delivery_purpose": "balanced",- "mode": "pyramid",- "visual_style": "swiss-minimal",+ "mode": "custom",+ "visual_style": "custom",+ "image_strategy": "custom","image_usage": ["ai", "provided"],"image_ai_path": "auto","formula_policy": "mixed",@@ -466,8 +469,10 @@ corresponding direct values (`formula_policy`, `generation_mode`, boolean"id": "executive-clarity","name_zh": "稳妥专业","note_zh": "像成熟咨询简报",- "mode": "pyramid",- "visual_style": "swiss-minimal",+ "mode": "custom",+ "mode_behavior_zh": "以 pyramid 的结论先行为主轴,在风险段引入 narrative 的局势—张力—解法转折;标题保持判断句,每章以可执行结论收束。",+ "visual_style": "custom",+ "visual_style_behavior_zh": "以 swiss-minimal 的精确栅格和大留白为基底,融入 editorial 的细规则、边注与证据层级;标题锐利,正文中性,装饰只用于标记推理关系。","icons": "tabler-outline","color": { "name_zh": "冷静专业", "palette": {"background": "#FFFFFF", "secondary_bg": "#F4F6F8",@@ -481,10 +486,11 @@ corresponding direct values (`formula_policy`, `generation_mode`, boolean"body_size": 24},"image_strategy": {- "name_zh": "克制矢量",- "rendering": "vector-illustration",- "visual_zh": "扁平矢量、实色块、少阴影",- "mood_zh": "稳定、可信、克制"+ "name_zh": "编辑式证据图",+ "rendering": "custom",+ "visual_zh": "简化矢量主体配合编辑式注释与局部材质对比",+ "mood_zh": "审慎、可信,像调查报道中的证据插图",+ "behavior_zh": "融合 vector-illustration 的清晰轮廓与 editorial 的证据编排;使用平面色块、细规则和局部纸张纹理,避免写实景深与装饰性渐变,颜色继承当前演示文稿角色。"}}]@@ -492,11 +498,11 @@ corresponding direct values (`formula_policy`, `generation_mode`, boolean}```-The example shows one candidate's complete shape; the actual array repeats that shape for exactly three candidates. Every candidate requires a unique stable `id`, mode, visual style, icon value, complete six-role palette, complete heading/body stack, and complete image strategy even when `recommend.image_usage` excludes AI. Custom mode/style/rendering values require their localized behavior sibling. Legacy grids remain readable only with three complete palettes and complete typography.+The example shows one candidate's complete shape; the actual array repeats that shape for exactly three candidates. Every candidate requires a unique stable `id`, literal `custom` mode/style/rendering with localized behavior, an icon value, complete six-role palette, complete heading/body stack, and complete image strategy even when `recommend.image_usage` excludes AI. The server rejects any fixed mode/style/rendering inside a new direction. Legacy grids remain readable only with three complete palettes and complete typography.-- `recommend.*` names each recommended id. New mode / style values use a catalog id or literal `custom`; arbitrary prose values are legacy-only. Use `recommend.image_strategy: "custom"` only when an explicit user-supplied image direction should start selected. Missing recommendations fall back to the normal preset. Legacy aliases remain accepted; new files write canonical ids.+- `design_directions.selected` owns the initial complete bundle. New direction mode/style/rendering values are always literal `custom`; prose stays in the required behavior sibling. `recommend.*` remains a compatibility hint and may mirror `custom`, but it never replaces the selected direction. Legacy aliases remain accepted; new files write canonical ids.- The three proactive-execution fields are top-level boolean `{ "value": ... }` objects, not catalog ids. Omitted fields use `true / false / false` for notes / custom animation / narration audio. These are absence-of-instruction defaults, not permission to override the user's latest explicit request. Preserve all three raw values independently through `result.json`; do not couple or rewrite them. Strategist derives effective Speaker Notes as enabled when audio is `true` and records `Narration Audio dependency` as provenance in the Design Spec. `proactive_custom_animations: false` leaves Strategist animation suggestions unchanged; it only prevents unrequested custom-animation execution.-- `custom_candidates` is an optional legacy recommendation-only shape. New files place every project-specific preset or custom variant inside one of the three `design_directions`; this preserves three distinct UI identities even when several variants serialize as `custom`. A custom behavior names exact catalog ids only when it actually uses them as synthesis bases. The UI rejects a selected blank and omits unselected candidates from `result.json`. Template-backed variants obey inherited identity, prototype capacity, and `template_application`.+- `custom_candidates` is an optional legacy recommendation-only shape. New files place all three project-specific variants inside `design_directions`; each remains separately selectable and becomes editable in place. A custom behavior names exact catalog ids only when it actually uses them as synthesis bases. The UI rejects a selected blank and submits only the edited current value. Template-backed variants obey inherited identity, prototype capacity, and `template_application`.- Seed `audience`, `communication_intent`, `audience_outcome`, and `delivery_context` when evidence supports them; users need not supply them, and every Stage-1 prose field may end blank. The contract and `primary_language` stay in `result.json` and `design_spec.md`; `spec_lock.md communication` receives `primary_language`, compact `audience` / `objective` / `core_message`, and reading mode. `communication_intent` may preserve multiple purposes and priority/sequence; never add a `primary_job` enum.- Do not write `recommend.template_reuse_scope` or `recommend.template_adherence`. Strategist records those internal exporter values later in `spec_lock.md` after inspecting the actual template and current content.- For a confirmed templates-mode handoff, write one editable prose field as top-level `template_application.value`. It summarizes **how to use** the already selected project-local template: actual page/prototype use and preservation/reorganization decisions. It never chooses, changes, or reinstalls a workspace. Omit it for free design. The UI returns the current string through final Stage 2; Strategist then persists the final effective plan as `- **Template Application**: ...` in `design_spec.md §I`, which Executor reads from the retained Design Spec. Never replace it with internal reuse/adherence ids or a fixed option menu.@@ -520,8 +526,8 @@ Template-mode-only Stage-2 fragment:- **Per-role size override** (parallel to color's per-role HEX override): besides `body_size`, the page exposes editable inputs for `title` / `subtitle` / `annotation`. The browser applies one documented deterministic dependency chain: `reading mode → body baseline → unpinned role sizes` (role ramp: `body ×` the §g ratios). Changing reading mode updates the body and all unpinned roles locally; changing body updates unpinned roles locally. Editing body or a role pins that value, so later reading-mode changes do not overwrite it. A font-only selection preserves current sizes; applying a complete direction restores that direction's typography baseline and derived unpinned sizes, because the top card is an explicit reset action. This is a browser-only state update: it performs no fetch and asks the backend to author no new recommendations. Each role input is labelled as px and shows an approximate pt equivalent (`1px = 0.75pt`) for orientation. The final values are written to `result.json` as `typography.sizes: { "title", "subtitle", "annotation" }` in **px** — every canvas, no pt and no `sizes_pt` provenance. These confirmed values are Strategist input anchors: the completed page plan may add recurring roles, and downstream execution owns bounded per-occurrence treatment. Candidate `sizes` remain accepted for compatibility, but the fresh Stage-2 baseline is normalized through the same local ramp before first render.- **`delivery_purpose` compatibility key / Reading mode** (enumerable, PPT only) decides where meaning is carried, not merely how large type is: `text` makes pages self-contained with complete sentences, short prose, captions, tables, and necessary detail; `balanced` shares explanation between page and presenter; `presentation` uses one idea, concise claims, and visual evidence while speech / notes carry the detail. It therefore governs page grammar, granularity, density / rhythm, and note burden. Reading-mode cards intentionally show **no px value**; the typography section owns the separately visible body / role sizes and applies any local default. It is surfaced in Stage 2 beside the visual system, separate from communication intent. `recommend.delivery_purpose` pre-selects one; `result.json` retains the key, while `spec_lock.md` uses canonical `consumption_mode`. Non-PPT canvases omit it.- **Combined style preview** — a compact live "overall impression" strip sits just above the color section and is **sticky**: it pins under the topbar so it stays visible while the user scrolls through the color / icon / typography sections, keeping the picking controls and their combined effect on screen together. It applies the currently selected color palette **and** typography (heading sample in `primary` over `background`, body sample in `body_text`, an `accent` bar, a `secondary_bg` chip) and repaints on every color / HEX-override / font / `body_size` change. It does not replace the per-candidate swatches or font samples (those stay for picking); it is deliberately an abstract style chip, **not** a slide-layout preview — page layout preview remains the live-preview server's job (Step 6). No schema field; it derives entirely from the existing color + typography selections.-- **Generated-image direction** appears only for current `image_usage: ai`, but all three project candidates already exist in `design_directions` before that toggle. Turning AI on reveals those candidates immediately without a backend rerun, followed by the 20 system preset styles. Direction-local custom variants remain separately identifiable and editable; a preset submits its id, while Custom submits `rendering: "custom"` + non-empty `behavior`. Turning AI off omits `image_strategy` from the final result without deleting the authored recommendation candidates. Catalog-based custom behavior names exact ids for optional `image_rendering_references`; a novel behavior has none. The left preview follows selection. No image palette is written; deck colors remain authoritative, and legacy `image_strategy.palette` is ignored.-- **`design_directions`** is the canonical Stage-2 starting set: exactly three top-down, project-fit bundles with stable ids, localized copy, mode, style, icons, always-present image strategy, complete language-aware typography, and HEX `background`, `secondary_bg`, `primary`, `accent`, `secondary_accent`, `body_text`. Clicking a card applies every field it owns; lower controls may then diverge and the card shows an adjusted state. Clicking the same or another card reapplies that immutable bundle. `result.json` stores the current flattened components, never a direction id.+- **Generated-image direction** appears only for current `image_usage: ai`, but all three custom project candidates already exist in `design_directions` before that toggle. Turning AI on reveals those candidates immediately without a backend rerun, followed by the 20 fixed system styles. Selecting a project candidate expands its behavior editor in that card; a fixed preset submits its id, while a project candidate submits `rendering: "custom"` + edited non-empty `behavior`. Turning AI off omits `image_strategy` from the final result without deleting the authored recommendation candidates. Catalog-based custom behavior names exact ids for optional `image_rendering_references`; a novel behavior has none. The left preview follows selection. No image palette is written; deck colors remain authoritative, and legacy `image_strategy.palette` is ignored.+- **`design_directions`** is the canonical Stage-2 starting set: exactly three top-down, project-fit bundles with stable ids, localized copy, custom mode/style/rendering, icons, complete language-aware typography, and HEX `background`, `secondary_bg`, `primary`, `accent`, `secondary_accent`, `body_text`. Clicking a card applies every field it owns; projected custom fields can then be edited in place and all lower controls may diverge. The card shows an adjusted state, while clicking the same or another whole direction reapplies its immutable authored bundle. `result.json` stores the edited current components, never a direction id.- `recommend.generation_mode` and `refine_spec` mirror [`generate-pptx`](../../workflows/generate-pptx.md) Step 4. `split` / `true` are explicit opt-ins. Refinement adds no UI stage: after Gate 1 it stops before the lock for unrestricted chat revision until approval.- `content_divergence` is a **free-text** Stage-1 source-treatment field. Blank means a balanced default; facts stay sourced at every level. Strategist consumes it while authoring §IX and records it in `design_spec.md §I`; it is not written to `spec_lock.md`. Beautify sends `{ "value": "keep source wording and page structure verbatim", "locked": true }`, so the UI displays it read-only and the server restores it on every staged submit. Template-fill does not use this confirmation flow and does not surface it.- `lang` is the soft UI-language default (`zh` / `en` / `ja`); the persisted user choice wins. It never sets `primary_language`.@@ -540,8 +546,10 @@ Template-mode-only Stage-2 fragment:"delivery_context": "Primary: presenter-led 20-minute leadership review; secondary: reader-led approval copy shared afterward","artifact_afterlife": "Approval record, hand-off reference, and audit trail","content_divergence": "freely restructure and expand within the source",- "mode": "pyramid",- "visual_style": "swiss-minimal",+ "mode": "custom",+ "mode_behavior": "...",+ "visual_style": "custom",+ "visual_style_behavior": "...","color": { "name": "...", "palette": { "background": "#...", "secondary_bg": "#...", "primary": "#...", "accent": "#...", "secondary_accent": "#...", "body_text": "#..." } },"icons": "tabler-outline","typography": { "name": "...", "heading": { "primary": "...", "english": "...", "css": "..." }, "body": { "primary": "...", "english": "...", "css": "..." }, "body_size": 24, "body_size_unit": "px", "sizes": { "title": 42, "subtitle": 32, "annotation": 18 } },@@ -550,7 +558,7 @@ Template-mode-only Stage-2 fragment:"image_usage": ["ai", "provided"],"image_notes": "封面和章节页用 AI 主视觉;产品页优先用户素材,缺口页可用占位符。","image_ai_path": "auto",- "image_strategy": { "name": "方案 A", "rendering": "vector-illustration", "visual": "...", "mood": "..." },+ "image_strategy": { "name": "方案 A", "rendering": "custom", "visual": "...", "mood": "...", "behavior": "..." },"proactive_speaker_notes": true,"proactive_custom_animations": false,"proactive_narration_audio": false,@@ -581,7 +589,7 @@ The Stage-1 intermediate write retains the communication contract for Stage 2.- Bespoke mode / style prose lives only in the required behavior sibling; image custom prose lives in `image_strategy.behavior`. Canvas / icons retain free-text edge cases, color / typography retain `name: "custom"`, and image usage remains a source-id array plus `image_notes`.- `image_ai_path` and `image_strategy` appear only with `image_usage: ai` and remain confirmed downstream. The page is default; explicit/failure chat fallback keeps identical fields. `image_ai_path` selects the Step 5 path, and [`strategist-image.md`](../../references/strategist-image.md) §2 retains the selected rendering or custom behavior as the deck-level image identity anchor; individual prompts still adapt subject, composition, and atmosphere within it.-- Stage-1 **Confirm contract & template choice** writes the Stage-1 `result.json` and `template_selection.json` together, then keeps the page open while the agent installs the selection. The agent runs `--complete-template-selection`, writes fresh Stage 2 only after that handoff, and the page keeps polling. Stage-2 **Confirm final plan** saves the final `result.json` and shuts the server down (auto-close). The AI reads each receipt at its owning boundary; chat fallback mirrors the same decisions without UI artifacts. Either way, Step 4 ends with `--shutdown` so a never-confirmed page cannot retain its selected port ahead of Step 6 live preview.+- Stage-1 **Confirm contract & template choice** writes the Stage-1 `result.json` and `template_selection.json` together, then keeps the page open while the agent installs the selection. A successful Stage-1 wait is explicitly intermediate and cannot end the task. In the same active run, the agent runs `--complete-template-selection`, writes fresh Stage 2 only after that handoff, and enters the final wait while the page keeps polling. Stage-2 **Confirm final plan** saves the final `result.json` and shuts the server down (auto-close). The AI reads each receipt at its owning boundary; chat fallback mirrors the same decisions without UI artifacts. Either way, Step 4 ends with `--shutdown` so a never-confirmed page cannot retain its selected port ahead of Step 6 live preview.## Scopediff --git a/skills/ppt-master/scripts/prompt_audit_manifest.json b/skills/ppt-master/scripts/prompt_audit_manifest.jsonindex 8dcf060f..8dd9d29d 100644--- a/skills/ppt-master/scripts/prompt_audit_manifest.json+++ b/skills/ppt-master/scripts/prompt_audit_manifest.json@@ -154,7 +154,7 @@"max_tokens": 13000},"route.generate.planning": {- "description": "Generate-PPTX planning through Strategist, including reference-first whole-document authoring and complete mode, visual-style, and image-rendering decision catalogs; schemas and optional scaffolds are tool-consumed.",+ "description": "Generate-PPTX planning through Strategist, including reference-first whole-document authoring, the three compact decision indexes, and a conservative audit envelope for only the exact custom bases selected after those indexes; schemas and optional scaffolds are tool-consumed.","scope": "cumulative","include": ["bootstrap.routing"@@ -177,7 +177,7 @@"*/_index.md"],"select": 5,- "load_event": "strategist-mode-catalog",+ "load_event": "strategist-selected-mode-bases","registry": "modes"},{@@ -186,7 +186,7 @@"*/_index.md"],"select": 18,- "load_event": "strategist-visual-style-catalog",+ "load_event": "strategist-selected-visual-style-bases","registry": "visual-styles"},{@@ -195,14 +195,14 @@"*/_index.md"],"select": 20,- "load_event": "strategist-image-rendering-catalog",+ "load_event": "strategist-selected-image-rendering-bases","registry": "image-renderings"}],"max_tokens": 110000},"route.generate.quick-generate": {- "description": "Self-contained one-pass Generate profile with source intake, complete design-decision catalogs, conditional resource preparation, and complete flat SVG visual-construction authorities.",+ "description": "Self-contained one-pass Generate profile with source intake, the three compact decision indexes, a conservative audit envelope for only the resolved preset or exact custom bases, conditional resource preparation, and complete flat SVG visual-construction authorities.","scope": "cumulative","include": ["bootstrap.routing"@@ -224,7 +224,7 @@"*/_index.md"],"select": 5,- "load_event": "quick-mode-catalog",+ "load_event": "quick-selected-mode-bases","registry": "modes"},{@@ -233,7 +233,7 @@"*/_index.md"],"select": 18,- "load_event": "quick-visual-style-catalog",+ "load_event": "quick-selected-visual-style-bases","registry": "visual-styles"},{@@ -242,7 +242,7 @@"*/_index.md"],"select": 20,- "load_event": "quick-image-rendering-catalog",+ "load_event": "quick-selected-image-rendering-bases","registry": "image-renderings"}],@@ -370,7 +370,7 @@"max_tokens": 115000},"route.generate.planning-ai": {- "description": "Generate-PPTX planning after AI imagery is confirmed, adding image-layout and resource-planning authorities to the already-loaded rendering decision catalog.",+ "description": "Generate-PPTX planning after AI imagery is confirmed, adding image-layout and resource-planning authorities to the rendering index and already-selected rendering bases.","scope": "cumulative","include": ["route.generate.planning-image"@@ -644,7 +644,7 @@"max_tokens": 170000},"stage.generate.executor.flat": {- "description": "Incremental flat Executor core with complete visual-construction authorities and complete mode/visual-style execution catalogs.",+ "description": "Incremental flat Executor core with complete visual-construction authorities, the compact mode/style indexes, and a conservative audit envelope for only the locked preset or exact custom references.","scope": "incremental","files": ["skills/ppt-master/references/executor-base.md",@@ -660,7 +660,7 @@"*/_index.md"],"select": 5,- "load_event": "executor",+ "load_event": "executor-selected-mode-bases","registry": "modes","allow_repeat": true},@@ -670,7 +670,7 @@"*/_index.md"],"select": 18,- "load_event": "executor",+ "load_event": "executor-selected-visual-style-bases","registry": "visual-styles","allow_repeat": true}diff --git a/skills/ppt-master/workflows/generate-pptx.md b/skills/ppt-master/workflows/generate-pptx.mdindex b19d906c..f51881dc 100644--- a/skills/ppt-master/workflows/generate-pptx.md+++ b/skills/ppt-master/workflows/generate-pptx.md@@ -238,21 +238,15 @@ both the communication contract and template/free-design choice and any selectedworkspace has been installed.At Step-4 entry, load the always-required planning context directly in one-batch: the role cores, every canonical content-type source file defined below,-the compact structured analysis facts already present, and the three complete-design-decision catalogs. Preserve the boundary of every catalog file inside-the batch; do not concatenate them into a new artifact, route them one at a-time, or let later `*_references` decide what enters context. For a multi-deck+batch: the role core, every canonical content-type source file defined below,+and the compact structured analysis facts already present. Do not load any+mode, visual-style, or image-rendering detail file before Stage 1. For a multi-deck`source_profile.json`, read its compact `decks[]` digests in that batch and opena deck's larger identity/slide-library files only when the specific need belowarises.```Read references/strategist.md-Read references/strategist-image.md-Read references/modes/_index.md + all 5 sibling entry files-Read references/visual-styles/_index.md + all 18 sibling entry files-Read references/image-renderings/_index.md + all 20 sibling entry files```Then load only the extra role modules triggered by the current plan:@@ -262,13 +256,16 @@ Then load only the extra role modules triggered by the current plan:| Stage 1 is confirmed and its template choice installed a selected Brand/Style/Layout/Deck workspace into this project | `references/strategist-template.md` before Stage 2 || The confirmed Stage 2 `image_usage` contains a source other than `none`, the user supplied an explicit non-`none` image constraint, or formula-worthy content activates formula planning | `references/image-layout-spec.md` + `references/image-layout-patterns.md` before production detail, formula resources, or §VIII |-The image decision core and complete rendering catalog are already loaded before-Stage 2 so every direction carries a real rendering candidate. Core chooses-Stage-2 sources independently. Confirmed non-`none` or formulas load the layout-references and continue into resource planning; confirmed `none` without-formulas writes no image rows while retaining recommendation-only rendering-candidates. Only an installed project-local template state loads the template-module, and only after Stage 1 is confirmed; a bare template/style name does not.+After Stage 1 and template handoff, load `strategist-image.md` plus only the+three `_index.md` files. Author the three whole solution intents before mapping+any component basis. Freeze every referenced mode/style/rendering id from the+indexes, then read once only the deduplicated union of those exact detail files+and finish the three custom behaviors. A novel custom reads no detail file.+Confirmed non-`none` or formulas load the layout references and continue into+resource planning; confirmed `none` without formulas writes no image rows while+retaining recommendation-only rendering candidates. Only an installed+project-local template state loads the template module, and only after Stage 1+is confirmed; a bare template/style name does not.> ⚠️ **Mandatory artifact gates**: after final confirmation, author complete `design_spec.md` from `${SKILL_DIR}/templates/design_spec_reference.md`. After Gate 1 and any refinement approval, author `spec_lock.md` from `${SKILL_DIR}/templates/spec_lock_reference.md` plus approved Design Spec/context. Author each new artifact once without placeholders or `scaffold-*` (manual-only). Schema validity does not prove semantic fidelity.@@ -328,6 +325,13 @@ python3 ${SKILL_DIR}/scripts/confirm_ui/server.py <project_path> --daemonpython3 ${SKILL_DIR}/scripts/confirm_ui/server.py <project_path> --wait-only --wait-stage stage1```+**Hard rule — Stage 1 is intermediate**: exit `0` from this first wait is an+instruction to continue, not a route-completion condition. Do not send a final+chat reply, go idle, or yield the task here. In the same active run, read the two+Stage-1 receipts, complete the template/free-design handoff, author fresh Stage+2, and invoke the final wait below. Only `stage: final` + `status: confirmed`+may close this confirmation flow.+The single Stage-1 submission writes both `result.json` and`template_selection.json`; neither replaces the other. Read each exactly once.Require a confirmed communication result and either `free_design` with no roots@@ -347,10 +351,14 @@ or `templates` with at least one server-resolved root.it. The server requires this handoff before Stage 2.2. Only now inspect installed template state and apply- `strategist-template.md` when active. Derive the complete deck solution and- production defaults, loading the triggered image-planning bundle above.- Create `confirm_ui/recommendations.stage2.json` without changing Stage 1;- declare `stage: "stage2"`, then wait for the final confirmation:+ `strategist-template.md` when active. Read `strategist-image.md` plus only+ `modes/_index.md`, `visual-styles/_index.md`, and+ `image-renderings/_index.md`; author three whole solution intents, freeze+ their exact component references from those indexes, then read only the+ referenced detail files and complete the custom projections. Derive the+ remaining production defaults and create+ `confirm_ui/recommendations.stage2.json` without changing Stage 1; declare+ `stage: "stage2"`, then wait for the final confirmation:```bashpython3 ${SKILL_DIR}/scripts/confirm_ui/server.py <project_path> --wait-only@@ -526,22 +534,22 @@ Workflow:**Artifact ownership**: `svg_output/` is the author source, `svg_final/` is derived, and image facts come from the regenerated `analysis/image_analysis.csv`; see [`references/artifact-ownership.md`](../references/artifact-ownership.md).Read the execution references for this deck's locked `mode` + `visual_style`-(from `spec_lock.md`). Load this fixed required block directly as one batch;-preserve every file boundary and do not route among catalog entries one at a-time:+(from `spec_lock.md`). Load this fixed required block directly as one batch:```Read references/executor-base.md # REQUIRED: flat/shared execution coreRead references/shared-standards-core.md # REQUIRED: SVG compatibility + shared aesthetic/leading baselineRead references/svg-effects.md # REQUIRED: Visual Job Router + effects/construction vocabularyRead references/native-shape-authoring.md # REQUIRED: native-shape selection and Boolean constructionRead references/semantic-svg.md # REQUIRED: semantic metadata boundary-Read references/modes/_index.md + all 5 sibling entry files-Read references/visual-styles/_index.md + all 18 sibling entry files+Read references/modes/_index.md+Read references/visual-styles/_index.md+Read references/modes/<resolved-id>.md # one preset id, or each `mode_references` id+Read references/visual-styles/<resolved-id>.md # one preset id, or each `visual_style_references` id```Keep the core's shared visual-quality defaults and `svg-effects.md` §6.1 Visual Job Router active during page authoring; they are not passive compatibility reading. Explicit user/template requirements and the locked style override compatible aesthetic defaults, never technical Required / Forbidden boundaries.-> Read only the always-on references above plus the conditionally triggered modules below. The complete mode and visual-style catalogs are already present once per valid Executor context. Apply the locked preset directly; for `custom`, synthesize only the exact bases named by optional `mode_references` / `visual_style_references` under the corresponding behavior. References express provenance and synthesis intent, not additional load triggers. If absent, treat the direction as genuinely novel. Do not infer adjacent bases or blend unselected catalog identities.+> Read only the always-on references above plus the conditionally triggered modules below. The indexes provide routing information, not permission to open siblings. A preset reads its one locked file. For `custom`, read only the exact bases named by optional `mode_references` / `visual_style_references`, then synthesize them under the corresponding behavior. If absent, treat the direction as genuinely novel and read no preset file. Do not infer adjacent bases, glob a catalog, or blend unselected identities.| Deterministic trigger | Additional references ||---|---|diff --git a/skills/ppt-master/workflows/profiles/quick-generate.md b/skills/ppt-master/workflows/profiles/quick-generate.mdindex 59ed4cdc..cf664128 100644--- a/skills/ppt-master/workflows/profiles/quick-generate.md+++ b/skills/ppt-master/workflows/profiles/quick-generate.md@@ -203,24 +203,22 @@ use; otherwise decide which prototypes to use, skip, repeat, reorder, or adaptwhile authoring. Persist no separate template-application artifact. If notemplate was installed, make the same design choices freely.-Before resolving the one-pass design, read these three complete catalogs in one-deterministic, boundary-preserving batch:+Before resolving the one-pass design, read only these three indexes:```-Read references/modes/_index.md + all 5 sibling entry files-Read references/visual-styles/_index.md + all 18 sibling entry files-Read references/image-renderings/_index.md + all 20 sibling entry files+Read references/modes/_index.md+Read references/visual-styles/_index.md+Read references/image-renderings/_index.md```-Do not concatenate the files into a generated bundle or rediscover them one at-a time. Compare three complete, project-fit solution directions internally,-including one rendering candidate for each, and then choose the best whole-solution for direct execution. The three internal directions must all be viable-and meaningfully distinguishable, but need not use different catalog ids or fit-safe / shifted / bold archetypes. Decide whether AI images are useful as a-separate source judgment; even when the answer is no, the rendering comparison-still informs visual coherence. Keep the chosen mode, style, rendering, and any-exact custom bases in active context only.+Resolve the best whole solution from the project brief and index summaries,+freeze its exact mode/style/rendering ids, then read only those selected preset+files or custom-basis files. A novel custom reads none. Never open detail files+to compare candidates, glob a catalog, or let an unselected sibling influence+the decision. Decide whether AI images are useful as a separate source judgment;+even when the answer is no, retain the chosen rendering direction for visual+coherence. Keep the chosen mode, style, rendering, and exact bases in active+context only.**One-pass decision boundary**: resolve only what is needed to author this deckin the current context. Do not print a strategy summary, create a planning@@ -346,12 +344,11 @@ not route among them one file at a time:[`svg-effects.md`](../../references/svg-effects.md),[`native-shape-authoring.md`](../../references/native-shape-authoring.md),[`semantic-svg.md`](../../references/semantic-svg.md),-and [`executor-structure.md`](../../references/executor-structure.md). Retain the-complete mode and visual-style catalogs already read during one-pass design-resolution, and realize only the chosen direction. Exact `*_references` preserve-the basis of a custom synthesis; they do not trigger another catalog read. A-genuinely novel custom direction follows its resolved behavior without inventing-a nearby preset.+and [`executor-structure.md`](../../references/executor-structure.md). Retain+only the mode/style detail files selected during one-pass design resolution and+realize that chosen direction. Exact `*_references` define the complete basis+of a custom synthesis; a genuinely novel custom follows its resolved behavior+without reading or inventing a nearby preset.Do not load `executor-base.md`: it owns Default's persisted-plan handoff,first-page gate, and completion routing. Excluding that file is not a capabilitydiff --git a/skills/ppt-master/workflows/stages/resume-execute.md b/skills/ppt-master/workflows/stages/resume-execute.mdindex e2c2ca92..ade7ec5a 100644--- a/skills/ppt-master/workflows/stages/resume-execute.md+++ b/skills/ppt-master/workflows/stages/resume-execute.md@@ -81,7 +81,7 @@ Then jump to `### Step 6: Executor Phase` and run the documented pipeline:`enabled` / `disabled` / `disabled`; these production decisions never comefrom `spec_lock.md`- If resuming mid-deck, read the latest completed SVG and current image metadata when images are used-- Read the complete Step 6 always-on core exactly as listed in [`generate-pptx.md`](../generate-pptx.md), including the full mode and visual-style catalogs as one boundary-preserving batch; apply optional `*_references` only as the declared basis of a custom synthesis, then load only the branches selected by the condition table+- Read the complete Step 6 always-on core exactly as listed in [`generate-pptx.md`](../generate-pptx.md), then read one locked preset file or only the exact `*_references` of a custom synthesis; never glob the mode or visual-style catalogs, and load only the branches selected by the condition table- For each page, make the mandatory Structure decision from retained §IX after its content/communication move is established and before any geometry; a `yes` result loads `executor-structure.md` before realization and creates no artifact or lock row- Design Parameter Confirmation- When structured, read the template Design Spec and each selected prototype once; retain unchanged references in the fresh context. A later bounded repair follows [`executor-base.md`](../../references/executor-base.md) §2.1 only while that context remains valid and uncompacted