Skip to content

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

fix(prompts): remove accumulated zero-image exit clauses and name web mood/scene jobs

hugohe3553eef9af3c6
diff --git a/skills/ppt-master/references/executor-base.md b/skills/ppt-master/references/executor-base.md
index eb3209de..eb4764e5 100644
--- a/skills/ppt-master/references/executor-base.md
+++ b/skills/ppt-master/references/executor-base.md
@@ -164,7 +164,7 @@ Before drawing each page, look up its entry in `page_rhythm` (key format `P<NN>`
- **Main-agent ownership**: SVG generation must run in the main agent (not sub-agents) — pages share upstream context for cross-page visual continuity
- **Generation rhythm**: P01 → first-page gate → remaining pages with one page gate per first-exercised `not-exercised` item → final gate, in one context without batches or other mid-run checker calls.
- **Fact provenance**: when a §IX page lists `Fact IDs`, resolve each ID from `sources/*.facts.json` and keep the claim/value unchanged. Render a compact source footnote using the source name and a short URL/domain when space permits; when speaker notes are enabled, state the attribution naturally there too. When §IX says `Data class: scenario`, place a visible localized `Scenario data` / `情景数据` label adjacent to the affected KPI/chart and, when notes are enabled, state naturally there that the number is illustrative. Never attach an external fact ID to scenario data or let an unlabeled invented KPI look factual.
-- **Mandatory — resolve the page carrier mix before coordinates**: decide background paint/field, editable text and optional lettering, native geometry/lines, prepared photos/scenes/illustration/icon assets, and applicable visualizations in one page-level composition decision. Use any suitable subset; omitting a carrier remains valid. Use only prepared external resources, preserve every binding resource job and constraint, and choose the actual combination, visual weight, z-order, and local native construction from the page message and hierarchy. The resolved style controls treatment and emphasis, never carrier eligibility, image source, or the complete native construction vocabulary.
+- **Mandatory — resolve the page carrier mix before coordinates**: decide background paint/field, editable text and optional lettering, native geometry/lines, prepared photos/scenes/illustration/icon assets, and applicable visualizations in one page-level composition decision. Use only prepared external resources, preserve every binding resource job and constraint, and choose the actual combination, visual weight, z-order, and local native construction from the page message and hierarchy. The resolved style controls treatment and emphasis, never carrier eligibility, image source, or the complete native construction vocabulary.
- **Default — stage each page with the style's composition geometry (may override when another page-fit move is stronger)**: an SVG page is a canvas, not a DOM. Resolve the page-scale move from `spec_lock.md`: a preset uses that selected style's §1 `Composition geometry`; `custom` executes `visual_style_behavior` first, then uses §1 geometry only from exact `visual_style_references` that the behavior assigns a shape or composition job. Other bases contribute only their assigned job, and an unreferenced novel custom follows its behavior alone. Its motivation is the slide-versus-web reading: parallel rounded card grids (3-card rows, KPI grids, 2×2 card matrices) read as a web page, while a page-scale geometric move reads as a slide. Treat every listed move as generative vocabulary rather than a finite menu, then apply [`native-shape-authoring.md`](./native-shape-authoring.md) §2.1's shared exact-fit geometry gate.
- **Default — consider the planned motif direction (may override when another coherent expression better serves the deck)**: when §III `Theme` recommends a cross-page motif or element family, decide whether it earns a continuity job. If adopted, keep its reuse coherent while varying scale, crop, density, position, and content interaction by page role; otherwise adapt or decline it and establish a more fitting style-consistent expression. An explicit user/template motif remains binding.
- **Inherited containers**: preserve meaningful template frames; restyle radius, fill, stroke, and depth from the active Design Spec and `spec_lock.md`. Selected Chart/Table reference adaptation is owned by [`executor-visualization.md`](./executor-visualization.md); preview effects never override project styling or structural roles.
diff --git a/skills/ppt-master/references/strategist-image.md b/skills/ppt-master/references/strategist-image.md
index b4cf919e..45bca870 100644
--- a/skills/ppt-master/references/strategist-image.md
+++ b/skills/ppt-master/references/strategist-image.md
@@ -10,7 +10,7 @@ Always-on Stage-2 rendering-candidate extension plus confirmed image elaboration
## 1. Proposed and Confirmed Image Plan
-Before Stage 2, construct rendering candidates independently of the proposed source set. After confirmation, use this module within [`strategist.md`](./strategist.md)'s one-pass page carrier planning: run its eligibility and fit decisions inside that pass, then plan and route only the resulting image, lettering, and illustrated-icon jobs; map the confirmed source set through §h and honor explicit `image_notes` roles. This module never reopens the complete carrier mix as a separate pass, materializes a file, or adds a source. The confirmed non-`none` set is an allowed acquisition boundary, not coverage: use a suitable subset and leave irrelevant sources unused. Explicit must-use sources, assets, or page roles remain required. Asset inventory and judgment determine unconfirmed count, subject, placement, and composition without substituting an unconfirmed source.
+Before Stage 2, construct rendering candidates independently of the proposed source set. After confirmation, use this module within [`strategist.md`](./strategist.md)'s one-pass page carrier planning: run its eligibility and fit decisions inside that pass, then plan and route only the resulting image, lettering, and illustrated-icon jobs; map the confirmed source set through §h and honor explicit `image_notes` roles. This module never reopens the complete carrier mix as a separate pass, materializes a file, or adds a source. The confirmed non-`none` set is the acquisition boundary. Explicit must-use sources, assets, or page roles remain required. Asset inventory and judgment determine unconfirmed count, subject, placement, and composition without substituting an unconfirmed source.
For illustration, confirmed `none` stops and explicit user intent wins. Otherwise the locked visual style's `Illus.` propensity (`core` / `supportive` / `sparse`) tunes centrality and recurrence after the per-page composition scan; it never restricts eligible page types, element scale, or carrier combinations. When illustration is active, prefer one coherent family that can serve the actual page jobs, including recurring title/corner chrome, dominant anchors, supporting figures, and accents. A compact icon cue does not discharge a scene, subject, or visual-weight job that a photo or illustration family would serve.
@@ -65,7 +65,7 @@ For specialized or regulated paper-figure subjects, preserve the prompt depth re
## 3. Image Resource List
-Add §VIII rows only for planned images; permitted unused sources create no row. Fill filename, dimensions/ratio, layout suggestion, crop, purpose/type, acquisition, status, reference, and conditional AI fields. `Acquire Via` is `ai`, `web`, `user`, `placeholder`, or `slice`; status follows [`svg-image-embedding.md`](./svg-image-embedding.md). Keep any unavailable planned/required asset `Pending` or `Needs-Manual`; never delete or reclassify it to appear complete. After final confirmation, project each placed row into `spec_lock.md images` as `<path> | source=<Acquire Via> | crop=<adaptive|no-crop>` and omit unplaced source/sheet rows. Preserve exact confirmed `source`/`crop`; `Layout pattern` stays in §VIII as preferred expression rather than locked geometry.
+Add §VIII rows only for planned images. Fill filename, dimensions/ratio, layout suggestion, crop, purpose/type, acquisition, status, reference, and conditional AI fields. `Acquire Via` is `ai`, `web`, `user`, `placeholder`, or `slice`; status follows [`svg-image-embedding.md`](./svg-image-embedding.md). Keep any unavailable planned/required asset `Pending` or `Needs-Manual`; never delete or reclassify it to appear complete. After final confirmation, project each placed row into `spec_lock.md images` as `<path> | source=<Acquire Via> | crop=<adaptive|no-crop>` and omit unplaced source/sheet rows. Preserve exact confirmed `source`/`crop`; `Layout pattern` stays in §VIII as preferred expression rather than locked geometry.
**Prepared derivatives**: Keep canonical; `Reference`: `Derived from <bare filename>; treatment=<operation>;`. Deterministic child: distinct `.png`, inherits acquisition; §4.4 follows `user`/`ai` above. Lock placed children; [`image-base.md`](./image-base.md) §2–3 owns preparation.
diff --git a/skills/ppt-master/references/strategist.md b/skills/ppt-master/references/strategist.md
index 06efe211..ef4f9967 100644
--- a/skills/ppt-master/references/strategist.md
+++ b/skills/ppt-master/references/strategist.md
@@ -188,7 +188,7 @@ The base icon style is one single-select identity, not a material whitelist:
| **A** | Emoji | Casual, playful, social media |
| **B** | Built-in generic icon library | Recurring compact semantic cues in one coherent SVG style |
| **C** | Custom project icons | Supplied, template-carried, or imported assets |
-| **D** | No base icons | Illustration, typography, shapes, or data already carry the compact cues |
+| **D** | No base icons | No shared generic base-icon identity is selected |
AI-generated illustrated icons are not a base-style option, add-on, Confirm UI
field, or result key. Like decorative lettering, they are a downstream image
@@ -293,73 +293,6 @@ page block, record the linked text/object and its exact absolute URI or final
inline/whole-object carrier, or create a link manifest or lock entry. Executor
owns SVG authoring under [`native-hyperlinks.md`](./native-hyperlinks.md).
-### h. Image Source Recommendation
-
-| Source id | Approach | Use when |
-|---|---|---|
-| `none` | No images | Data reports or process documentation whose visual burden is fully served by charts / native SVG |
-| `provided` | User-provided assets | Existing images carry factual, brand, product, or narrative authority |
-| `ai` | AI-generated | Invented or deliberately stylized scenes, illustrations, backgrounds, metaphors, decorative lettering, or another generated visual treatment is needed |
-| `web` | Web-sourced | A named or evidence-bearing real-world subject must appear as itself |
-| `placeholder` | Deferred | The image is required but will be supplied later |
-
-**Current inventory**: If `images/` is non-empty, run `python3 scripts/analyze_images.py <project_path>/images` and read `analysis/image_analysis.csv` before recommending a source. Re-run after that folder changes.
-
-**Hard rule**: Credentials do not decide image need. Missing `IMAGE_BACKEND`, host generation, or keyed stock-provider credentials never justifies `none` or deletion of a planned web-compatible role. Web search retains zero-config providers; an explicit generation-only requirement follows the normal Offline Manual boundary.
-
-**Mandatory — no AI capability preflight**: When `recommend.image_usage` includes `ai`, preserve an explicit user path instruction; otherwise recommend `auto`. Do not inspect backend configuration, check host-tool availability, or probe a provider during planning. Generate Step 5 execution is the first capability check.
-
-**Default — visual grounding before `none` (may override when the full-roster carrier review finds no useful image job)**: Honor an explicit no-image requirement. First decide whether the audience must recognize, experience, compare, or choose an externally verifiable subject, place, product, or setting. When yes, propose `provided` / `web`; propose `ai` when invented or deliberately stylized expression materially improves a planned visual job. Treat `none` as a positive whole-deck conclusion when no image source owns a meaningful communication job. Mixed sources may serve different page roles. The three Stage-2 style directions never settle source: a rendering candidate resolves how imagery looks, never whether a real subject must appear as itself.
-
-**Default — consider proactive illustrated icons without creating another
-confirmation field**: Before each Stage-2 `recommend.image_usage`, consider
-whether compact semantic jobs would communicate better through a coherent
-illustrated cue family. This may support an `ai` recommendation, but it is not
-an automatic source trigger or coverage quota. Resource grouping remains a
-fit-driven decision under [`strategist-image.md`](./strategist-image.md).
-
-**Mandatory — scan proactive decorative-lettering capability without making
-candidates an automatic source trigger**: Before each Stage-2
-`recommend.image_usage`, scan the complete planned roster for exact stable
-display strings whose artistic treatment could plausibly communicate better
-than native type. Page role, character count, word count, line count, kind of
-noun, and proposed style never pre-filter candidates: a complete long or
-multi-line title is as eligible as a short mark. Never invent, rewrite,
-shorten, or split copy to make generation easier. Passing both discovery
-questions exposes one possible AI visual job, not a selected resource or a
-mechanical reason to add `ai`. During page-carrier planning, compare those
-candidates with native type and the complete deck mix; select only the marks
-whose treatment wins that fit. Zero selected marks remains valid and needs no
-skip explanation or coverage quota. A selected mark may be the sole intended
-AI job and may support an AI recommendation stated in `image_notes.value`;
-when either discovery answer is no, native editable text remains valid. The
-absence of another AI-image job never forces lettering. Explicit no-AI or
-editable-only requirements win. Execution follows
-[`image-generator.md`](./image-generator.md) §7.
-
-**Recommendation output**: Write `recommend.image_usage` as one source id or an array for mixed sources. Put the intended communication jobs of each proposed source, authoritative assets, preferred/avoided imagery, and placeholder tolerance in `image_notes.value`. When `ai` is proposed, explain in editable natural language how generated visuals are expected to contribute and mention any materially anticipated illustration, illustrated-icon, or lettering role. Keep the note an open strategy—not an enum, carrier allowlist, page-by-page assignment, count, or resource manifest; name exact pages/assets only when already authoritative or required. `none` is exclusive. Decks built around real-world recognition or choice, including travel itineraries, lean `provided` / `web`; generic human-scale topics such as family life, education, wellness, or children lean `ai` when no supplied asset carries the story and invented or stylized expression serves it. Regulated investor decks, B2B finance reports, and data-only dashboards remain eligible for `none` by judgment.
-
-**Confirmed value wins**: Accept the confirmed legacy string or multi-select array. Map `ai→ai`, `web→web`, `provided→user`, and `placeholder→placeholder` into §VIII `Acquire Via`. Every direction already carries a rendering candidate whether or not AI is proposed; generated images inherit the deck colors and never introduce a second image-palette choice.
-
-**Always-on decision module; conditional resource extension**:
-
-1. Before authoring Stage-2 directions, load the workflow's complete fixed
- planning-capability batch. It includes this module, the image-layout
- authorities, all compact decision maps, the icon-library contract, the
- complete Chart and Table expression vocabularies. After the
- three whole-direction intents exist and their mode/style/rendering reference
- ids are frozen, read only
- those exact detail siblings 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.
- Confirmed `none` writes no image rows, but does not erase the three
- recommendation-only rendering candidates or the already-loaded composition
- vocabulary.
-
-The module owns AI rendering alternatives, acquisition paths, resource rows, prompt depth, page roles, and placement intent.
-
### Page Carrier and Capability Planning (Non-blocking — Strategist recommends, no user confirmation needed)
**Default — carrier planning in §IX (may stay implicit when a page's mix is obvious)**: During the same §IX roster
@@ -370,8 +303,7 @@ deriving §VIII resource rows. Decide the primary, structural, and supporting
jobs together. Use existing §VI/§VIII/§IX fields: keep the
ordinary icon basis and prepared-pool plan in §VI, and add an image, lettering,
or illustrated-icon resource to §VIII only when the page mix assigns it a
-plausible job. This creates no new field or candidate inventory; omitting any
-carrier remains valid. Macro composition recommendations
+plausible job. This creates no new field or candidate inventory. Macro composition recommendations
remain Reference; planned resource identities/jobs and explicit user/template
requirements retain their existing authority.
@@ -450,6 +382,73 @@ Correct failed selections by re-reading the complete vocabulary/registry;
| P03 | chart | line_chart | Compare the source metrics over time |
```
+### h. Image Source Recommendation
+
+| Source id | Approach | Use when |
+|---|---|---|
+| `none` | No images | No image source owns a meaningful communication job for the planned deck |
+| `provided` | User-provided assets | Existing images carry factual, brand, product, or narrative authority |
+| `ai` | AI-generated | Invented or deliberately stylized scenes, illustrations, backgrounds, metaphors, decorative lettering, or another generated visual treatment is needed |
+| `web` | Web-sourced | Named or evidence-bearing real-world subjects that must appear as themselves, plus generic photographic mood, background, or scene jobs that benefit from sourced visual grounding |
+| `placeholder` | Deferred | The image is required but will be supplied later |
+
+**Current inventory**: If `images/` is non-empty, run `python3 scripts/analyze_images.py <project_path>/images` and read `analysis/image_analysis.csv` before recommending a source. Re-run after that folder changes.
+
+**Hard rule**: Credentials do not decide image need. Missing `IMAGE_BACKEND`, host generation, or keyed stock-provider credentials never justifies `none` or deletion of a planned web-compatible role. Web search retains zero-config providers; an explicit generation-only requirement follows the normal Offline Manual boundary.
+
+**Mandatory — no AI capability preflight**: When `recommend.image_usage` includes `ai`, preserve an explicit user path instruction; otherwise recommend `auto`. Do not inspect backend configuration, check host-tool availability, or probe a provider during planning. Generate Step 5 execution is the first capability check.
+
+**Default — visual grounding before `none` (may override when the full-roster carrier review finds no useful image job)**: Honor an explicit no-image requirement. First decide whether the audience must recognize, experience, compare, or choose an externally verifiable subject, place, product, or setting. When yes, propose `provided` / `web`; propose `ai` when invented or deliberately stylized expression materially improves a planned visual job. Mixed sources may serve different page roles. The three Stage-2 style directions never settle source: a rendering candidate resolves how imagery looks, never whether a real subject must appear as itself.
+
+**Default — consider proactive illustrated icons without creating another
+confirmation field**: Before each Stage-2 `recommend.image_usage`, consider
+whether compact semantic jobs would communicate better through a coherent
+illustrated cue family. This may support an `ai` recommendation, but it is not
+an automatic source trigger or coverage quota. Resource grouping remains a
+fit-driven decision under [`strategist-image.md`](./strategist-image.md).
+
+**Mandatory — scan proactive decorative-lettering capability without making
+candidates an automatic source trigger**: Before each Stage-2
+`recommend.image_usage`, scan the complete planned roster for exact stable
+display strings whose artistic treatment could plausibly communicate better
+than native type. Page role, character count, word count, line count, kind of
+noun, and proposed style never pre-filter candidates: a complete long or
+multi-line title is as eligible as a short mark. Never invent, rewrite,
+shorten, or split copy to make generation easier. Passing both discovery
+questions exposes one possible AI visual job, not a selected resource or a
+mechanical reason to add `ai`. During page-carrier planning, compare those
+candidates with native type and the complete deck mix; select only the marks
+whose treatment wins that fit. Zero selected marks remains valid and needs no
+skip explanation or coverage quota. A selected mark may be the sole intended
+AI job and may support an AI recommendation stated in `image_notes.value`;
+when either discovery answer is no, native editable text remains valid. The
+absence of another AI-image job never forces lettering. Explicit no-AI or
+editable-only requirements win. Execution follows
+[`image-generator.md`](./image-generator.md) §7.
+
+**Recommendation output**: Write `recommend.image_usage` as one source id or an array for mixed sources. Put the intended communication jobs of each proposed source, authoritative assets, preferred/avoided imagery, and placeholder tolerance in `image_notes.value`. When `ai` is proposed, explain in editable natural language how generated visuals are expected to contribute and mention any materially anticipated illustration, illustrated-icon, or lettering role. Keep the note an open strategy—not an enum, carrier allowlist, page-by-page assignment, count, or resource manifest; name exact pages/assets only when already authoritative or required. `none` is exclusive.
+
+**Confirmed value wins**: Accept the confirmed legacy string or multi-select array. Map `ai→ai`, `web→web`, `provided→user`, and `placeholder→placeholder` into §VIII `Acquire Via`. Every direction already carries a rendering candidate whether or not AI is proposed; generated images inherit the deck colors and never introduce a second image-palette choice.
+
+**Always-on decision module; conditional resource extension**:
+
+1. Before authoring Stage-2 directions, load the workflow's complete fixed
+ planning-capability batch. It includes this module, the image-layout
+ authorities, all compact decision maps, the icon-library contract, the
+ complete Chart and Table expression vocabularies. After the
+ three whole-direction intents exist and their mode/style/rendering reference
+ ids are frozen, read only
+ those exact detail siblings 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.
+ Confirmed `none` writes no image rows, but does not erase the three
+ recommendation-only rendering candidates or the already-loaded composition
+ vocabulary.
+
+The module owns AI rendering alternatives, acquisition paths, resource rows, prompt depth, page roles, and placement intent.
+
### Speaker Notes Requirements
Resolve the effective Speaker Notes outcome from the latest explicit user
diff --git a/skills/ppt-master/workflows/generate-pptx.md b/skills/ppt-master/workflows/generate-pptx.md
index 21e1b729..f0ca5115 100644
--- a/skills/ppt-master/workflows/generate-pptx.md
+++ b/skills/ppt-master/workflows/generate-pptx.md
@@ -293,8 +293,7 @@ Read ${SKILL_DIR}/templates/charts/chart-vocabulary.md
Read ${SKILL_DIR}/templates/tables/table-vocabulary.md
```
-This is a capability map, not a usage checklist: retain zero-use outcomes and
-the Strategist/Executor ownership boundary. Author the three whole solution
+This is a capability map; retain the Strategist/Executor ownership boundary. 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
diff --git a/skills/ppt-master/workflows/profiles/quick-generate.md b/skills/ppt-master/workflows/profiles/quick-generate.md
index 8db24775..0f020657 100644
--- a/skills/ppt-master/workflows/profiles/quick-generate.md
+++ b/skills/ppt-master/workflows/profiles/quick-generate.md
@@ -394,7 +394,7 @@ or easier syntax never skips it.
**Hard rule**: Credentials do not decide image need or the initial carrier plan. Do not inspect backend configuration or probe a provider before planning. Web acquisition retains zero-config providers; actual AI generation capability is resolved only during resource preparation, where the declared Quick no-AI replan below owns automated exhaustion.
-**Default — visual grounding before a zero-image deck (may override when the full-roster carrier review finds no useful image job)**: Honor an explicit no-image requirement. When the audience must recognize, experience, compare, or choose an externally verifiable subject, place, product, or setting, plan supplied/extracted or web images. Prepare AI imagery proactively where invented or deliberately stylized expression materially improves a planned visual job; this may be a complete image or transparent elements composed with other page carriers. A zero-image result remains valid when no image job improves communication. This is a semantic decision, not an image-count quota.
+**Default — visual grounding before a zero-image deck (may override when the full-roster carrier review finds no useful image job)**: Honor an explicit no-image requirement. When the audience must recognize, experience, compare, or choose an externally verifiable subject, place, product, or setting, plan supplied/extracted or web images. Prepare AI imagery proactively where invented or deliberately stylized expression materially improves a planned visual job; this may be a complete image or transparent elements composed with other page carriers. This is a semantic decision, not an image-count quota.
**Mandatory — materialize a selected composable illustration family**: When
the carrier resolution selects one, resolve the family before SVG authoring.