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

docs(generation): align template-led recommendations across runtimes

hugohe39ccba2d44b0b
diff --git a/docs/getting-started.md b/docs/getting-started.md
index 2d251e91..63e1b108 100644
--- a/docs/getting-started.md
+++ b/docs/getting-started.md
@@ -108,7 +108,7 @@ You: Quickly generate a deck from sources/report.pdf — no need to confirm with
You: Turn this into a deck, skip the confirmation, about 8 pages, dark corporate look
```
-**Whatever you state explicitly is followed; whatever you leave unspecified the agent decides directly, without coming back to ask.** The page count and the look in the second example still hold — quick mode drops the round trip, not your say. State nothing, and the agent decides everything.
+**Whatever you state explicitly is followed; whatever you leave unspecified the agent decides directly, without coming back to ask.** The page count and the look in the second example still hold — quick mode drops the round trip, not your say. Instead of materializing Default's three directions, Quick directly executes the direction that Default would recommend: the strongest overall fit for free design, or the viable direction most fully expressing installed template context. State nothing, and the agent decides everything.
Quick mode never opens the Confirm UI template selector. Give it up to one exact
Brand / Style / Layout / Deck workspace root per kind and it validates,
diff --git a/docs/technical-design.md b/docs/technical-design.md
index 6070b003..c2830eea 100644
--- a/docs/technical-design.md
+++ b/docs/technical-design.md
@@ -502,7 +502,7 @@ without interaction, while the Stage-1 communication recommendation is authored
without reading those candidates or any template content. The UI confirms that
communication contract and the switchable free-design/template choice together;
only afterward does the agent install every selected spec separately into the
-project. 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 a custom mode, custom visual style, color, typography, icon, and custom generated-image rendering; the fixed catalogs remain conservative lower-level single-select alternatives. Each direction is one complete design authored top-down within the confirmed contract rather than assembled from catalog picks, and three exist so a single recommendation cannot lock the user in; the fixed catalogs stay the manual lower layer. `custom` has no required relationship to the catalogs, and one selected preset may be carried unchanged. The three bundles are plainly different designs at the whole-deck level, decided before any field is written and only then projected onto mode, visual style, rendering, color, typography, and icons; that difference lives in the solutions rather than in one designated field, so whichever components a direction requires carry it and any component may coincide. A different name, note, or reference count alone is not a difference, and bundles identical on every component are not three solutions. Where authoritative user/template truth fixes some components, the remaining open ones carry the difference; identical projections are valid only when nothing is open, and the plan states that boundary instead of inventing variation. It does not assemble the three solutions afterward from independent component picks or force them into safe / shifted / bold archetypes. After all three bundles are complete, it compares them against the confirmed contract and source, records the strongest overall fit as zero-based `design_directions.selected`, and gives array order no preference meaning. 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. The preferred top card is marked and applied initially. An inactive top card applies its immutable bundle, each projected custom card becomes editable in place after selection, and all lower controls may diverge; the adjusted active card exposes an explicit restore action, while final state stores only the edited current components. The same stage confirms reading mode, page count, conditional AI acquisition, generation mode, the Design Spec review toggle, and whether the agent should proactively generate speaker notes, custom animations, or narration audio. Formula handling is not a user-selectable production policy: structural mathematics becomes a native formula marker during authoring. 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.
+project. 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 a custom mode, custom visual style, color, typography, icon, and custom generated-image rendering; the fixed catalogs remain conservative lower-level single-select alternatives. Each direction is one complete design authored top-down within the confirmed contract rather than assembled from catalog picks, and three exist so a single recommendation cannot lock the user in; the fixed catalogs stay the manual lower layer. `custom` has no required relationship to the catalogs, and one selected preset may be carried unchanged. The three bundles are plainly different designs at the whole-deck level, decided before any field is written and only then projected onto mode, visual style, rendering, color, typography, and icons; that difference lives in the solutions rather than in one designated field, so whichever components a direction requires carry it and any component may coincide. A different name, note, or reference count alone is not a difference, and bundles identical on every component are not three solutions. Where authoritative user/template truth fixes some components, the remaining open ones carry the difference; identical projections are valid only when nothing is open, and the plan states that boundary instead of inventing variation. It does not assemble the three solutions afterward from independent component picks or force them into safe / shifted / bold archetypes. After all three bundles are complete, free design records the strongest overall fit as zero-based `design_directions.selected`. With installed template state, every bundle remains compliant with the same resolved context; `selected` identifies the viable bundle that most fully expresses it, while the other two vary only open dimensions rather than weakening template use or splitting its segments. Array order has no preference meaning. 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. The preferred top card is marked and applied initially. An inactive top card applies its immutable bundle, each projected custom card becomes editable in place after selection, and all lower controls may diverge; the adjusted active card exposes an explicit restore action, while final state stores only the edited current components. The same stage confirms reading mode, page count, conditional AI acquisition, generation mode, the Design Spec review toggle, and whether the agent should proactively generate speaker notes, custom animations, or narration audio. Formula handling is not a user-selectable production policy: structural mathematics becomes a native formula marker during authoring. 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 raw
evidence. In particular, enabling narration may enable the effective Speaker
diff --git a/docs/templates-architecture.md b/docs/templates-architecture.md
index 207d5835..b4b5d268 100644
--- a/docs/templates-architecture.md
+++ b/docs/templates-architecture.md
@@ -506,6 +506,8 @@ Bitmaps share the workspace `images/` pool and template SVGs reference them thro
Installing a template does not narrow away the communication question. Stage 1 confirms the same open communication contract together with, but independently from, the template choice. The communication recommendation uses only the current request, source facts, conversation constraints, and project initialization; even template canvas is excluded. Only after Stage 1 closes and any selection is installed does final Stage 2 inspect that state and confirm the complete solution and production plan. Brand supplies identity constraints while structure stays free; Style supplies method and visual-default seeds while remaining flat; Layout exposes structural capability; Deck contributes descriptive reusable application context for comparison, not the current project's contract. For Style-only use, Strategist does not look for prototypes and deterministically records `template_reuse_scope: style` with flat structure. It otherwise inspects every effective prototype—Layout when present, otherwise Deck—and current content, then authors one page/prototype plan and records `mirror`, `layout`, or `style` only as internal exporter values. A mirror-authored workspace therefore enables literal reuse but never forces it.
+Default still presents three template-compliant design directions. The Recommended direction is the viable one that most fully expresses the resolved template context; the other two vary only dimensions left open by that context and the user. Quick materializes no candidate set and directly executes that same recommended-direction rule.
+
Default confirms one natural-language `template_application` paragraph; Quick
freezes the same decision only in active context. Explicit user wording wins,
otherwise the agent decides from content and the complete SVG roster, with
diff --git a/docs/zh/getting-started.md b/docs/zh/getting-started.md
index 805694fc..6ced019d 100644
--- a/docs/zh/getting-started.md
+++ b/docs/zh/getting-started.md
@@ -108,7 +108,7 @@ Default Generate 把模板选择放在 Stage 1,与沟通契约同屏确认;
你:这份内容直接做成 PPT,跳过确认,8 页左右,深色商务风
```
-**你明确提的照做,你没提的 AI 直接定,不再回来问你。** 第二个例子里的页数和风格照样生效——快速模式省掉的是来回确认,不是你的话语权;什么都不提,才是全部交给 AI 决定。
+**你明确提的照做,你没提的 AI 直接定,不再回来问你。** 第二个例子里的页数和风格照样生效——快速模式省掉的是来回确认,不是你的话语权。Quick 不会真正生成 Default 的三套方向,而是直接执行 Default 会推荐的方向:自由设计时选整体适配度最高者,已安装模板时选最充分表达模板上下文的可行方向。什么都不提,才是全部交给 AI 决定。
快速模式不会打开 Confirm UI 的模板选择页。每个 kind 最多给出一个精确的
Brand / Style / Layout / Deck 工作区 root,它会直接校验、安装并使用;没有
diff --git a/docs/zh/technical-design.md b/docs/zh/technical-design.md
index 08a1ba1a..f7002fb5 100644
--- a/docs/zh/technical-design.md
+++ b/docs/zh/technical-design.md
@@ -426,7 +426,7 @@ PPT Master 把拥有 deck 状态的 Strategist、Image_Generator 和 Executor
Stage-1 沟通推荐的编写不得读取这些候选或任何模板内容。UI 在同一次提交中
确认沟通契约与可切换的自由设计/使用模板选择;只有确认后,Agent 才把非自由设计选择安装成彼此独立的项目本地 `spec`。Strategist 采用一个按依赖排序的两阶段 gate。`delivery_context` 在同一个开放文本字段中区分演讲者主导、读者主导、混合、录制/自动播放,明确主要场景并记录可选的次要用途;混合场景不能只写“混合”而不说明由哪一种主导。其中的文本框仍承载可编辑推荐,且没有任何一项要求非空:确认时按当前文本原样保存,清空后的值保持为空,不会回退到推荐内容。最终 Stage 2 只从该契约计算一次,同时确认完整 PPT 方案与生产机制:阅读模式、叙事 mode、页数、成套视觉系统、图片来源、生成图渲染、条件式 AI 图片获取路径、生成模式、Design Spec 审核开关,以及 Agent 是否主动生成讲稿、自定义动画和旁白音频。公式处理不是用户选择的生产策略:结构性数学内容在创作时直接成为原生公式 marker。仅在 Stage 1 确认后,存在已安装模板时,Strategist 才读取项目本地工作区和当前内容,推导**如何应用**并以可编辑的 `template_application` 自然语言展示;Stage 2 不会重新选模板,内部复用/遵循模式保持隐藏。阅读模式决定信息由页面、视觉、讲者和备注如何共同承担,其选项卡不展示 px 数值。浏览器可以在本地执行确定性的「阅读模式 → 正文基准 → 未锁定角色字号」联动;手动编辑字号即锁定可见值,不会重新计算 Stage 2。三个主动执行值是用户未明确要求时的兜底策略,不是能力禁用开关;优先级固定为「用户最新明确指令 → 最终 Stage 2 → `true / false / false` 默认值」。Strategist 仍可按内容给出非绑定的 Motion suggestion,建议本身不会启动自定义动画执行。生成图直接继承已选 PPT 色彩锚点,不再单设图片调色选择。最终状态有两个等价载体:默认 UI 路径在最终等待返回后只读取一次 `confirm_ui/result.json`;显式 chat-only 或委托路径保留等价的最终确认摘要,并可不产生 `result.json`。两条路径都会先解析并把生产流程的最终有效结果固化到同一份 `design_spec.md`,再完成 Gate 1 fidelity。未开启 refine 时立即进入 lock 编写;`refine_spec: true` 时,流程会在 `spec_lock.md` 之前暂停,用户可以通过正常聊天任意修改这同一份 Design Spec、迭代任意轮次,明确批准后才释放 Gate 2 并编写 lock。流程不会维护第二份 Design Spec 或并行 lock。正常的 lock 编写与下游执行不再回读确认通道。必需人工素材未就绪仍可能引入条件式阻塞点,因此这里不是对所有 runtime gate 的排他声明。项目校验要求 `spec_lock.md ## communication` 下存在紧凑的 `audience` / `objective` / `core_message` 锚点,并要求 §IX 每个 Slide block 都有 `Audience move`。
-三套成套方向仍把 mode、visual style 与生成图 rendering 投影为可编辑的 `custom`。每套方向都是在已确认契约内自顶向下完成的一套完整设计,而不是自下而上从目录里拼选出来的;给三套是为了不让单一推荐把用户锁死,固定 preset 目录始终是供用户手动选择的下层。其 custom 投影不受“与 preset 是什么关系”的约束,可以原样承接一个 preset。`custom` 与 preset 目录没有固定关系,一个最合适的 preset 也可以原样成为完整基础。三套方案在整份 deck 的层面本身就显著不同:先定下三个大方案,再补全各自细节,最后才映射到 mode、visual style、rendering、色彩、字体和图标等具体选项。差异存在于方案本身,而不是由某个指定字段来证明——由该方案设计真正需要的组件承担,任何组件都可以承担,也任何组件都允许一致。仅换名称、note 或参考数量不构成差异;所有组件都完全相同的三项也不成其为三套方案。当用户或模板的真值锁定了部分组件时,由其余开放组件承担差异;只有在没有任何开放组件时投影才可以完全相同,并须如实说明边界而不是强行制造差异。三套成套方案全部完成后,Strategist 才按已确认契约与来源比较整体适配度,把首选方案的实际零基索引写入 `design_directions.selected`;数组顺序不表示偏好。选择参考前只读取 mode、visual style 与 rendering 的三个目录索引;各方向的基础冻结后,只读取去重后的已选细节文件并完成 `custom` 行为。图片来源是独立判断,所以即使最初不推荐 AI 图片,每套方向也已包含 `rendering` 候选。首选方向卡片会被标记并在初始时应用;点击未激活的方向卡片会应用其不可变的整套方案,选中的 `custom` 投影卡片随后可原位编辑,下层控件也可彼此分离。已调整的活动卡片提供显式恢复操作,最终状态只保存编辑后的当前组件值,不把方向 `id` 当作执行权威。
+三套成套方向仍把 mode、visual style 与生成图 rendering 投影为可编辑的 `custom`。每套方向都是在已确认契约内自顶向下完成的一套完整设计,而不是自下而上从目录里拼选出来的;给三套是为了不让单一推荐把用户锁死,固定 preset 目录始终是供用户手动选择的下层。其 custom 投影不受“与 preset 是什么关系”的约束,可以原样承接一个 preset。`custom` 与 preset 目录没有固定关系,一个最合适的 preset 也可以原样成为完整基础。三套方案在整份 deck 的层面本身就显著不同:先定下三个大方案,再补全各自细节,最后才映射到 mode、visual style、rendering、色彩、字体和图标等具体选项。差异存在于方案本身,而不是由某个指定字段来证明——由该方案设计真正需要的组件承担,任何组件都可以承担,也任何组件都允许一致。仅换名称、note 或参考数量不构成差异;所有组件都完全相同的三项也不成其为三套方案。当用户或模板的真值锁定了部分组件时,由其余开放组件承担差异;只有在没有任何开放组件时投影才可以完全相同,并须如实说明边界而不是强行制造差异。三套成套方案全部完成后,自由设计按已确认契约与来源比较整体适配度,把最优者的零基索引写入 `design_directions.selected`。已安装模板时,三套方案都遵守同一套解析后的模板上下文;`selected` 指向其中最充分表达该模板的可行方案,另外两套只在开放维度上变化,不得通过弱化模板使用或拆分其片段来制造差异。数组顺序不表示偏好。选择参考前只读取 mode、visual style 与 rendering 的三个目录索引;各方向的基础冻结后,只读取去重后的已选细节文件并完成 `custom` 行为。图片来源是独立判断,所以即使最初不推荐 AI 图片,每套方向也已包含 `rendering` 候选。首选方向卡片会被标记并在初始时应用;点击未激活的方向卡片会应用其不可变的整套方案,选中的 `custom` 投影卡片随后可原位编辑,下层控件也可彼此分离。已调整的活动卡片提供显式恢复操作,最终状态只保存编辑后的当前组件值,不把方向 `id` 当作执行权威。
最终 Stage 2 确认的三个主动执行值始终保留为相互独立的原始证据。
尤其是,启用旁白可以在 Design Spec 中启用 Speaker Notes 的最终有效结果,
diff --git a/docs/zh/templates-architecture.md b/docs/zh/templates-architecture.md
index 5d026e93..b61d17e9 100644
--- a/docs/zh/templates-architecture.md
+++ b/docs/zh/templates-architecture.md
@@ -435,6 +435,8 @@ apply 阶段解析一份 library 裸 spec 或全部 project 限定名 spec;根
安装模板不会让沟通问题消失。Stage 1 把同一份开放式沟通契约与模板选择同时确认,但两者相互独立:沟通推荐只使用当前请求、源材料事实、对话约束和项目初始化状态,连模板画布也不能参与。Stage 1 完成且所选模板安装后,最终 Stage 2 才读取该状态,并确认完整方案与制作计划。Brand 提供身份约束、结构仍然自由;Style 提供方法和视觉默认值候选并保持 flat;Layout 提供结构能力;Deck 提供描述性的可复用应用语境供对照,但不充当当前项目契约。Style-only 时 Strategist 不读取原型,固定写入 `template_reuse_scope: style` 与 flat 结构;其他情况读取全部有效原型(有 Layout 时用 Layout,否则用 Deck)和当前内容,生成页面/原型计划,并把 `mirror`、`layout` 或 `style` 记录为内部导出值。按 mirror 创建的工作区因此只提供原样复用能力,不会强制使用。
+Default 仍提供三套符合模板约束的设计方向。其中的推荐方向是最充分表达解析后模板上下文的可行方案;另外两套只在模板和用户留白的维度上变化。Quick 不生成候选集,而是直接执行同一套推荐规则。
+
Default 确认一段自然语言 `template_application`;Quick 形成同样的决策,但只冻结在当前上下文。用户明确要求优先;否则 agent 根据内容与完整 SVG roster 判断,没有更强理由时默认按参照型使用。参照型、增强型、替换型只是描述性范式,不是固定字段;任何针对单个原型的例外必须写出精确 SVG 文件名。运行时选择不改变模板结构能力:自由设计及仅 Brand/Style 的输出保持 flat;Layout/Deck 输出保留显式 Master/Layout/slot 元数据,除非用户明确要求只参考视觉并舍弃结构。Confirm UI 显示自由设计/使用模板和这段文本,但不显示内部复用/遵循字段。规划语义由 `references/strategist.md` 与 `references/strategist-template.md` 负责;Default 的持久机器结构由 `templates/schemas/spec_lock.schema.json` 负责,Quick 则直接校验全页 SVG 结构合同。
---
diff --git a/skills/ppt-master/references/strategist-template.md b/skills/ppt-master/references/strategist-template.md
index a5ecdb9e..ac83226a 100644
--- a/skills/ppt-master/references/strategist-template.md
+++ b/skills/ppt-master/references/strategist-template.md
@@ -77,7 +77,9 @@ When the communication contract conflicts with the workspace, choose and state t
> Internal note: `content_divergence` controls source reorganization; the AI-derived `template_reuse_scope` records the reused layer; `template_adherence` records whether a structured plan keeps or extends existing Layout identities.
-**Template design precedence**: Explicit current user instructions and final confirmation win. The installed set contains at most one contribution per kind, and all four kinds may coexist. Brand identity overrides Deck identity when both are present. Layout overrides only Deck structure; Deck still owns its reusable application context and any identity not overridden by Brand. Without Layout, Deck owns structure. Style owns Direction / method only: its color, typography, icon, and image values are candidate defaults and never override resolved Brand/Deck identity or become official facts. Preferred Mode / Visual Style values seed Stage 2; the Style overlay must resolve into the final single `mode` and `visual_style` lock rather than create a parallel narrative or aesthetic authority. Style takes this segment ahead of ordinary Stage-2 defaults; the active structural prototypes and Deck Signature facts remain compatibility constraints, not a second method owner. Library/explicit provenance never changes this order. Each of the three directions still carries six palette roles and complete fonts: repeat fixed Brand/Deck values with `typography.fixed: true`; adapt Style candidates to that identity and vary only open roles. Keep resolved icon and image constraints. Style Review Focus never activates [`visual-review`](../workflows/stages/visual-review.md); only an explicit user request does.
+**Template design precedence**: Explicit current user instructions and final confirmation win. The installed set contributes at most one of each kind; all four may coexist. Brand overrides Deck identity. Layout overrides Deck structure; Deck retains application context and identity not overridden by Brand. Without Layout, Deck owns structure. Style owns Direction / method only: its visual values remain candidate defaults and yield to resolved Brand/Deck identity, while its preferred Mode / Visual Style seed the single final locks instead of creating parallel authority. Style takes this segment ahead of ordinary Stage-2 defaults; active prototypes and Deck Signature facts remain compatibility constraints. Library/explicit provenance never changes this order.
+
+**Default — template-led recommendation (may override when explicit user or confirmed-contract requirements demand another result)**: Make all three directions obey the same resolved template context. Repeat fixed Brand/Deck palette roles and complete fonts with `typography.fixed: true`; keep resolved icon/image constraints and vary only open roles or dimensions. Mark the viable direction that most fully expresses the template-owned or template-informed structure, visual language, and application rules as `design_directions.selected`. Never weaken template use or split its segments across cards to manufacture alternatives. Style Review Focus never activates [`visual-review`](../workflows/stages/visual-review.md); only an explicit user request does.
---
diff --git a/skills/ppt-master/references/strategist.md b/skills/ppt-master/references/strategist.md
index ff7928a6..8fe9756a 100644
--- a/skills/ppt-master/references/strategist.md
+++ b/skills/ppt-master/references/strategist.md
@@ -36,7 +36,7 @@ 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 · 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. 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. Each direction is one complete design authored top-down within the confirmed contract, never assembled bottom-up from catalog picks; three exist so a single recommendation cannot lock the user in, and the fixed catalogs stay the manual lower layer. Its custom projections are unrestricted by catalog relationship and may carry one preset unchanged. The three directions are plainly different designs at the whole-deck level before any field is written; that difference lives in the solutions, not in one designated field. Whichever components a direction's own design requires carry it — mode, visual style, rendering, color, type, or icons — any of them may, and none is required to differ. A different name, note, or reference count alone is not a difference, and projections identical on every component are not three solutions. Do not force safe / shifted / bold archetypes or artificial extremes. After all three bundles are complete, compare them against the confirmed contract and source, choose the strongest overall fit, and write its actual zero-based index as `design_directions.selected` (`0`, `1`, or `2`); array order never determines preference. 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. Each direction is one complete design authored top-down within the confirmed contract, never assembled bottom-up from catalog picks; three exist so a single recommendation cannot lock the user in, and the fixed catalogs stay the manual lower layer. Its custom projections are unrestricted by catalog relationship and may carry one preset unchanged. The three directions are plainly different designs at the whole-deck level before any field is written; that difference lives in the solutions, not in one designated field. Whichever components a direction's own design requires carry it — mode, visual style, rendering, color, type, or icons — any of them may, and none is required to differ. A different name, note, or reference count alone is not a difference, and projections identical on every component are not three solutions. Do not force safe / shifted / bold archetypes or artificial extremes. After all three bundles are complete, choose the strongest overall fit when no template is installed; with installed template state, choose the viable direction that most strongly expresses its resolved context under [`strategist-template.md`](./strategist-template.md). Write its actual zero-based index as `design_directions.selected` (`0`, `1`, or `2`); array order never determines preference. 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`.
**Default — continuity-aware whole solution (may override when a scene reset communicates better)**: Within active-profile invariants and before recommending page count or production mechanics, judge whether adjacent explanation beats can remain within one recognizable mental map while a visible state changes. Where that choice lowers cognitive switching and motion has a named communication job, let it shape the solution's narrative spine, page rhythm, visual approach, and enabled notes/narration segmentation, and recommend the existing `proactive_custom_animations: true`. This is one positive signal, not the only reason to enable animation; absent it, retain the existing default or other valid evidence. Topic or wording repetition alone is insufficient. A `Motion suggestion` remains optional advice and never changes the effective outcome.
diff --git a/skills/ppt-master/scripts/docs/confirm_ui.md b/skills/ppt-master/scripts/docs/confirm_ui.md
index c7e69af5..0391cd53 100644
--- a/skills/ppt-master/scripts/docs/confirm_ui.md
+++ b/skills/ppt-master/scripts/docs/confirm_ui.md
@@ -320,7 +320,7 @@ template-selection receipt.
- **Closed enumerable** — PPT reading mode (`delivery_purpose` compatibility key), 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 `custom` mode, `custom` visual style, color, typography, icon id, and `custom` generated-image rendering regardless of recommended image source. Its localized note is a compact, user-facing style summary. It may reuse localized display labels from `catalogs.visual_styles` when they describe the result concisely, but those labels are optional vocabulary rather than a selection constraint or required mapping. Otherwise it uses concise natural language and never forces the nearest label. The summary stays within one or two short sentences and does not expose catalog ids or reference mechanics. Each candidate is one complete design authored top-down within the confirmed contract, never assembled bottom-up from catalog picks; three exist so a single recommendation cannot lock the user in, while the fixed catalogs stay the manual lower layer. Its custom projections are unrestricted by catalog relationship and may carry one preset unchanged. The three candidates are plainly different designs at the whole-deck level, and that difference lives in the solutions rather than in one designated field: whichever components a candidate's design requires carry it, and mode, visual style, rendering, catalog bases, color, typography, and icons are each free to coincide. A different name, note, or reference count alone is not a difference, and candidates identical on every component are not three solutions. Do not force safe / shifted / bold archetypes. Where authoritative user/template truth fixes some components, the remaining open ones carry the difference; identical projections are valid only when nothing is open, stated as that boundary in the direction note. After completing all three bundles, Strategist compares them against the confirmed contract and source, then writes the strongest overall fit's zero-based index to `selected`; array position does not determine preference. That bundle becomes the initial default and applies its three custom projections coherently. 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. Its localized note is a compact, user-facing style summary. It may reuse localized display labels from `catalogs.visual_styles` when they describe the result concisely, but those labels are optional vocabulary rather than a selection constraint or required mapping. Otherwise it uses concise natural language and never forces the nearest label. The summary stays within one or two short sentences and does not expose catalog ids or reference mechanics. Each candidate is one complete design authored top-down within the confirmed contract, never assembled bottom-up from catalog picks; three exist so a single recommendation cannot lock the user in, while the fixed catalogs stay the manual lower layer. Its custom projections are unrestricted by catalog relationship and may carry one preset unchanged. The candidates are plainly different whole-deck designs; any component may carry the difference or coincide. Names, notes, or reference counts alone do not distinguish them, and identical projections are valid only when authoritative truth leaves nothing open, stated in the note instead of inventing variation. Do not force safe / shifted / bold archetypes. After completing all three bundles, Strategist writes the strongest overall fit's zero-based index to `selected` when no template is installed. With installed template state, every candidate obeys the same resolved context; `selected` identifies the viable candidate that most fully expresses it, while the other two vary only open dimensions—never by weakening template use or splitting segments across cards. Array position does not determine preference. That bundle becomes the initial default and applies its three custom projections coherently. 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; all three are editable after selection and a selected custom value cannot be blank. The original recommendation remains immutable so the active whole-direction card can explicitly restore every edited component without making an ordinary card click destructive. 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.
diff --git a/skills/ppt-master/workflows/profiles/quick-generate.md b/skills/ppt-master/workflows/profiles/quick-generate.md
index 0be8ca4f..57b58e48 100644
--- a/skills/ppt-master/workflows/profiles/quick-generate.md
+++ b/skills/ppt-master/workflows/profiles/quick-generate.md
@@ -290,11 +290,15 @@ Read ${SKILL_DIR}/templates/tables/table-vocabulary.md
```
This batch is the complete capability map for planning, not a usage checklist:
-zero use of any capability remains valid. Resolve the best whole solution from
-the project brief and loaded decision authorities, freeze its exact
-mode/style/rendering ids, then read only those selected detail files or custom
-bases. A novel custom reads none. Never open unselected detail siblings to
-compare candidates, glob a catalog, or let them influence the decision. Decide
+zero use of any capability remains valid. Resolve one recommended whole
+solution directly; do not materialize Default's three candidates. Without an
+installed template, choose the strongest overall fit from the project brief and
+loaded decision authorities. With one, choose the viable solution that most
+fully expresses the resolved template context and frozen Template Application,
+varying only dimensions they leave open. Freeze its exact mode/style/rendering
+ids, then read only those selected detail files or custom bases. A novel custom
+reads none. Never open unselected detail siblings to compare candidates, glob a
+catalog, or let them 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.