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

feat(image-generation): add AI decorative lettering workflow

hugohe3c66aefb0dab1
diff --git a/docs/powerpoint-svg-mapping.md b/docs/powerpoint-svg-mapping.md
index f06771ba..c9acc9d5 100644
--- a/docs/powerpoint-svg-mapping.md
+++ b/docs/powerpoint-svg-mapping.md
@@ -136,7 +136,7 @@ preset selection and authoring behavior are documented in
| Bulleted paragraph | Recognized leading bullet form | Native DrawingML bullet | `Native-normalized` | Only the registered bullet grammar is promoted |
| Rotated text | Supported transform on the text object | Rotated text shape | `Native-normalized` | Skewed text and browser-only transforms are unsupported |
| Text shadow or glow | Supported filter/effect contract | One native outer shadow or glow | `Approximate` | One supported effect graph only; review material effects |
-| WordArt, text warp, or text-on-path | No registered main-route mapping | Not generated as native WordArt | `Bake-required` or rebuild with ordinary text/geometry | Browser rendering does not imply PowerPoint support |
+| WordArt, text warp, or text-on-path | Prepared image asset for decorative lettering, or ordinary `<text>` as the editable fallback | Picture or ordinary text; never newly authored native WordArt | `Direct preservation` in source-preserving native routes; otherwise `Bake-required` or rebuild with supported carriers | No generated-SVG WordArt/warp/path attribute is registered; browser rendering does not imply PowerPoint support |
## 5. PowerPoint picture features
diff --git a/docs/roadmap.md b/docs/roadmap.md
index 87f2c2bc..22143452 100644
--- a/docs/roadmap.md
+++ b/docs/roadmap.md
@@ -36,7 +36,7 @@ A presentation is four layers: what is on the slide, how it is arranged, how it
| Object | Status | Notes |
|---|---|---|
| Text | Systematized | Role anchors deck-wide, bounded per-occurrence adjustment, hierarchy and paragraph rules, natively editable runs |
-| WordArt & warped text | Bounded by design | Native WordArt, text warp, and text-on-path are not generated; the same emphasis is rebuilt with ordinary editable text, registered text treatments, and geometry, so every glyph stays a real text run |
+| Native WordArt & warped text | Not planned | AI-generated decorative lettering is the preferred visual carrier, with ordinary editable text as the fallback. Native WordArt, text warp, and text-on-path would add a separate authoring and compatibility surface without improving that path, so they are not generated |
| Vector shapes | Systematized | primitive → Office preset → Boolean → freeform construction ladder, with native conversion rules |
| Lines & connectors | Asymmetric by design | Native `p:cxnSp` export is implemented, and endpoint attachment is restored on the preserve/mirror round-trip from a source deck. Newly authored connectors stay unconnected. Binding them would first require deciding which lines are real edges and which are decoration — an intent judgment that no geometric threshold settles, and one that is made by the AI wherever it is placed, so moving it upstream to authoring buys no reliability. The result would be some arrows in a diagram following their node and others not |
| Icons | Systematized | Bundled libraries with per-project sync; project icons are prepared material |
diff --git a/docs/why-ppt-master.md b/docs/why-ppt-master.md
index 5215659a..0a3ac404 100644
--- a/docs/why-ppt-master.md
+++ b/docs/why-ppt-master.md
@@ -30,7 +30,7 @@ Editable is already table stakes — exporting each slide as an editable `.pptx`
And this depth is a **direction of travel, not a fixed list.** The project's north star is to keep converging with PowerPoint itself — an ongoing effort to build and integrate more of its native capabilities, release after release, narrowing the gap between what an AI can generate for you and what you could build by hand in PowerPoint.
-So the boundary is honest, and it moves. Some things are out of scope today — **SmartArt** (a closed, brittle object model, deliberately left out and better rebuilt from ordinary native shapes), a few decorative effects (WordArt, reflection, soft edges), and embedded or legacy objects (OLE, video, macros). Native equations cover standalone blocks and same-paragraph inline math, with an executable input profile pinned to the documented Microsoft 365 versions and a PowerPoint 2010+ package target; repository verification is compiler/OMML/package-level rather than complete Microsoft 365 UI certification. Matrices and multiline derivations remain block-level. PPTX import can rebuild only PPT Master-owned, validator-clean OMML into normalized formula markers; it does not recover arbitrary third-party Office Math or the author's original LaTeX spelling. Cross-client rendering/editability is not promised. What's in and what's out is never hand-waved: the exact, feature-by-feature boundary — native / approximate / bake-required / unsupported — is published in the [PowerPoint ↔ SVG Mapping Guide](./powerpoint-svg-mapping.md).
+So the boundary is honest, and it moves. Some things are deliberately outside it — **SmartArt** (a closed, brittle object model, better rebuilt from ordinary native shapes), native WordArt and warped text (AI-generated decorative lettering plus ordinary editable text already cover the use case), a few other decorative effects (reflection, soft edges), and embedded or legacy objects (OLE, video, macros). Native equations cover standalone blocks and same-paragraph inline math, with an executable input profile pinned to the documented Microsoft 365 versions and a PowerPoint 2010+ package target; repository verification is compiler/OMML/package-level rather than complete Microsoft 365 UI certification. Matrices and multiline derivations remain block-level. PPTX import can rebuild only PPT Master-owned, validator-clean OMML into normalized formula markers; it does not recover arbitrary third-party Office Math or the author's original LaTeX spelling. Cross-client rendering/editability is not promised. What's in and what's out is never hand-waved: the exact, feature-by-feature boundary — native / approximate / bake-required / unsupported — is published in the [PowerPoint ↔ SVG Mapping Guide](./powerpoint-svg-mapping.md).
And out of scope rarely means *can't* — more often it means *not yet* (the timing isn't right) or *not worth it* (for a niche effect, a quick manual tweak in PowerPoint beats the engineering cost). That call is easy to make precisely because PPT Master's output is a high-quality **draft you keep editing, not a sealed final deck** — the last mile is yours by design.
diff --git a/docs/zh/powerpoint-svg-mapping.md b/docs/zh/powerpoint-svg-mapping.md
index 8c1c72f5..929c180c 100644
--- a/docs/zh/powerpoint-svg-mapping.md
+++ b/docs/zh/powerpoint-svg-mapping.md
@@ -130,7 +130,7 @@ PowerPoint 意图
| 项目符号段落 | 已识别的前导项目符号形式 | 原生 DrawingML bullet | `Native-normalized` | 仅提升已登记 bullet 语法 |
| 旋转文本 | 文本对象上受支持的 transform | 旋转文本 shape | `Native-normalized` | 倾斜文本与浏览器专属 transform 不受支持 |
| 文本阴影或发光 | 受支持 filter/effect 合同 | 一个原生外阴影或发光 | `Approximate` | 仅支持一个已登记效果图;实质效果需复核 |
-| WordArt、文本变形或沿路径文本 | 无已登记主路线映射 | 不生成原生 WordArt | `Bake-required` 或使用普通文本/几何重建 | 浏览器可渲染不代表 PowerPoint 受支持 |
+| WordArt、文本变形或沿路径文本 | 装饰文字使用已准备的图片资产,或用普通 `<text>` 作为可编辑兜底 | 图片或普通文字;不新建原生 WordArt | 源保留型原生路线为 `Direct preservation`;其他路线需要 `Bake-required` 或使用受支持载体重建 | 不登记任何生成 SVG 的 WordArt / 变形 / 路径文字属性;浏览器可渲染不代表 PowerPoint 受支持 |
## 5. PowerPoint 图片功能
diff --git a/docs/zh/roadmap.md b/docs/zh/roadmap.md
index 3df06c14..2065e5b3 100644
--- a/docs/zh/roadmap.md
+++ b/docs/zh/roadmap.md
@@ -36,7 +36,7 @@
| 对象 | 状态 | 说明 |
|---|---|---|
| 文字 | 系统化 | 全 deck 字号角色锚点、逐处受限微调、层级与段落规则、原生可编辑文本 |
-| WordArt 与文字变形 | 有意边界 | 不生成原生 WordArt、文字变形与路径文字;同样的强调改用普通可编辑文字、已注册的文字处理与几何重建,每个字形都保持为真实文本 run |
+| 原生 WordArt 与文字变形 | 暂不考虑 | 艺术字首选 AI 生成的装饰文字图片,普通可编辑文字负责兜底。原生 WordArt、文字变形与路径文字会额外引入一套创作和兼容性表面,却不能改善这条主路径,因此不生成 |
| 矢量形状 | 系统化 | primitive → Office preset → Boolean → freeform 构造阶梯,附原生转换规范 |
| 线条 / 连接符 | 有意的不对称 | 原生 `p:cxnSp` 导出已实现,端点绑定在来源 deck 的 preserve/mirror 往返路径上会被还原。新创作的连接符保持不连接。要绑定就得先判断哪些线是真实的边、哪些是装饰——这是意图判断,任何几何阈值都定不下来;而无论把这个判断放在导出期还是创作期,做判断的都是 AI,往上游挪并不会更可靠。结果只会是同一张图里有的箭头跟着节点走、有的不走 |
| 图标 | 系统化 | 内置图标库 + 逐项目同步;项目图标属于已准备材料 |
diff --git a/docs/zh/why-ppt-master.md b/docs/zh/why-ppt-master.md
index b7e99841..b00986fa 100644
--- a/docs/zh/why-ppt-master.md
+++ b/docs/zh/why-ppt-master.md
@@ -30,7 +30,7 @@
而这份深度是**一个前进方向,不是一张固定清单。** 项目的北极星是持续向 PowerPoint 本身靠拢——不断开发、集成更多它的原生能力,一个版本接一个版本,缩小「AI 能替你生成的」和「你在 PowerPoint 里手工能做出的」之间的差距。
-所以边界是诚实的,而且它在移动。有些能力今天还不在范围内——**SmartArt**(一个封闭、脆弱的对象模型,被刻意排除,其含义更适合用普通原生形状重建)、少数装饰性效果(艺术字、反射、柔化边缘)、以及嵌入 / 遗留对象(OLE、视频、宏)。原生公式已覆盖独立块级公式和同段行内公式,可执行输入档位锁定到所述 Microsoft 365 文档版本,生成包仍面向 PowerPoint 2010+;仓库验证覆盖编译器、OMML 与包结构,不等同于完整的 Microsoft 365 UI 认证。矩阵与多行推导继续使用块级形式。PPTX 导入只会把 PPT Master 自有且通过校验的 OMML 恢复为规范公式 marker;不恢复任意第三方 Office Math,也不恢复作者原始 LaTeX 写法。跨客户端公式显示与编辑仍不在承诺内。哪些在内、哪些在外从不含糊:逐条的功能对照边界——原生 / 近似 / 需烘焙 / 不支持——都公开在 [PowerPoint ↔ SVG 映射指南](./powerpoint-svg-mapping.md) 里。
+所以边界是诚实的,而且它在移动。有些能力被明确留在范围外——**SmartArt**(一个封闭、脆弱的对象模型,其含义更适合用普通原生形状重建)、原生 WordArt 与文字变形(AI 生成的装饰文字图片加普通可编辑文字已经覆盖这类需求)、少数其他装饰性效果(反射、柔化边缘),以及嵌入 / 遗留对象(OLE、视频、宏)。原生公式已覆盖独立块级公式和同段行内公式,可执行输入档位锁定到所述 Microsoft 365 文档版本,生成包仍面向 PowerPoint 2010+;仓库验证覆盖编译器、OMML 与包结构,不等同于完整的 Microsoft 365 UI 认证。矩阵与多行推导继续使用块级形式。PPTX 导入只会把 PPT Master 自有且通过校验的 OMML 恢复为规范公式 marker;不恢复任意第三方 Office Math,也不恢复作者原始 LaTeX 写法。跨客户端公式显示与编辑仍不在承诺内。哪些在内、哪些在外从不含糊:逐条的功能对照边界——原生 / 近似 / 需烘焙 / 不支持——都公开在 [PowerPoint ↔ SVG 映射指南](./powerpoint-svg-mapping.md) 里。
而且「不在范围内」很少等于「做不到」——更多时候是「时机未到」,或者「性价比不划算」(一个小众效果,去 PowerPoint 里手动改一下,比为它做工程更值)。这个取舍之所以好做,正因为 PPT Master 的产出是一份高质量的**草稿、供你继续修改,而不是封死的成品**——最后一公里本就交给你。
diff --git a/skills/ppt-master/references/executor-base.md b/skills/ppt-master/references/executor-base.md
index 591d0663..ff2602d0 100644
--- a/skills/ppt-master/references/executor-base.md
+++ b/skills/ppt-master/references/executor-base.md
@@ -115,6 +115,7 @@ Apply the content-vs-expression contract above within the selected reading mode.
- **Core message ≥ `body`**: map the page's primary claim to declared `lead` / `subtitle`, never below the current body treatment. Footnotes, page numbers, and credits use declared `footnote` / `annotation`; do not invent a smaller role.
- **Write unitless px, with at most two decimals.** Structural and mapped-role text uses only its anchor or a value within its `±2`px band; the sparse display-size exception is defined separately below. Do not substitute familiar pt-style numbers or emit long precision tails.
- **Sparse display-size exception**: a short non-structural Hero/Display element may use one undeclared size outside all anchor bands at most twice across the deck without a lock row. The third occurrence makes that size recurring: stop and return to Strategist to name the role in the Design Spec and `spec_lock.md`, then read back and validate the affected fragments before reuse. This exception never applies to titles, body copy, subtitles, annotations, footnotes, captions, data labels, or card copy, and nearby sizes must not be introduced to imitate one recurring treatment.
+- **Prepared decorative lettering**: When the approved plan selects stable artistic lettering as part of the visual, place its prepared AI/slice file as an image asset and keep the ordinary editable title/subtitle in separate native text frames. Do not recreate the asset with layered glyph copies or native WordArt; when the plan selects the text fallback instead, use ordinary `<text>` without inventing a missing image.
- **Outside-band recovery**: for structural text, reflow geometry and use the declared role band locally. For a sparse display occurrence, keep the unitless value and verify that its deck-wide count remains at most two. Never flatten a justified distinction or add a role merely to silence the checker. Mirror pages preserve exact source typography as inherited input.
- Images MUST reference files listed under `images`; no invented filenames
- For math, load [`native-formula.md`](./native-formula.md): simple notation stays text; one-line structural prose uses inline; matrices, multiline derivations, or standalone high structure use block. Keep exact LaTeX plus preview; never use an image.
diff --git a/skills/ppt-master/references/image-generator.md b/skills/ppt-master/references/image-generator.md
index ca18f32c..ea25b8a0 100644
--- a/skills/ppt-master/references/image-generator.md
+++ b/skills/ppt-master/references/image-generator.md
@@ -2,7 +2,7 @@
# Image_Generator Reference Manual
-Role definition for the **AI image generation path**: convert each active `Acquire Via: ai` row into an optimized prompt, generate the image, and save it to `project/images/`; also defines the `slice` derivation path for AI-generated illustration sheets.
+Role definition for the **AI image generation path**: convert each active `Acquire Via: ai` row into an optimized prompt, generate the image, and save it to `project/images/`; also defines the `slice` derivation path for AI-generated illustration and decorative-lettering sheets.
**Trigger**: the Default Generate resource list contains `Acquire Via: ai` or `slice`, or Quick Generate has resolved a required AI/sliced image in active context. Load only when at least one such resource exists.
@@ -248,21 +248,29 @@ Example opening for a triptych hero:
**When uncertain about field conventions**: read `sources/` before drafting the prompt.
-### 4.3 Illustration sheets — one generation, many spot elements
+### 4.3 Illustration sheets — one generation, many spot or lettering elements
-An illustration sheet can produce several small **spot illustrations** in one generation and preserve closely matched rendering, deck-color treatment, and line quality before slicing.
+An Illustration Sheet can produce several small **spot illustrations** or
+**decorative lettering elements** in one generation and preserve closely
+matched rendering, deck-color treatment, and finish before slicing. A lettering
+sheet is the batch form of stable Layer 1 artwork; it does not turn page copy
+into an image.
-**Default — one sheet for a compatible spot family (may override when separate generation serves the assets better)**: Prefer a sheet when several elements share similar proportions, detail, quality, and semantic precision. Generate elements separately when those needs differ materially; quantity alone neither requires nor forbids a sheet. A single hero/local image stays with the normal one-row-per-image flow (§4.1).
+**Default — one sheet for a compatible asset family (may override when separate generation serves the assets better)**: Prefer a sheet when several spots or lettering elements share similar proportions, detail, quality, and semantic precision. Generate elements separately when those needs differ materially; quantity alone neither requires nor forbids a sheet. A single hero/local image or standalone artistic word stays with the normal one-row-per-image flow (§4.1).
-**Hard rule**: a spot sheet is a generation source, not a slide asset. In Default Generate, keep the sheet row out of `spec_lock.md images`; in Quick Generate, retain its generation-only status in active context and the operational manifest. The sheet is never referenced from SVG. Only sliced element rows are placed.
+**Hard rule**: a sheet is a generation source, not a slide asset. In Default Generate, keep the sheet row out of `spec_lock.md images`; in Quick Generate, retain its generation-only status in active context and the operational manifest. The sheet is never referenced from SVG. Only sliced element rows are placed.
-**Sheet prompt convention** (one manifest item, `page_role: local`, `text_policy: none`, `image_size` chosen from final placement size):
+**Sheet prompt convention** (one manifest item, `page_role: local`,
+`image_size` chosen from final placement size; spot sheets use
+`text_policy: none`, lettering sheets use `text_policy: embedded`):
- Choose the sheet `aspect_ratio` and `--grid` from the target element shape. Do not default every sheet to `1:1` + a symmetric grid.
- Lay the elements out in an explicit **R×C grid, evenly spaced with clear gutters**, each element **centered in its own cell** and isolated (no element bleeds into a neighbor).
-- State the intended cell shape in the prompt: compact square object, tall portrait element, or wide landscape vignette. Do not let the model shrink every subject into a centered square sticker.
+- State the intended cell shape in the prompt: compact square object, tall portrait element, wide landscape vignette, or wide lettering mark. Do not let the model shrink every subject into a centered square sticker.
- One **flat single-color background** across the whole sheet, set to the deck's background/secondary HEX — this is what lets the slicer key it out cleanly and lets the cut element sit on the slide without a visible box.
-- Shared `deck_rendering` + `color_scheme` as always. NO text, labels, or numbers anywhere (§5.1, §5.3).
+- Shared `deck_rendering` + `color_scheme` as always.
+- **Spot sheet**: apply the §5.3 `none` cue; include no text, labels, or numbers.
+- **Lettering sheet**: put exactly one named stable string in each cell as the only text, quote every complete character sequence literally in the prompt, and describe one shared artistic treatment. Keep each mark isolated on the flat key background with no scene, title copy, labels, watermark, mockup surface, or unrequested symbols.
**Cell geometry is designed, not assumed.** `slice_images.py --grid RxC` cuts rows first and columns second. The cell ratio is:
@@ -277,12 +285,13 @@ Use that deliberately. On a wide sheet (`16:9`, `21:9`, `4:1`, `8:1`), `1xN` mak
| Compact objects / badges | `1:1` sheet | `2x2`, `2x3`, or `3x3` |
| Tall side accents / upright objects | wide or square sheet | `1xN`, or any `MxN` whose cells are portrait |
| Wide banners / horizontal vignettes | wide sheet | `Nx1`, or any `MxN` whose cells are landscape |
+| Decorative words / short lettering marks | wide sheet | `Nx1`, or any `MxN` whose cells fit the planned word shapes |
If one deck needs mixed shapes, create separate sheets per shape family unless one carefully designed grid gives every element enough room. Keep the visual family consistent through the same `deck_rendering` and `color_scheme`, not by forcing all cells into one square sheet.
**Resource contract — the sheet and its elements are different row kinds.** A sliced element can only be placed if it exists in the active placeable-resource authority: `spec_lock.md images` in Default Generate or the current agent's prepared resource decision in Quick Generate. Default Generate keeps both row kinds in §VIII under [`strategist-image.md`](./strategist-image.md); Quick Generate resolves the same distinction in active context and its operational manifest without creating planning artifacts:
-- **Sheet row** — `Acquire Via: ai`, `Type: Illustration Sheet`, the intent prompt, named as the slice source with its intended cell shape and placement purpose (`Reference: landscape footer-vignette spot set`). It is generated in Step 5 but **never placed on a slide** — keep it **out of** `spec_lock.md images`. Image_Generator resolves the exact `aspect_ratio`, grid, and slice command from this intent.
+- **Sheet row** — `Acquire Via: ai`, `Type: Illustration Sheet`, the intent prompt, named as the slice source with its intended cell shape and placement purpose (`Reference: landscape footer-vignette spot set`, or `decorative lettering set: exact strings = ...`). It is generated in Step 5 but **never placed on a slide** — keep it **out of** `spec_lock.md images`. Image_Generator resolves the exact `aspect_ratio`, grid, and slice command from this intent.
- **Element rows** — one per used element, `Acquire Via: slice`, filename matching a `--names` output, `Reference` naming the parent sheet + cell/element. These **are** placed — list every one in the active placeable-resource authority, normally with `crop=no-crop` (a tight-trimmed transparent spot should be fit, not cover-cropped). Their dimensions are filled in after slicing (the preparation pass re-runs `analyze_images.py`). Each row carries an owner-resolved layout recommendation; SVG authoring may realize it as a direct cutout or inside an appropriate container while preserving the resource and crop/content constraints.
For traceability, add optional `slice_grid` and `slice_names` fields to the sheet item in `image_prompts.json` after choosing the geometry. `image_gen.py` validates, preserves, and displays these metadata fields; it does not run the separate slicing command.
@@ -297,12 +306,12 @@ python3 scripts/slice_images.py <project>/images/illus_sheet.png --grid 2x3 \
**Three constraints that decide whether it looks good**:
1. **Flat background, matched to the slide.** `image_gen.py` has no transparent-background mode, so the cut element carries whatever was behind it. A flat sheet background (= deck background HEX) is what `--alpha` keys out and what makes non-keyed pieces blend.
-2. **Clean grid, or it cuts ugly.** State the exact row/column structure and cell shape so the model does not invent a square matrix; `--trim` absorbs smaller placement variance. Do not generate several sheets or read them back merely to choose a favorite; re-roll only when user/live-preview feedback exposes an unusable slice.
+2. **Clean grid, or it cuts ugly.** State the exact row/column structure and cell shape so the model does not invent a square matrix; `--trim` absorbs smaller placement variance. For lettering, a wrong/missing character, extra copy, fused cells, or scene background makes the parent sheet unusable. Do not generate several sheets or read them back merely to choose a favorite; re-roll only when user/live-preview feedback exposes an unusable slice, then slice the replacement sheet again.
3. **Generate only as large as needed.** Each cell is a fraction of the sheet. Pick the smallest sheet size that keeps each sliced cell at least **1.5-2x** the intended display size. `1K` is usually enough for small 80-160px decorative spots; use `2K` for medium 180-320px placements; reserve `4K` for large, cropped, or potentially enlarged elements.
-**Reference — sliced-asset placement is not a constraint**: A transparent slice may remain an unboxed cutout or enter a card, evidence frame, label, panel, or other suitable container. The owner-resolved layout text is an expression recommendation; SVG authoring owns the actual geometry and treatment while preserving the resource role and crop/content constraints.
+**Reference — sliced-asset placement is not a constraint**: A transparent slice may remain an unboxed cutout or enter a card, evidence frame, label, panel, or other suitable container. Decorative-lettering slices may combine with shapes or other slices, while ordinary titles/subtitles remain separate SVG text. The owner-resolved layout text is an expression recommendation; SVG authoring owns the actual geometry and treatment while preserving the resource role and crop/content constraints.
-**Through-line — one family, many roles.** A spot sheet pays off more when the same motif family also drives the cover and section dividers. A large cover / divider anchor is not a giant sheet cell—generate it as its own `hero_page` image sharing the sheet's `deck_rendering`, `color_scheme`, and subject world. Plan this only when the deck leans into illustration, never as a quota.
+**Through-line — one family, many roles.** A sheet pays off more when its visual family recurs coherently: an illustration sheet may share a motif world with cover/divider anchors, while a lettering sheet can supply the deck's small set of matching artistic hooks. A large cover/divider scene is not a giant sheet cell—generate it as its own `hero_page` image sharing the sheet's `deck_rendering` and `color_scheme`. Plan either relationship only when it serves the deck, never as a quota.
---
diff --git a/skills/ppt-master/references/strategist-image.md b/skills/ppt-master/references/strategist-image.md
index 6bf6fb63..b5ceb515 100644
--- a/skills/ppt-master/references/strategist-image.md
+++ b/skills/ppt-master/references/strategist-image.md
@@ -16,7 +16,7 @@ For illustration, apply this precedence: confirmed `none` → explicit user inte
**Context-first understanding for provided assets**: Do not visually scan `images/`. First infer identity, role, and crop / focus needs from source position and surrounding prose, captions / alt / titles, filename, user notes / confirmed `image_notes`, existing resource records, and CSV geometry. Inspect only one specific image when a remaining ambiguity would change selection, factual identity, page role, crop safety, or focal placement. Never inspect for inspiration, bulk-open the folder, or infer external facts / provenance from pixels. Record the result in §VIII. Leave an optional unresolved asset unused; route an unresolved must-use asset through failure recovery.
-**Default — one coherent sheet for compatible same-family spots (may override when aspect, detail, quality, or semantic needs differ)**: prefer one Illustration Sheet when several AI-generated spots can share a useful cell shape and production treatment; generate them independently when forcing one sheet would weaken a planned element. When a sheet is chosen, plan one unplaced `ai` Illustration Sheet row plus one placed `slice` row per used element; only slice rows enter `spec_lock.md images`. State the intended placement shape family in the sheet reference and use separate sheets for incompatible shapes. [`image-generator.md`](./image-generator.md) §4.3 owns grid, ratio, slicing, and execution details. Final Stage 2 chooses the AI execution path under `image-generator.md` §7; do not pre-empt or re-pick it here.
+**Default — one coherent sheet for compatible same-family spots or lettering elements (may override when aspect, detail, quality, or semantic needs differ)**: prefer one Illustration Sheet when several AI-generated spots or stable decorative-lettering elements can share a useful cell shape and production treatment; generate them independently when forcing one sheet would weaken a planned element. When a sheet is chosen, plan one unplaced `ai` Illustration Sheet row plus one placed `slice` row per used element; only slice rows enter `spec_lock.md images`. State the intended placement shape family in the sheet reference. For lettering, also record every exact string, set the sheet to `text_policy: embedded`, and keep authoritative title/chrome wording outside the sheet. Use separate sheets for incompatible shapes or treatments. [`image-generator.md`](./image-generator.md) §4.3 owns grid, ratio, slicing, and execution details. Final Stage 2 chooses the AI execution path under `image-generator.md` §7; do not pre-empt or re-pick it here.
**Mandatory — image-treatment path scan, not a quota**: Per selected image choose `none` (unchanged), `native` (SVG crop/clip, transform, opacity, frame/depth, overlap), or `prepared derivative` (separate pixel blur/tone or cutout/registered layers); `none` is valid.
@@ -48,4 +48,4 @@ References describe visual intent: AI uses subject + intent + composition withou
Choose narrative intent before dimensions, then apply the already-read [`image-layout-spec.md`](./image-layout-spec.md) to the actual page region. Techniques needing a cutout, blurred crop, or desaturated copy require that prepared asset. Write `Crop Policy: no-crop` whenever cropping could remove required pixels, labels, evidence, identity, or edge content; screenshots, charts, certificates/contracts, dense diagrams, logos, and product markings are common triggers rather than an exhaustive list. Otherwise write `Crop Policy: adaptive`: Executor may use complete display or a focal-safe crop, and the value never commands cropping.
-Judge `text_policy` per AI row using [`image-generator.md`](./image-generator.md) §5.3; paper figures, academic schematics, panel comparisons, and data-axis graphics are positive triggers for reconsidering an all-`none` plan. Step 5 dispatches pending `ai` / `slice` rows to Image_Generator and pending `web` rows to Image_Searcher.
+Judge `text_policy` per AI row using [`image-generator.md`](./image-generator.md) §5.3; paper figures, academic schematics, panel comparisons, data-axis graphics, and stable decorative lettering are positive triggers for reconsidering an all-`none` plan. Step 5 dispatches pending `ai` / `slice` rows to Image_Generator and pending `web` rows to Image_Searcher.
diff --git a/skills/ppt-master/references/strategist.md b/skills/ppt-master/references/strategist.md
index 47bb4b3c..15198854 100644
--- a/skills/ppt-master/references/strategist.md
+++ b/skills/ppt-master/references/strategist.md
@@ -311,6 +311,7 @@ user/template requirements bind.
| Image composition | Image-as-canvas, editorial crop, collage, cutout, or meaningful focus / comparison / evidence units carry the page better than an adjacent rectangle | Propose a permitted source; when selected, apply the already-loaded [`strategist-image.md`](./strategist-image.md) resource contract plus the conditional image-layout references, record a concise §VIII `Layout pattern` suggestion, and describe page-level image/overlay relationships in §IX `Layout` / `Images` |
| Native paint / overlay | Gradient, translucency, scrim, vignette, or wash supports focus, hierarchy, depth, legibility, or image integration | Record purpose/layering in §IX `Layout`, plus `Images` when imagery participates; no new field or type/stops/opacity/coordinates—Executor chooses realization |
| Native shape / Merge Shapes | A literal Office symbol, a stock bent/curved relationship contour, or a compound silhouette, negative-space cutout, overlap-only region, or meaningful fragmentation strengthens the visual idea | Add an optional §IX `Native shape suggestion` with the semantic result plus a candidate preset/Connector family or Boolean operation/operands |
+| AI decorative lettering asset | A small set of stable cover/divider keywords needs a material, dimensional, hand-rendered, or otherwise illustrative treatment beyond ordinary text | Apply [`strategist-image.md`](./strategist-image.md): when compatible, plan one unplaced AI Illustration Sheet plus one transparent `slice` row per used lettering element; record every exact string, keep ordinary title/chrome as native text, and choose ordinary text instead whenever editability is the stronger requirement |
| Page transition | A section/state change, spatial continuity, recorded/self-running flow, or the same semantic object changing position, scale, crop, or state across adjacent pages benefits from motion | Add an optional §IX `Motion suggestion` describing the communication job and any continuing object's initial state → action → end state; leave effect, ids, pairing names, and timing to Executor |
| Object animation | Progressive reveal, emphasis, movement, removal, or deliberate stillness clarifies sequence, causality, comparison, hierarchy, narration order, full-view → detail, atmosphere → evidence, or hotspot/annotation order | Add an optional §IX `Motion suggestion` naming each relevant semantic unit's lifecycle duty and initial state → communication action → end state, plus any meaningful order/relationship; leave group ids, effects, options, and timing to Executor |
diff --git a/skills/ppt-master/references/svg-effects.md b/skills/ppt-master/references/svg-effects.md
index 884c8bdc..779ad06f 100644
--- a/skills/ppt-master/references/svg-effects.md
+++ b/skills/ppt-master/references/svg-effects.md
@@ -584,6 +584,12 @@ respective sections; they do not weaken those contracts.
| Shadow/glow | §6.4 filter on `<text>` only | Shape shadow / run glow; `Approximate` |
| Native bullet | Leading `· • ● ▪ ■ ◆ ◇ ◦ ‣` + non-empty content | `·`/`•` → `•`; others unchanged; color/alpha from marker run; font/size follow text |
+**Hard rule — generated decorative lettering ownership**: Approved AI
+decorative lettering is a prepared `<image>` asset under the image contracts,
+not an advanced native-text treatment. Keep ordinary editable titles and
+subtitles as normal `<text>`; this contract does not add WordArt, text warp, or
+text-on-path authoring.
+
```xml
<text x="100" y="200" font-size="20" xml:space="preserve">Current <tspan
fill="#999999" text-decoration="line-through">old</tspan> value</text>
@@ -875,7 +881,7 @@ back-to-front and omit every layer without a distinct job.
| Page / deck job | Back-to-front stack | Stop |
|---|---|---|
-| Cover | Hero field → optional scrim/wash → purposeful opening/contour → native title | Stop when copy is safe and title/field read together |
+| Cover | Hero field → optional scrim/wash → purposeful opening/contour → native title, optionally paired with a prepared decorative-lettering image | Stop when copy is safe and title/field read together |
| Divider | Image band or quiet field → restrained wash → recurring geometry → number/title | Reuse deck language; add no effect family |
| Text-led explanation | Quiet field → recurring material/contour → native hierarchy → optional local emphasis | Emphasis clarifies the argument, never decorates body copy |
| Process / system | Context field → native relation lines → nodes/labels → optional state/direction focus | Every connector stays semantic; atmosphere must not obscure flow |
diff --git a/skills/ppt-master/workflows/generate-pptx.md b/skills/ppt-master/workflows/generate-pptx.md
index 8b2ee200..cadac334 100644
--- a/skills/ppt-master/workflows/generate-pptx.md
+++ b/skills/ppt-master/workflows/generate-pptx.md
@@ -522,7 +522,7 @@ A deck with only `ai` rows never loads `image-searcher.md`; a deck with only `we
> **Default — short provider query (may override for a complete entity name or necessary disambiguation)**: keep §VIII `Reference` as the locked subject/focal/crop intent and author a separate concrete `image_queries.json.query`. Search/review never rewrites the Design Spec or lock to fit a candidate.
-> **Default — one sheet for compatible AI spots (may override for different cell shape, detail, quality, or semantics)**: prefer one grid sheet for a same-family set; independent `ai` rows remain valid. When selected, choose a grid matching the planned cells, keep the sheet unplaced, and place/project each `slice` row. Contract: [image-generator.md](../references/image-generator.md) §4.3.
+> **Default — one sheet for compatible AI spots or decorative lettering elements (may override for different cell shape, detail, quality, or semantics)**: prefer one grid sheet for a same-family set; independent `ai` rows remain valid. A lettering sheet records every exact stable string and contains no scene or page chrome. When selected, choose a grid matching the planned cells, keep the sheet unplaced, and place/project each transparent `slice` row. Contract: [image-generator.md](../references/image-generator.md) §4.3.
> ⚠️ **Honor the Design Spec's confirmed image source before running any generation command**: the `ai` generation path (Path A = `image_gen.py` API / Path B = host-native tool / Offline Manual) is **not** auto-only — the production value recorded in `design_spec.md §I` wins. `host-native` forces Path B even when `IMAGE_BACKEND` is configured; `api` forces Path A; `manual` forces offline. Never reopen `result.json` here, and never run `image_gen.py --manifest` when the recorded value is `host-native` or `manual`. Full selection rule: [image-generator.md](../references/image-generator.md) §7 Path Selection.
@@ -530,7 +530,7 @@ Workflow:
1. Extract all resource rows from the design spec. First separate rows whose `Reference` starts `Derived from <canonical bare filename>; treatment=` so they cannot re-enter ordinary ai/web/slice acquisition; reject source/output equality, a derivative parent, chains, cycles, or self-reference; then group canonical rows by `Acquire Via`. Every Pending/Failed canonical acquisition row and Pending derivative must reach a terminal state before Executor starts.
2. Generate prompts (ai rows) and/or run search (web rows) per [image-base.md](../references/image-base.md) §3 dispatch table
-2.5. **Slice any spot-illustration sheets (only if `slice` rows exist).** For each generated `ai` **sheet** row, run `slice_images.py` (grid + the element `--names` matching the `slice` rows, `--trim --alpha`) so every element file lands in `images/`; mark each `slice` row `Generated`. A sheet still in `Needs-Manual` cannot be sliced — leave its `slice` rows `Needs-Manual` and surface them at the Step 7 readiness gate. Contract: [image-generator.md](../references/image-generator.md) §4.3.
+2.5. **Slice any illustration or lettering sheets (only if `slice` rows exist).** For each generated `ai` **sheet** row, run `slice_images.py` (grid + the element `--names` matching the `slice` rows, `--trim --alpha`) so every transparent element file lands in `images/`; mark each `slice` row `Generated`. A sheet still in `Needs-Manual` cannot be sliced — leave its `slice` rows `Needs-Manual` and surface them at the Step 7 readiness gate. Contract: [image-generator.md](../references/image-generator.md) §4.3.
2.6. **Materialize planned prepared derivatives.** After each named canonical source reaches a usable terminal state, preserve it and write the separately named derivative only from its declared treatment. Use `image_treat.py` for per-pixel blur, desaturation/grayscale, duotone, brightness, or contrast; that row inherits the canonical `Acquire Via` and terminal class. Use `image-generator.md` §4.4 only for registered clean-base/layer work; a supplied final asset is `user / Existing`, while generated/reconstructed output remains `ai / Generated`. A standalone cutout must be prepared RGBA, a flat-key slice, or supplied by the active host; otherwise mark it `Needs-Manual`. Do not present `image_treat.py` as photo background removal. Do not bake crop/clip, rotation/mirror, opacity, frame, shadow, scrim/wash, vignette, or overlap into a bitmap. Any derivative of a web source copies that source's license/attribution record to the new filename. A parent without a usable status leaves the child `Needs-Manual`.
3. Verify every processed acquisition/derivative row reaches its source-class terminal status under [`svg-image-embedding.md`](../references/svg-image-embedding.md); no `Pending`, `Failed`, or web `Needs-Selection` remains. On `auto`, follow the owning fallback chain. For confirmed `api` or `host-native`, retry only that path, then mark unresolved rows `Needs-Manual` without switching provider.
4. Re-derive image facts after canonical acquisition, slicing, and prepared derivatives are final — `python3 ${SKILL_DIR}/scripts/analyze_images.py <project_path>/images` — so `analysis/image_analysis.csv` reflects every image the Executor may place. Image facts are regenerated on use, never a stale store (see Step 4's image-facts note).
diff --git a/skills/ppt-master/workflows/profiles/quick-generate.md b/skills/ppt-master/workflows/profiles/quick-generate.md
index 9be6ef40..a066bb5a 100644
--- a/skills/ppt-master/workflows/profiles/quick-generate.md
+++ b/skills/ppt-master/workflows/profiles/quick-generate.md
@@ -329,6 +329,7 @@ because Quick is expected to be faster is not.
| Sequence, hierarchy, role, region, or relationship determines page-local topology | Qualitative structure |
| Rows, columns, cells, headers, merges, and alignment form the information model | Cell-grid table |
| Mathematical notation is clearer as typeset math than ordinary text | PowerPoint-native inline or block math |
+| A small set of stable cover/divider keywords needs a material, dimensional, hand-rendered, or otherwise illustrative treatment beyond ordinary text | Prepare one AI Illustration Sheet plus transparent slices when the elements are compatible; place the slices as images and keep ordinary editable title/chrome in separate text frames. Choose ordinary text before acquisition when editability or available tooling makes it the better carrier |
| Typography, spacing, and simple geometry already carry the message | Use no additional visual carrier |
This carrier menu does not satisfy or replace the per-page Structure decision in §3.
@@ -372,7 +373,7 @@ Prepare only the resource paths needed by the decided pages:
| Formula | Create no resource file. Retain the exact source LaTeX, then choose ordinary text, an inline native marker, or a block native marker under §3; the registered SVG preview is discarded by native export |
| AI image | Follow `image-base.md` + `image-generator.md`; apply only the chosen rendering preset or exact custom bases, never blend unselected catalog identities, and keep `image_prompts.json` plus its human-readable sidecar |
| Web image | Follow `image-base.md` + `image-searcher.md`; keep query/status data and `image_sources.json`, including any required on-slide attribution |
-| Illustration slice | Generate or obtain the parent sheet, run `slice_images.py`, and place only the resulting element files |
+| Illustration / lettering slice | Generate or obtain the parent sheet, run `slice_images.py --trim --alpha`, and place only the resulting transparent element files; a lettering sheet names every exact stable string and contains no scene or page chrome |
| Registered reconstruction group | Follow `image-generator.md` §4.4; keep full-canvas members registered with `crop=no-crop`, and materialize every required shared-plate member as an independent picture object |
| Visualization | Keep Chart values, Table cell topology, and chosen treatment in active context; load the applicable Chart/Table authority in §3 and write native replacement metadata only for an independently selected native-ready object |
@@ -523,8 +524,9 @@ and omit Master/Layout/layer/placeholder metadata. A request that specifically
requires reusable native Master/Layout/placeholder output is incompatible with
the lockless Quick exporter and must use the default lock-backed profile.
-**Typography**: name an installed concrete font family in the SVG; do not depend
-on a lock or generated font asset.
+**Typography**: name a concrete target-installed/approved PowerPoint family
+under [`shared-standards-core.md`](../../references/shared-standards-core.md)
+§4.1; do not depend on a lock or generated font asset.
**Generation pacing**: the current main agent hand-writes the SVG roster in
order. Use P01 as the visual-system calibration baseline and continue