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(roadmap): mark mode/visual-style validation done; log template-fill route

hugohe30fc208091fba
diff --git a/docs/roadmap.md b/docs/roadmap.md
index 079e8345..353fa35b 100644
--- a/docs/roadmap.md
+++ b/docs/roadmap.md
@@ -46,10 +46,12 @@ The past two months' structural capability growth. Single flags / incremental po
### 2026-06 — Mode & visual-style dual catalogs
+- **Replicate any PPTX's design → refill content route** ([`workflows/template-fill-pptx.md`](../skills/ppt-master/workflows/template-fill-pptx.md)) — when a user supplies an existing `.pptx` plus new material / a topic and asks to "reuse this deck's design / fill the content back in", this standalone workflow edits the PPTX directly and never enters the SVG generation pipeline. Output stays natively editable (it reuses the original slides' shapes / layouts, not a screenshot refill); it isolates private parts on reuse, exposes chart data, and runs capacity checks. Trigger follows the template rule — only on an explicit ask to reuse an existing deck — and it deliberately does not reflow / add pages / swap images (that's the from-scratch main route). Distinguished from Non-goals #53 below
- **Three executors retired → mode + visual-style dual catalogs** ([`references/modes/`](../skills/ppt-master/references/modes/) + [`references/visual-styles/`](../skills/ppt-master/references/visual-styles/)) — the old three `executor-*.md` (general / consultant / consultant-top) entangled domain · audience · persuasion · narrative on one axis; split into two orthogonal catalogs (following the `image-renderings` pattern: flat dir + `_index` + on-demand read + Strategist locks one). **mode** = narrative skeleton (`pyramid` / `narrative` / `instructional` / `showcase`; consultant + top merge into pyramid since their narrative core is identical); **visual-style** = SVG layout aesthetic (`swiss-minimal` / `editorial` / `soft-rounded` / `dark-tech`, each paired with an image-rendering, **zero HEX** — color truth stays in confirmation e + image-palettes). Strategist `§d` locks `mode` + `visual_style` independently into `spec_lock`; Executor loads the two locked files; any mode × any style. Render coordinates stay in `templates/charts/`
- **Prompt constraint-strength decoupling** ([`docs/rules/prompt-style.md`](rules/prompt-style.md) §4) — three explicit strength tiers — rule (`Hard rule` / `Forbidden`) / default (`Default — … may override`) / reference (`Reference — not a constraint`) — plus an "objective failure vs taste" test and a checker boundary, so the model can tell "must keep vs may deviate" at a glance; the visual-style catalog is Reference-strength throughout
- **visual-style catalog grows to 18, aligned with image-renderings + examples reclaimed** — first four distilled from the [examples library](../examples/) (`brutalist` / `blueprint` / `memphis` / `zine`), then six filling in the hand-drawn / textured renderings that have a layout twin (`sketch-notes` / `ink-notes` / `chalkboard` / `paper-cut` / `vintage-poster` / `pixel-art`), then four more reclaimed from still-uncovered example aesthetics: `ink-wash` (rice-paper whitespace, from 藏拙 / 李子柒) · `glassmorphism` (dark frosted-glass + gradient light, from glassmorphism_demo, split out of soft-rounded) · `photo-editorial` (full-bleed photography dominates, text captions, from Pritzker / fashion_weekly) · `data-journalism` (Bloomberg/Economist multi-column micro-charts + sidebars, from global_ai_capital). The catalog is regrouped into five families (corporate-product / editorial-publication / expressive-print / hand-drawn-brush / specialty). **The test**: a rendering earns a visual-style twin only when it defines a whole-page layout language, not merely how an inserted image looks — so photo-*led composition* gets `photo-editorial` (paired with corporate-photo), while purely atmospheric renderings (nature / warm-scene / fantasy-animation) stay imagery-only and just pair with a layout style. Zero HEX, Reference strength throughout
- **mode catalog grows to 5: add `briefing`** — fills the "neutral information delivery" cell: no thesis, no story, no teaching, no spectacle — topic titles, even weight, complete and scannable, for status updates / reference decks / catalogs / meeting packs / FAQs that inform without arguing. The five now partition presentation *intent* more nearly MECE: persuade (pyramid) · tell a story (narrative) · teach (instructional) · impress (showcase) · simply inform (briefing). `_index` gains a `briefing` vs `pyramid` tie-breaker ("if you'd have to invent a thesis to fit pyramid, it's briefing"). Five presets plus a `custom` escape hatch for a bespoke direction none of them captures (a special cadence, a multi-mode fusion, a particular posture) — either user-requested or Strategist-recommended, confirmed like every lock; a deck always locks one value, and a fusion is one `custom` describing the acts. The only thing to avoid is defaulting to `custom` when a preset genuinely fits. Mirrors the truth-precedence rule that a user-authored outline or direction overrides the mode
+- **mode / visual-style system validated on real decks + four calibration tightenings landed** — the 5 modes + 18 visual-styles + the `custom` escape hatch were exercised on five covering decks (briefing×data-journalism / narrative×photo-editorial / instructional×chalkboard / showcase×glassmorphism / custom×zine, with the narrative deck going through the AI-image branch): **zero selection misses** (all four Close-calls tie-breakers fired and held against the real grey-zone pulls), **discipline fully honored** (zero HEX / Reference strength / whole-page layout language), **the `custom` mechanism works** (a `mode_behavior` prose paragraph carried a 10-page generation and reads as plain language at confirmation, not a bare token), **mode ⟂ visual_style holds** (any combination without bleed, including a positive check of the "keynote/launch = mode not style" route), export 5/5 decks × every page with 0 failures. Tightened four spots from the real signal: `strategist §e` now locks the full neutral tier set the visual_style implies up front (killing the mid-deck color top-ups seen in three consecutive decks), `executor-base §1` re-skins chart/layout template gradients-shadows-fills to the deck's visual_style (templates supply structure, not skin; mirror templates stay verbatim per §1.1), `briefing §1` makes `core_message` state coverage rather than a claim (briefing-only; global §IX assertion semantics stay for narrative/instructional/pyramid), and `svg_quality_checker` fixes font-family drift false positives (delimiter-matched capture + stack normalization) and drops the font-size ceiling for showcase mode and poster visual-styles
---
@@ -57,8 +59,7 @@ The past two months' structural capability growth. Single flags / incremental po
Directions actively underway or up next, with no committed timeline.
-- **Validate and calibrate the new mode / visual-style system on real decks** — the 5 modes + 18 visual-styles + the `custom` escape hatch are all still design-stage, unproven at this scale on real decks. The next step is not more presets but running real decks across the new modes / styles / custom and tightening from real signal: where the Strategist mis-selects a mode or style, where the Executor doesn't honor a style's discipline, whether a `custom` lock reads clearly at confirmation. Then adjust the auto-selection tables and the per-file wording accordingly
-- **mode catalog — settled** — the structure (5 + custom) is locked and the close-call tie-breakers are consolidated into one table covering the four genuinely-adjacent pairs (`pyramid↔briefing`, `narrative↔pyramid`, `narrative↔showcase`, `instructional↔briefing`); the rest are far enough apart to need none. All that remains is wording refinement to the mode files as real decks exercise them — which rides on the validation pass above, not a separate workstream
+- No committed next capability right now. The mode / visual-style validation and calibration is settled (see "2026-06" above): the structure (5 modes + 18 visual-styles + custom) is locked, the four adjacent pairs are consolidated into one Close-calls table, and the four calibration tightenings have landed. Future direction is driven by real usage signal and feedback; long-running improvements are under "Ongoing maintenance" below, and evaluated-out directions under "Non-goals"
---
@@ -82,6 +83,8 @@ PPT Master's main route is "AI generates SVG from scratch → DrawingML", with t
**The basic need is actually simple**: if you just need "replace Excel data into fixed positions in a PPT template", have the AI write a few lines of `python-pptx`. You don't need this pipeline.
+> **vs. the `template-fill-pptx` route**: "reuse a deck's *own* design and refill it with new content" is a supported capability (see "2026-06" above), with natively-editable output. What's out of scope here is the other shape — parsing an **arbitrary third-party** template's master / theme / placeholder system to do text-only substitution. Different investment points; don't conflate them.
+
### Switch to native PowerPoint charts (Excel-native chart)
**Issues**: [#99](https://github.com/hugohe3/ppt-master/issues/99), [#100](https://github.com/hugohe3/ppt-master/issues/100)-class
diff --git a/docs/zh/roadmap.md b/docs/zh/roadmap.md
index d6fd11bf..e53c5335 100644
--- a/docs/zh/roadmap.md
+++ b/docs/zh/roadmap.md
@@ -46,10 +46,12 @@
### 2026-06(讲解 mode 与视觉风格双 catalog 化)
+- **任意 PPTX 复刻设计 → 内容回填路线**([`workflows/template-fill-pptx.md`](../../skills/ppt-master/workflows/template-fill-pptx.md)) — 用户给一份现成 `.pptx` 加新材料 / 主题、要求「复用这套 deck 的设计 / 把内容填回去」时,走这条独立工作流直接编辑 PPTX,不进 SVG 生成管线。输出仍是原生可编辑 PPTX(复用原 slide 的形状 / 版式而非截图回填),过程做私有部件隔离、暴露图表数据、容量校验;触发同模板规则——显式要求复用既有 deck 才进,刻意不做改版式 / 加页 / 换图(那是从零生成主路线的活)。与下文 Non-goals 的 #53 区分见该节
- **三个 executor 退役 → mode + visual-style 双 catalog**([`references/modes/`](../../skills/ppt-master/references/modes/) + [`references/visual-styles/`](../../skills/ppt-master/references/visual-styles/)) — 原三个 `executor-*.md`(general / consultant / consultant-top)把「领域 · 受众 · 说服 · 叙事」捆在一条线;拆成两个正交 catalog(照 `image-renderings` 范式:扁平目录 + `_index` + 按需读 + Strategist 锁一个)。**mode** = 讲解骨架(`pyramid` / `narrative` / `instructional` / `showcase`,consultant + top 因叙事内核相同合并为 pyramid);**visual-style** = SVG 排版美学(`swiss-minimal` / `editorial` / `soft-rounded` / `dark-tech`,各 paired 一个 image-rendering,**零 HEX**——颜色真值守在 confirmation e + image-palettes)。Strategist `§d` 双层独立锁定 `mode` + `visual_style` 进 `spec_lock`,Executor 加载两个 locked 文件;任意 mode × 任意 style 自由组合,渲染坐标仍留 `templates/charts/`
- **提示词约束强度三档解耦**([`docs/rules/prompt-style.md`](../rules/prompt-style.md) §4) — 规则(`Hard rule` / `Forbidden`)/ 默认(`Default — … may override`)/ 参考(`Reference — not a constraint`)三档显式化 + 「客观失败 vs 品味」判据 + checker 边界,让模型对「该守 vs 可破」一目了然;visual-style catalog 全程用 Reference 强度
- **visual-style catalog 扩充至 18 个,与 image-renderings 对齐 + 示例库回收** — 先从[示例库](../../examples/)提炼 4 个(`brutalist` / `blueprint` / `memphis` / `zine`),再补齐 [`image-renderings`](../../skills/ppt-master/references/image-renderings/) 里有排版对应物的手绘 / 纹理风格 6 个(`sketch-notes` / `ink-notes` / `chalkboard` / `paper-cut` / `vintage-poster` / `pixel-art`),再回收示例库里仍未覆盖的独立气质:`ink-wash`(新中式水墨留白,源 藏拙 / 李子柒)· `glassmorphism`(深底磨砂玻璃 + 流光,源 glassmorphism_demo,从 soft-rounded 独立)· `photo-editorial`(满版摄影主导、文字点题,源 Pritzker / fashion_weekly)· `data-journalism`(Bloomberg/Economist 新闻信息图,多栏微图表 + 数据侧栏,源 global_ai_capital)。catalog 重组为 5 组(企业产品 / 编辑出版 / 表现印刷 / 手绘笔触 / 特殊)。**关键判据**:一个 rendering 升 visual-style 的前提是它定义「整页版面语言」而非「插入图的样子」——故 corporate-photo「摄影主导版面」该建(photo-editorial),而 nature / warm-scene / fantasy-animation 等纯氛围 rendering 仍只配对、不单建。全程零 HEX、Reference 强度
- **mode catalog 扩档至 5 个:加 `briefing`** — 补上「中性信息平铺」这一格:无论点 / 无故事 / 不教学 / 不冲击,topic 标题、等权铺事实、完整可扫读,服务周报 / 参考册 / 目录 / 会议材料 / FAQ 这类「只告知不论证」的 deck。五个 mode 自此更接近 MECE 地切分**表达意图**:说服(pyramid)· 讲故事(narrative)· 教会(instructional)· 震住(showcase)· 只告知(briefing)。`_index` 加了 `briefing` vs `pyramid` 的灰区判据(「要不要造个 thesis 才塞得进 pyramid → 那就是 briefing」)。五个预设之外加一个 `custom` 兜底,承接预设盖不住的 bespoke 方向(特殊节奏 / 多 mode 融合 / 特定姿态)——用户点名**或策略师推荐**皆可,与所有锁一样由用户确认;一份 deck 永远只锁一个值,融合=一个 custom 描述多幕。唯一要避免的是「预设明明贴合却图省事甩 custom」。这与「用户自带大纲 / 方向覆盖 mode」是同一条真值优先原则
+- **mode / visual-style 体系真实 deck 验证完成 + 四项校准收紧落地** — 5 mode + 18 visual-style + `custom` 逃生舱在 5 份覆盖性 deck 上跑过验证(briefing×data-journalism / narrative×photo-editorial / instructional×chalkboard / showcase×glassmorphism / custom×zine,其中 narrative 一份走 AI 图生成分支):**选型零误判**(四对 Close-calls 灰区引力全被触发且全抗住)、**纪律全落实**(零 HEX / Reference 强度 / 整页版面语言)、**custom 机制可用**(`mode_behavior` 散文段落撑过 10 页生成、能讲成大白话让用户确认)、**mode ⟂ visual_style 正交成立**(任意组合无串味,含「keynote/发布会=mode 不是 style」路由正面验证)、导出 5/5 deck × 全页 0 失败。据真实信号收紧四处:`strategist §e` 按 visual_style 预判中性档位一次锁全(消除连续三份的 Executor 中途补色)、`executor-base §1` 套模板页重皮到当前 visual_style(模板供结构不供皮,镜像模板仍按 §1.1 逐字保留)、`briefing §1` 的 `core_message` = 本页覆盖什么而非证明什么(briefing 专属例外,全局 §IX 论断语义保留给 narrative/instructional/pyramid)、`svg_quality_checker` 修字体 drift 误报(按定界符匹配 + font-stack 归一化)+ 放宽 showcase mode 与 poster 类 visual-style 的字号上限
---
@@ -57,8 +59,7 @@
明确在做或下一步要做的方向,不承诺时间窗口。
-- **用真实 deck 验证并校准 mode / visual-style 新体系** — 5 个 mode + 18 个 visual-style + `custom` 逃生舱目前都还是设计态,没在真实 deck 上按这个规模跑过验证。下一步不是再加预设,而是跑几份覆盖新 mode / visual-style / custom 的真实 deck,从真实信号反过来收紧:Strategist 在哪选错了 mode 或 style、Executor 有没有落实某个 style 的纪律、custom 锁定在确认环节读起来清不清楚;据此调整 auto-selection 表与各文件措辞
-- **mode catalog 已收口** — 结构(5 个 + custom)定型,近邻消歧判据补齐成一张 Close-calls 表(`pyramid↔briefing`、`narrative↔pyramid`、`narrative↔showcase`、`instructional↔briefing` 四对真正会混的对,其余 far-apart 不需要)。residual 只剩各 mode 文件随真实 deck 落实情况的措辞精修,并入上面的验证 pass,不再单独占工
+- 暂无已承诺的下一步能力方向。mode / visual-style 体系的验证与校准已收口(见上「2026-06」),结构(5 mode + 18 visual-style + custom)定型、四对近邻消歧并成一张 Close-calls 表、四项校准收紧已落地。后续方向由真实使用信号与反馈驱动;长期改进见下「持续维护方向」,已评估不做的见「明确不做」
---
@@ -82,6 +83,8 @@ PPT Master 主路线是「AI 从零生成 SVG → DrawingML」,整条管线围
**基础诉求其实很简单**:如果只是「固定位置替换 Excel 数据到 PPT 模板」,直接让 AI 写一段 `python-pptx` 脚本即可,几行代码搞定,不需要本项目这套管线。
+> **与 `template-fill-pptx` 路线的区别**:「复用某份 deck **自己的**设计、把新内容回填进去」是已支持的能力(见上「2026-06」),输出仍原生可编辑。这里拒的是另一种形态——解析**任意第三方**模板的母版 / 主题 / 占位符体系并仅做文字替换;两者发力点不同,别混为一谈。
+
### 改用原生 PowerPoint 图表(Excel-native chart)
**对应 Issue**:[#99](https://github.com/hugohe3/ppt-master/issues/99)、[#100](https://github.com/hugohe3/ppt-master/issues/100) 类