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(beautify): judge identity alternatives like the from-scratch flow

hugohe308ecba433d6e
diff --git a/skills/ppt-master/references/strategist.md b/skills/ppt-master/references/strategist.md
index 132a4e47..fa788576 100644
--- a/skills/ppt-master/references/strategist.md
+++ b/skills/ppt-master/references/strategist.md
@@ -56,7 +56,7 @@ The deck's **narrative + persuasion skeleton** — how the argument is organized
**Source**:
- User supplied their own outline / structure → it is authoritative. Transcribe it into `§IX` as given (page order + titles preserved); still lock a mode, but for register / voice and page-internal treatment, **not** to reshape — never reorder the user's pages or rewrite their given titles. Note in `design_spec.md` that the structure is user-authored. `briefing` imposes the least if no particular "讲法" is intended.
-- Beautify / re-layout workflow ([`beautify-pptx.md`](../workflows/beautify-pptx.md)) → the extracted source content is authoritative and **verbatim**, one step stricter than the user-outline case above. Each source slide becomes exactly one `§IX` page in source order; transcribe every content block word-for-word — never reshape / re-primary / condense / merge / split / reword. Lock `mode: briefing`; color (e) and typography (g) are the source identity the user confirmed in the beautify plan (theme or observed usage), locked as truth (skip both recommendation flows). Charts / tables / images are regenerated from their extracted data in the inherited style (route chart/table data to §VII, pictures to §VIII) — data values stay frozen, the rendering is the deck's own; never carried over verbatim. Layout, hierarchy, rhythm, and visual rendering are what gets redesigned.
+- Beautify / re-layout workflow ([`beautify-pptx.md`](../workflows/beautify-pptx.md)) → the extracted source content is authoritative and **verbatim**, one step stricter than the user-outline case above. Each source slide becomes exactly one `§IX` page in source order; transcribe every content block word-for-word — never reshape / re-primary / condense / merge / split / reword. Lock `mode: briefing`; color (e) and typography (g) are whatever the user confirmed in the beautify plan — the source identity (theme or observed) by default, or a content / brand-aware alternative the beautify plan offered and the user picked — locked as truth (the beautify plan already ran the recommendation through the confirm UI, so do not re-recommend here). Charts / tables / images are regenerated from their extracted data in the inherited style (route chart/table data to §VII, pictures to §VIII) — data values stay frozen, the rendering is the deck's own; never carried over verbatim. Layout, hierarchy, rhythm, and visual rendering are what gets redesigned.
- A bespoke direction the five don't give — a nameable cadence (dialectic 正反合, myth-vs-reality, countdown, Socratic), a multi-act fusion of modes, or the user's own feel (confrontational here, detached there). Either the user asks, **or you recommend it** when a fusion / bespoke direction genuinely serves the deck better than a single preset (a recommendation the user confirms, like every lock). The *kind* doesn't matter → `mode: custom` + a `mode_behavior:` paragraph that **crystallizes the intent** (act sequence or posture shifts, title voice, page rhythm, register) concretely enough for the Executor to follow per page; it reads only `spec_lock.md`, never the chat. One deck locks **one** value — a fusion is one `custom` describing the acts, never several modes. Avoid only the *dodge*: don't default to `custom` when a preset genuinely fits, and prefer a dominant mode + page-level variation when one mode leads.
- No user structure or cadence → recommend by the index's auto-selection table (content / audience signal → mode) plus the deck's stated purpose; the mode does the structural lifting. Present as a recommendation; the user may override.
diff --git a/skills/ppt-master/workflows/beautify-pptx.md b/skills/ppt-master/workflows/beautify-pptx.md
index 964e02cc..4e4ea132 100644
--- a/skills/ppt-master/workflows/beautify-pptx.md
+++ b/skills/ppt-master/workflows/beautify-pptx.md
@@ -188,7 +188,8 @@ Write `<project_path>/confirm_ui/recommendations.json` and launch the same confi
```
- **Recommend keep, allow override**: pre-fill canvas / mode / visual style / icons / image strategy with the source-faithful default (canvas = Step 3 format, mode = `briefing`, image_usage = `provided` since pictures are reused). Enumerable fields already list every catalog option with the source-faithful one badged, so the user can switch. Beautify's only true non-choices are the frozen text and the strict 1:1 page count (changing those means routing to the main pipeline instead — see CLAUDE.md).
-- **Always offer real choices, default to the source replica**: for color and typography, author **several candidates** like the from-scratch flow — but the pre-selected default (`selected: 0`, the first card) is the one that **best replicates the source deck's style** (the truest reading of `theme` / `observed`). Include the other source reading as a second candidate when `theme` and `observed` differ, plus **enough fresh alternatives to reach ≥3 candidates total** (the same creative-choice rule used elsewhere) so a user who does *not* want to keep the old look can switch in one click. Replicate-by-default, depart-by-choice.
+- **Our recommendation is the pre-selected default = the source replica**: for color and typography, author **several candidates** like the from-scratch flow. The pre-selected default (`selected: 0`, the first card) is what beautify recommends — the candidate that **best replicates the source deck's style** (the truest reading of `theme` / `observed`). Replicate-by-default.
+- **Judge the other alternatives exactly as the from-scratch flow does — fonts as much as colors**: don't invent a beautify-specific rule. Author each non-replica candidate with the **same content-driven judgment the Strategist uses when generating from scratch** (color §e, typography §g), applied to the material this project provides — the source document's content and subject, the company's own theme colors, and any brand signal. Pick the palette **and** the font pairing by what fits *this* deck's content; fonts are chosen by content fit, not just defaulted to a safe face. Reach **≥3 candidates total** (PPT-safe stacks; the same creative-choice rule used elsewhere) so a user who departs from the replica still lands on a considered, content-fitting direction — depart-by-choice.
- **`body_size` is the load-bearing field**: seed it from a canvas-appropriate baseline (the page hints ≈2.5–3.3% of canvas height) — for a presentation / projection deck lean toward the relaxed end (e.g. `24` → 18pt), for a dense document deck the compact end (e.g. `18` → 13.5pt). The user sets the final value here; this is what prevents the deck from exporting at an unintentionally small size.
```bash