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: read a book-length source by heading index; Morph pairs on a structured page are Slide-local groups decided before P01; both notes heading forms named
hugohe3e1ab6661f9ad
diff --git a/skills/ppt-master/references/executor-notes.md b/skills/ppt-master/references/executor-notes.mdindex 400db2d7..b5370f4d 100644--- a/skills/ppt-master/references/executor-notes.md+++ b/skills/ppt-master/references/executor-notes.md@@ -8,7 +8,7 @@ Conditional late-stage authority for generating or validating the complete speak## 1. Complete Speaker-notes Document-Write the whole deck to `notes/total.md` in one batch: `# <number>_<page_title>` per page, `---` between pages; only the heading is stripped before TTS. `notes_to_audio.py` reads the body verbatim, so write prose only — no list/bullet markup, stage markers, key-point labels, duration lines, or other metadata. Keep one language unless the confirmed contract is bilingual — then every page keeps the same segment order (first language, blank line, second language); spell out digits or symbols when literal TTS would sound wrong (Chinese "百分之六十八" rather than "68%").+Write the whole deck to `notes/total.md` in one batch: `# <number>_<page_title>` per page (`# Slide <number>` only for a script written before the roster exists; the splitter takes both), `---` between pages; only the heading is stripped before TTS. `notes_to_audio.py` reads the body verbatim, so write prose only — no list/bullet markup, stage markers, key-point labels, duration lines, or other metadata. Keep one language unless the confirmed contract is bilingual — then every page keeps the same segment order (first language, blank line, second language); spell out digits or symbols when literal TTS would sound wrong (Chinese "百分之六十八" rather than "68%").**Pre-SVG narration branch**: when `notes/total.md` already exists from a final/literal script or Quick direct narrated video, validate it instead of regenerating. Retain every word and segment of a final/literal script; agent-authored Quick narration may be repaired only for final-SVG inconsistency and before audio. A `# Slide <number>` heading remains valid until Generate Step 7.1 resolves the roster.diff --git a/skills/ppt-master/references/pptx-structure-interface.md b/skills/ppt-master/references/pptx-structure-interface.mdindex f9ee03d4..37efc908 100644--- a/skills/ppt-master/references/pptx-structure-interface.md+++ b/skills/ppt-master/references/pptx-structure-interface.md@@ -64,6 +64,8 @@ Every new SVG project declares one deterministic route:**Slot bounds**: derive `data-pptx-bounds` from the intended design zone, column, panel inset, safe area, or picture frame — never from text length, glyph width, line count, or a tight content box. Repeat the same slot ids/types/effective indices/default bounds/binding modes on every slide using that Layout; Slide content and local carrier geometry may differ from the default frame. A template-owned chart/table carrier may declare `data-pptx-native-authority="json"`; its metadata, marker identity, bounds, and slot binding are structural facts while its preview children are derived.+**Morph endpoints**: a slot becomes a Layout placeholder at export and cannot pair; template prototypes supply only fixed layers and slots, so a Morph pair is a Slide-local group authored beside them, decided before P01.+**Text carriers**: a multiline placeholder stays one native text frame, so leave strict-line text Slide-local when separate frames are required. Leave a carrier empty or whitespace-only when the placeholder must be visually blank — export materializes an invisible run; never insert a dummy dash, sub-1pt text, or an opacity-hidden glyph. A materialized mirror carrier may keep the source `data-pptx-frame`; do not add it to an authored `standard` / `fidelity` carrier merely to duplicate its bounds. `object` is the generic content slot; `media` binds an authored image/crop and does not synthesize video or audio from a decorative group.## 3. Legacy Template Input Boundarydiff --git a/skills/ppt-master/workflows/profiles/quick-generate.md b/skills/ppt-master/workflows/profiles/quick-generate.mdindex 793fcf90..c570982d 100644--- a/skills/ppt-master/workflows/profiles/quick-generate.md+++ b/skills/ppt-master/workflows/profiles/quick-generate.md@@ -56,6 +56,8 @@ Artifact roles follow [`artifact-ownership.md`](../../references/artifact-owners| CSV / TSV | Read directly as a plain-text table || Markdown or conversation text | Read directly |+A book-length converted source is located by its heading index and searched phrases, then read only in the sections the deck draws on.+**Orientation review**: apply [`conversion.md`](../../scripts/docs/conversion.md) § Image Orientation Review before import when correction is requested, converted text asks for rotated viewing, or an asset is visibly sideways (skip the legacy HTML tool).**Research scope**: after reading every source, research only the gaps where the requested outcome would otherwise require inventing, omitting, or leaving unsupported an externally verifiable claim. An Image to PPTX surface is a closed corpus whose unreadable regions become `manual_required`; a closed/source-only brief stays within its material.