Agent skill · Code Review & Quality

ppt-speech-writer

Read a real .pptx using text extraction, OOXML inspection, slide rendering, OCR, visual inventory, and vision-capable screenshot review; then write academic speaker notes grounded in every visible slide element, generate a complete display-version document, and inject clean notes into the PowerPoint notes pane. Use when the user wants speaker notes, presenter notes, a speech script, narration, or annotated notes for an existing PowerPoint deck, especially when slides contain images, charts, tables, SmartArt, axes, legends, or screenshot text.

AI272github.com/AI272GitHub ↗
claude-codecodexships scripts
Install
npx skills add AI272/speaker --skill ppt-speech-writer --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 8
SKILL.md size: 21 KB
Bundled scripts: yes
Path: ppt-speech-writer/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 408
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# PPT Speech Writer You are a senior academic presentation coach. This skill writes slide-by-slide speaker notes for an existing `.pptx`, grounded in the actual visible deck. It must inspect both the structured PowerPoint content and rendered slide images before drafting. ## Grounding Contract Do not rely on text boxes alone. A slide is considered read only after these evidence sources have been checked: 1. Structured extraction from PowerPoint objects: text frames, tables, chart XML, pictures, placeholders, notes, and raw OOXML text. 2. Rendered slide screenshots, one image per slide. 3. OCR or visual inspection of rendered slides when screenshots, charts, diagrams, SmartArt, or image-contained text are present. 4. A visible-element inventory for every slide. 5. Vision-capable review of rendered screenshots for every slide with charts, diagrams, SmartArt, screenshots, dense figures, or image-only content. If a visible element cannot be interpreted reliably, say so and ask the user before writing notes for that slide. Never invent chart values, axes, labels, image meaning, or screenshot text. ## Language Lock Do not infer the output language from the user's chat language. Before wr

What's inside
Steps it walks through
  1. Grounding Contract
  2. Language Lock
  3. Slide Prose Style
  4. Timing And Pacing Model
  5. Planning rates (pauses already absorbed)
  6. Reserve time before budgeting words
  7. Per-slide budget
  8. Writing to the budget in both languages
  9. Required Workflow
  10. 1. Create Output Layout
  11. 2. Extract Structured Slide Content
  12. 3. Render Slides
  13. 4. Build The Visual Inventory
  14. 5. Run Vision Review
Ships with 7 files
  • LOGIC.md
  • scripts/inject_notes.py
  • scripts/read_slides.py
  • scripts/render_slides.py
  • scripts/vision_review.py
  • scripts/visual_inventory.py
  • scripts/write_display_docx.py
Commands it runs
python scripts/read_slides.py "/path/to/deck.pptx" \
python scripts/render_slides.py "/path/to/deck.pptx" \
python scripts/visual_inventory.py \
python scripts/vision_review.py \
python scripts/write_display_docx.py \
python scripts/inject_notes.py \
About this skill
What does the ppt-speech-writer skill do?

Read a real .pptx using text extraction, OOXML inspection, slide rendering, OCR, visual inventory, and vision-capable screenshot review; then write academic speaker notes grounded in every visible slide element, generate a complete display-version document, and inject clean notes into the PowerPoint notes pane. Use when the user wants speaker notes, presenter notes, a speech script, narration, or annotated notes for an existing PowerPoint deck, especially when slides contain images, charts, tables, SmartArt, axes, legends, or screenshot text.

How do I install it?

Run `npx skills add AI272/speaker --skill ppt-speech-writer --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From AI272/speaker, a repository with 408 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going