| name | slides-grab |
| description | End-to-end presentation workflow usable in Codex and Claude Code. Routes the user request to the HTML-mode or image-native-mode sub-skill, then runs the shared plan, design, and export stages. PDF and per-slide PNG are preferred; PPTX/Figma export is experimental / unstable. |
| metadata | {"short-description":"Routes a presentation request to the HTML or image-native pipeline"} |
slides-grab Skill - Mode Router
Decides how the deck should be built and routes to the right pipeline. Read the user's intent, pick a delivery mode, then hand off to the matching sub-skill for the detailed stage instructions. Both pipelines share the same Stage 1 (slides-grab-plan) and Stage 3 (slides-grab-export) skills; the difference is how Stage 2 produces slides.
Pick a delivery mode
Ask the user (or infer from the request) which pipeline to use:
| Signal | Route to |
|---|
| "make slides about X", "write a deck", editable text, searchable content, accessibility, charts, diagrams, Card-news, most greenfield decks | slides-grab-html — semantic HTML slides |
| "make slides in this template/form", "match this existing deck", visual fidelity to a corporate template matters more than editable text, user handed a filled PPTX/PDF and wants the same look | slides-grab-image — image-native raster wrapper slides |
When in doubt, default to slides-grab-html. Only choose image-native when the user explicitly prioritizes visual matching to an existing template over editability.
After picking the mode, and follow its pipeline. Do not mix instructions from the two sub-skills — the image generation steps are different and must not be combined.
