Slides Grab

OrganizationPopular

NomaDamas

slides-grab

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.

Overview

Publisher	NomaDamas
Repository	`slides-grab`
Skill name	`slides-grab`
Stars	1.2K
Forks	135
Bundled files	1
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by NomaDamas on GitHub. Read the source before you install it.

Installation

Install the Slides Grab AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/NomaDamas/slides-grab.git /tmp/slides-grab
mkdir -p .claude/skills
cp -r /tmp/slides-grab/skills/slides-grab .claude/skills/slides-grab

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Slides Grab in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Slides Grab on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Slides Grab is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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, read the matching sub-skill in full and follow its pipeline. Do not mix instructions from the two sub-skills — the image generation steps are different and must not be combined.

Shared stages (both pipelines)

Stage 1 — Plan

Use the installed slides-grab-plan skill. The plan stage records the chosen mode: html or mode: image-native in slide-outline.md meta so Stage 2 knows which pipeline to run. Do not proceed to Stage 2 without approval of both style and outline.

Stage 3 — Export

Use the installed slides-grab-export skill. Export is gated on a Stage 2 design-gate Proceed verdict. PPTX and Figma are experimental / unstable.

Confirm user wants conversion.
Pick the primary target:
- Card-news / Instagram-style decks → slides-grab png --slides-dir <path> --slide-mode card-news --resolution 2160p (see slides-grab-card-news).
- Widescreen decks → slides-grab pdf --slides-dir <path> --output <name>.pdf.
Per-slide PNG (any mode): slides-grab png --slides-dir <path> --output-dir <path>/out-png --resolution 2160p.
PPTX (optional, experimental / unstable): use slides-grab convert --slides-dir <path> --output <name>.pptx --engine raster for visual fidelity (default), or --engine text for best-effort editable text.
Figma-importable PPTX (optional, experimental / unstable): slides-grab figma --slides-dir <path> --output <name>-figma.pptx.
Report results.

Shared rules (apply to both pipelines)

Always follow the stage order: Plan → Design → Export.
Get explicit user approval before advancing to the next stage.
Pass the design gate before export: Stage 2 must end with a Proceed verdict (zero unresolved Critical findings) on the latest rendered state. slides-grab pdf, slides-grab convert, and slides-grab figma block if the receipt is missing, stale, or fails the CLI-enforced report contract.
Use decks/<deck-name>/ as the slides workspace for multi-deck projects.
Call out export risk clearly: PPTX and Figma export are experimental / unstable.
For complex diagrams, default to a tldraw-generated asset unless the user explicitly asks for a different approach.
When a slide needs bespoke imagery inside an HTML deck, prefer the default codex-imagen provider via slides-grab image (reuses local Codex ChatGPT login — no API key required; run codex login once) and keep the saved asset local under <slides-dir>/assets/. Image-native decks generate each whole-slide raster with slides-grab image --image-native --name slide-XX so the wrapper and editor metadata are created together — see the image sub-skill.
When a slide needs a chart, default to Chart.js in-slide canvas rendering and require slides-grab validate plus slides-grab build-viewer review so blank canvases are caught as empty-canvas before export. Local videos live under <slides-dir>/assets/ with poster="./assets/<file>" thumbnails; use slides-grab fetch-video or yt-dlp to pull supported web videos first.
Use slides-grab list-styles and slides-grab preview-styles for bundled style discovery during planning.

Reference

references/presentation-workflow-reference.md — archived end-to-end workflow guidance from the legacy skill set
../slides-grab-html/SKILL.md — HTML-mode pipeline (semantic slides)
../slides-grab-image/SKILL.md — image-native pipeline (raster wrapper slides)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

references/presentation-workflow-reference.md5 KB

Frequently asked questions

What does the Slides Grab AI skill do?

Why use Slides Grab on TypingMind?

Because you install it once and use it with any model. Slides Grab is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Slides Grab in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/NomaDamas/slides-grab/tree/main/skills/slides-grab. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Slides Grab?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Slides Grab?

As many as you like. As long as a model supports skills, you can use Slides Grab with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Slides Grab AI skill free?

Yes. It is published on GitHub by NomaDamas under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Improve Codebase Architecture

mattpocock

CommunityPopular

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Grilling

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Teach

Teach the user a new skill or concept, within this workspace.

Api Design

Patrones de diseño REST API incluyendo nomenclatura de recursos, códigos de estado, paginación, filtrado, respuestas de error, versionado y rate limiting para APIs de producción.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

slides-grab Skill - Mode Router

Pick a delivery mode

Shared stages (both pipelines)

Stage 1 — Plan

Stage 3 — Export

Shared rules (apply to both pipelines)

Reference

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now