Slides Extract logo

Slides Extract

Organization
studio-yebisu
slides-extract

Extract template contracts from a .pptx file. Produces layout catalogs, archetypes, resolved manifest, and a clean base template for slides-build. Use when the user provides a PowerPoint template, says "use this template", "extract layouts", "analyze this pptx", or wants to prepare a template before building slides.

Overview

Publisherstudio-yebisu
Repositoryyaoyorozu-ai-toolbox-slides
Skill nameslides-extract
Stars
10
Forks
2
Bundled files
Instructions only
Links
  • 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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by studio-yebisu on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/studio-yebisu/yaoyorozu-ai-toolbox-slides/tree/main/examples/repositories/agent-slides-showcase/upstream/slides-extract
  4. 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.
2

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/studio-yebisu/yaoyorozu-ai-toolbox-slides.git /tmp/yaoyorozu-ai-toolbox-slides
mkdir -p .claude/skills
cp -r /tmp/yaoyorozu-ai-toolbox-slides/examples/repositories/agent-slides-showcase/upstream/slides-extract .claude/skills/slides-extract
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Slides Extract 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 Extract 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 Extract 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 Extract

You are a template analyst. Your job is to extract structured contracts from PowerPoint templates so that downstream skills can generate pixel-perfect decks without guessing.

Extract template contracts from a .pptx template or sample deck.

When to Use

  • Before the first /slides-build for a given template
  • When the source template changes
  • When you need to analyze a template's layouts and capabilities

Prerequisites

  • A .pptx file (template or sample deck with example slides)

Process

Step 1) Create project directory

Create a dedicated directory for this project's artifacts:

bash
mkdir -p output/<project-name>

All subsequent commands and outputs go in this directory.

Step 2) Run extraction

Use uvx --from agent-slides slides docs method:extract to verify the current contract, then:

bash
uvx --from agent-slides slides extract <template_or_sample.pptx> \
  --output-dir output/<project> \
  --base-template-out output/<project>/base_template.pptx \
  --compact

Optional: add --layout-preview-dir output/<project>/layout_previews for per-layout PNGs (legacy override), or specific --*-out paths for one-off custom filenames.

Step 3) Verify outputs

ArtifactPurpose
template_layout.jsonPhysical layout families, placeholders, geometry
content_layout.jsonArchetype-to-layout compatibility map
archetypes.jsonAvailable archetypes with usage constraints
resolved_manifest.jsonMerged contract — theme palette, per-archetype resolved layout bindings. Primary reference for /slides-build.
slides_manifest.jsonSlide-by-slide inventory of the source
slide_analysis.jsonDeep per-slide structural analysis
slide_screenshots/Visual reference screenshots
icons/Vector icons extracted from template slides (freeform/group shapes). Available via add_icon when icon_pack_dir is set in design profile.
base_template.pptxClean .pptx — all masters/layouts/theme, zero content slides

Step 4) Comprehension gate

Read resolved_manifest.json and verify you can answer these questions before proceeding:

  • What accent colors does the theme use? List the hex values. (Path: theme.palette.accent1 … accent6)
  • How many archetypes have resolved_layouts? Name them. (Note: archetypes is a dict keyed by archetype ID, not a list — iterate with for aid, arch in archetypes.items())
  • Which layouts are split-panel (title in a side zone)?
  • What text_color does each color zone use?

If any answer is unclear, re-read the manifest. Do not proceed to the design profile until all four are answered.

Step 5) Build design profile

Write design-profile.json in the project directory:

json
{
  "name": "<project-name>",
  "template_path": "base_template.pptx",
  "content_layout_catalog_path": "content_layout.json"
}

Add these fields from the extracted theme:

FieldSourcePurpose
primary_color_hexTheme accent1Brand accent color for subheadings
text_color_lightTheme lt1Light text for dark backgrounds
text_color_darkTheme dk1Dark text for light backgrounds
default_font_size_ptTemplate body sizeDefault for add_text
icon_pack_diricons/ (if extracted)Directory of template-specific vector icons for add_icon

Always use base_template.pptx (not the original) as template_path.

If the extraction produced an icons/ directory with .xml files, add "icon_pack_dir": "icons" to the design profile. These icons become available via add_icon alongside the built-in icon library.

Only add fields listed above or in the schema. The profile uses extra="forbid" — any unknown field (e.g., secondary_color_hex, accent_color_hex, font_name) causes a validation error.

Use uvx --from agent-slides slides docs schema:design-profile for the full schema.

Step 6) Preflight the project

Before handing the project off to /slides-build or /slides-full, verify the extracted artifacts and profile:

bash
uvx --from agent-slides slides preflight --project-dir output/<project> --profile output/<project>/design-profile.json --compact

If preflight fails, fix the project structure or profile paths before continuing.

Outputs

This skill produces the project directory consumed by all other slides skills:

  • base_template.pptx + contract JSONs -> /slides-build
  • design-profile.json -> all post-build skills

Error Handling

On any slides error, run uvx --from agent-slides slides docs method:extract to verify the current contract before retrying.

Acceptance Criteria

  1. All artifact files exist and are valid JSON (where applicable).
  2. resolved_manifest.json contains at least one archetype with resolved layouts.
  3. base_template.pptx opens without errors.
  4. design-profile.json references base_template.pptx and content_layout.json.
  5. slides preflight reports "ok": true.
  6. Comprehension gate questions answered correctly.

Frequently asked questions

What does the Slides Extract AI skill do?

Extract template contracts from a .pptx file. Produces layout catalogs, archetypes, resolved manifest, and a clean base template for slides-build. Use when the user provides a PowerPoint template, says "use this template", "extract layouts", "analyze this pptx", or wants to prepare a template before building slides.

Why use Slides Extract on TypingMind?

Because you install it once and use it with any model. Slides Extract 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 Extract in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/studio-yebisu/yaoyorozu-ai-toolbox-slides/tree/main/examples/repositories/agent-slides-showcase/upstream/slides-extract. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Slides Extract?

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 Extract?

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

Is the Slides Extract AI skill free?

It is published on GitHub by studio-yebisu. Check the repository for licensing terms. 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇