Automated summary
This skill scaffolds, structures, and deploys a Docusaurus site for a Physical AI textbook, with book-aware content and RAG-ready exports.
Strengths
- Modular hierarchical structure tailored for course content
- Local search and Algolia DocSearch integration
- RAG-ready exports via frontmatter and semantic headings
- Automated CI/CD for GitHub Pages or Vercel deployment
Limitations
- Requires Node.js and basic Docusaurus knowledge
- Custom MDX components must be developed separately
- DocSearch setup requires an external Algolia key
Use this skill when you need to create a documentation site for a structured technical textbook with modules, weeks, and chapters, and want easy ingestion into RAG systems.
Do not use it for a simple landing page or blog without a deep hierarchy, or if you need an online CMS with live editing capabilities.
Security analysis
SafeThe skill instructs setting up a Docusaurus documentation site using standard tools (npx, npm) and writing content. There are no destructive commands, no exfiltration, and no obfuscation. All actions are typical of project scaffolding and deployment.
No concerns found
How this analysis is madeExamples
Set up a Docusaurus site for my Physical AI textbook with modules 1-4, a capstone, and a quarter overview. Configure sidebar, add MDX components for callouts and hardware tables, enable search, and set up GitHub Actions deployment to GitHub Pages.Create a new chapter for module 2 week 3 on sensor fusion. Write an MDX file with frontmatter including title, description, module=2, week=3, and tags. Follow the semantic heading structure (h2 for weeks, h3 for sections).List all markdown files under docs/ excluding build/ and static/. Output a glob pattern to feed into a RAG ingestion pipeline. Ensure each file has frontmatter fields title, description, module, week, tags.name: book-docusaurus description: Scaffold, structure, and deploy the Physical AI textbook in Docusaurus with book-aware content and RAG-ready exports. Use when creating or updating the Docusaurus site, adding chapters, configuring sidebar, or deploying to GitHub Pages/Vercel.
Book Docusaurus Skill
Instructions
-
Scaffold the site
- Ensure Node >=18 is installed
- Run
npx create-docusaurus@latest physical-ai-book classicin project root or/docs - Configure
docusaurus.config.jswith site metadata, GitHub Pages URLs, i18n (en default)
-
Structure content
- Build
sidebars.jsfor Quarter overview, Modules 1-4, Capstone, Assessments, Hardware kits, Cloud option - Create MDX stubs per module/week with learning outcomes and tasks
- Add capstone outline
- Build
-
Authoring affordances
- Add MDX components for callouts, checklists, hardware tables, code blocks
- Enable search (Algolia DocSearch placeholder) and local search plugin for dev
-
Deploy
- Add GitHub Actions workflow for GH Pages (
npm ci,npm run build,npm run deploy) - Document Vercel deploy steps (import repo, build command
npm run build, outputbuild)
- Add GitHub Actions workflow for GH Pages (
-
RAG-readiness
- Enforce frontmatter fields:
title,description,module,week,tags - Keep headings semantic (h2 for weeks, h3 for sections)
- Avoid heavy client-side rendering for core text
- Export ingestion guidance: markdown path glob, ignore build/static
- Enforce frontmatter fields:
Examples
# Create new chapter
mkdir -p docs/module-1/week-1
cat > docs/module-1/week-1/intro.mdx << 'EOF'
---
title: Introduction to Physical AI
description: Overview of embodied intelligence and humanoid robotics
module: 1
week: 1
tags: [physical-ai, robotics, introduction]
---
# Introduction to Physical AI
Content here...
EOF
# Build and test locally
npm run build
npm run serve
Definition of Done
npm run buildpasses; site renders outline and sample content- Sidebar matches course hierarchy; links valid
- GH Pages workflow present; deploy instructions written
- Content annotated with frontmatter and semantic headings suitable for chunking
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/book-docusaurus-mmlj2otu/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/book-docusaurus-mmlj2otu' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/book-docusaurus-mmlj2otu/download' --output '.skill-downloads/book-docusaurus-mmlj2otu/SKILL.md.part' && mv '.skill-downloads/book-docusaurus-mmlj2otu/SKILL.md.part' '.skill-downloads/book-docusaurus-mmlj2otu/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/book-docusaurus-mmlj2otu/SKILL.md' && test -s '.skill-downloads/book-docusaurus-mmlj2otu/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/book-docusaurus' && cp -R '.skill-downloads/book-docusaurus-mmlj2otu' '.claude/skills/book-docusaurus'Cursor
test -f '.skill-downloads/book-docusaurus-mmlj2otu/SKILL.md' && test -s '.skill-downloads/book-docusaurus-mmlj2otu/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/book-docusaurus' && cp -R '.skill-downloads/book-docusaurus-mmlj2otu' '.cursor/skills/book-docusaurus'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/book-docusaurus-mmlj2otu'openskills read 'book-docusaurus-mmlj2otu'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/book-docusaurus-mmlj2otu/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.