docusaurus-v2-to-v3-migration
Use when migrating Docusaurus projects from v2 to v3
Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security
Installation for Agentic Skill
View all platforms →skilz install mcclowes/lea/docusaurus-v2-to-v3-migrationskilz install mcclowes/lea/docusaurus-v2-to-v3-migration --agent opencodeskilz install mcclowes/lea/docusaurus-v2-to-v3-migration --agent codexskilz install mcclowes/lea/docusaurus-v2-to-v3-migration --agent geminiFirst time? Install Skilz: pip install skilz
Works with 22+ AI coding assistants
Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...
Extract and copy to ~/.claude/skills/ then restart Claude Desktop
git clone https://github.com/mcclowes/leacp -r lea/.claude/skills/docusaurus-migration ~/.claude/skills/Need detailed installation help? Check our platform-specific guides:
Related Agentic Skills
tailwind-shadcn-setup
by vanman2024
Setup Tailwind CSS and shadcn/ui component library for Next.js projects. Use when configuring Tailwind CSS, installing shadcn/ui, setting up design...
spanish-language-tutor
by sandraschi
Comprehensive Spanish language expert covering grammar, conversation, regional dialects, and language learning strategies
frontend-dev-guidelines
by diet103
Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organiz...
torch-geometric
by davila7
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, ...
Agentic Skill Details
- Repository
- lea
- Stars
- 3
- Type
- Non-Technical
- Meta-Domain
- development
- Primary Domain
- javascript
- Market Score
- 16
Agent Skill Grade
B Score: 85/100 Click to see breakdown
Score Breakdown
Areas to Improve
- Missing TOC in long reference file
- Second-person usage in reference
- Incomplete package.json template
Recommendations
- Add trigger phrases to description for discoverability
- Add table of contents for files over 100 lines
Graded: 2026-01-24
Developer Feedback
I've been looking at how teams handle Docusaurus migrations and your skill caught my eye—85/100 suggests you've nailed the core execution but there's probably some rough edges in the handoff or edge case handling I'd be curious about.
Links:
The TL;DR
You're at 85/100, solid B grade territory. This is based on Anthropic's skill best practices. Your strongest suit is Ease of Use (24/25)—that 5-step migration workflow with the pre-migration checklist is genuinely clean. The weakest link is Spec Compliance (11/15), mainly because your metadata's not quite matching the directory structure and you're light on discovery triggers.
What's Working Well
Progressive Disclosure is chef's kiss. Your 54-line SKILL.md stays focused while punting the heavy details (396 lines of breaking changes) to a reference file. That's exactly how this should work—users get oriented fast without drowning in v2→v3 minutiae.
The workflow is locked in. Five numbered steps, clear validation checkpoints (run mdx-checker → fix → test with npm start → build → deploy). That's the kind of concrete guidance that actually prevents migration disasters instead of just listing breaking changes.
Strong token economy. Quick Start shows actual deps, Pre-Migration Checklist is actionable, and you're not padding with fluff. The Troubleshooting section in breaking-changes.md has real gotchas (ESM imports, custom theme issues) not generic placeholder content.
The Big One: Add a Table of Contents
Your breaking-changes.md is 396 lines deep with solid structure, but it's missing a TOC. When someone's mid-migration and hitting a weird config issue, they shouldn't have to scroll through everything to find "Prism React Renderer Changes."
**Ad...
Browse Category
More development Agentic SkillsReport Security Issue
Found a security vulnerability in this agent skill?
Report Security Issue
Thank you for helping keep SkillzWave secure. We'll review your report and take appropriate action.
Note: For critical security issues that require immediate attention, please also email security@skillzwave.ai directly.