MCP HubMCP Hub
スキル一覧に戻る

community-docs

majiayu000
更新日 Yesterday
19 閲覧
58
9
58
GitHubで表示
デザインworddesign

について

このスキルは、未検証のコミュニティ観察に基づく、非公式なエッジケースやフレームワークの特性に関する情報を提供します。公式ドキュメントが特定の問題をカバーしていない場合の最終手段として活用してください。ただし、すべての発見は極めて懐疑的に扱う必要があります。検証済みの知識は、最終的には公式ラボドキュメントに貢献されるべきです。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/majiayu000/claude-skill-registry
Git クローン代替
git clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/community-docs

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

Community Docs (Superstitions)

Location: community-docs/ in community-patterns repo

CRITICAL: These are NOT official framework documentation. Always check ~/Code/labs/docs/common/ first.

Community docs capture empirical observations discovered during pattern development - unverified things that seemed to work but may be coincidence or context-specific.

Superstitions (⚠️ Treat With Skepticism)

Location: superstitions/

Single observations only. May be wrong, incomplete, or context-specific.

  • Treat with extreme skepticism
  • May be wrong, incomplete, or context-specific
  • Each has prominent warning disclaimer
  • Try if completely stuck, but verify thoroughly

When to Consult Superstitions

After checking official labs/docs/ first:

  • Encountering undocumented edge cases
  • Framework behaving unexpectedly
  • TypeScript errors not explained in official docs
  • Before creating new superstition (check if already documented)

Do NOT consult before official docs - labs/docs/ is always more authoritative!

Searching Superstitions

# Search superstitions
grep -r "Cell.*handler" community-docs/superstitions/

# List superstitions by topic
ls community-docs/superstitions/ | grep "types-"
ls community-docs/superstitions/ | grep "reactivity-"

If a Superstition Works

Upstream it to labs docs instead of keeping it here:

  1. Identify the appropriate doc in ~/Code/labs/docs/common/
  2. Add the information to that doc
  3. Create a PR to labs
  4. Once merged, delete the superstition

The goal is for verified knowledge to live in official docs, not here.

Creating a New Superstition

Only after solving something not in any docs:

  1. Search first - Check it's not already documented:

    grep -r "your topic" ~/Code/labs/docs/common/
    grep -r "your topic" community-docs/superstitions/
    
  2. Create file: community-docs/superstitions/YYYY-MM-DD-topic-brief-description.md

    • Use topic prefixes: types-, reactivity-, jsx-, handlers-, llm-, patterns-, etc.
  3. Copy template from community-docs/superstitions/README.md

  4. Include full ⚠️ disclaimer at top

  5. Document:

    • What problem you had
    • What you tried that didn't work
    • What solution seemed to work
    • Code examples (before/after)
    • Your context
    • Related official docs
  6. Commit: "Add superstition: [brief description]"

Remember: You're creating a hypothesis, not stating fact! Be humble about uncertainty.

Deprecated Tiers

The blessed/ and folk_wisdom/ directories are deprecated. Previously we had a three-tier promotion system. Now, verified knowledge should be upstreamed directly to labs docs.

Important Notes

Skepticism is critical:

  • Superstitions may be wrong or context-specific
  • Always prefer official labs/docs/ when they exist

Do NOT:

  • Trust superstitions blindly
  • Skip checking official docs first
  • Create superstition for things in official docs

DO:

  • Read disclaimer on every superstition
  • Verify against official docs
  • Test thoroughly before relying on it
  • Upstream verified knowledge to labs docs

Superstitions are a safety net for edge cases, not a primary reference!

Related Skills

  • recovery-strategies - Use superstitions as part of recovery escalation
  • pattern-dev - Reference when stuck on implementation

GitHub リポジトリ

majiayu000/claude-skill-registry
パス: skills/community-docs

関連スキル

content-collections

メタ

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

スキルを見る

creating-opencode-plugins

メタ

This skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.

スキルを見る

polymarket

メタ

This skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.

スキルを見る

cloudflare-turnstile

メタ

This skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.

スキルを見る