MCP HubMCP Hub
スキル一覧に戻る

creating-github-issues

majiayu000
更新日 2 days ago
24 閲覧
58
9
58
GitHubで表示
メタword

について

このスキルは、開発者がGitHubイシューを作成する前に適切な調査とドキュメンテーションを行うことで、包括的なイシュー作成を支援します。イシュー関連のフレーズをトリガーとして、コードベースの調査や具体的な技術的詳細の記載方法をユーザーにガイドします。このワークフローでは、ファイルパス、コードスニペット、既存のパターンなどのコンテキストを追加し、明確で実行可能なイシュー作成を重視しています。

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/creating-github-issues

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

Creating GitHub Issues

Overview

Every GitHub issue should be well-researched and clearly documented. This skill ensures issues contain enough context for anyone to understand and implement them.

Mandatory Workflow

Step 1: Research the Codebase

Before writing the issue, use the Explore agent or search tools to understand:

  • Where relevant code lives (file paths, functions, components)
  • How similar functionality is currently implemented
  • Database tables, API endpoints, or UI components involved
  • Existing patterns that should be followed

Include in the issue:

  • Specific file paths and line numbers
  • Code snippets showing current implementation
  • References to similar existing code as examples

Why: Issues with research reduce back-and-forth questions and give implementers a head start.

Step 2: Create the Issue

Use gh issue create with a well-structured body:

gh issue create --title "Brief descriptive title" --body "$(cat <<'EOF'
## Summary
<1-3 sentences describing what needs to be done>

## Current State
<What exists now, with file paths and code references>

## Proposed Changes
<What should change, with specific details>

## Technical Notes
<File paths, database tables, API endpoints, code snippets>

## Acceptance Criteria
- [ ] Specific testable requirement
- [ ] Another requirement
EOF
)"

Step 3: Add Labels

Discover current labels and apply appropriate ones:

gh label list --limit 50

Common label categories:

  1. Type (pick one):

    • enhancement - New feature or improvement
    • bug - Something isn't working
    • documentation - Documentation improvements
    • question - Further information requested
  2. Priority (if applicable):

    • priority: critical - Production broken, blocking issue
    • priority: high - Important bug fix, urgent feature
    • priority: low - Nice to have, can wait
  3. Area (if applicable):

    • Labels indicating which part of the codebase is affected
gh issue edit <number> --add-label "enhancement"

Step 4: Add to Project (if applicable)

If the repository uses GitHub Projects:

gh issue edit <number> --add-project "Project Name"

Issue Template

## Summary
<1-3 sentences describing what needs to be done>

## Current State
<What exists now>
- File: `path/to/file.ts:123`
- Current behavior: <description>

## Proposed Changes
<What should change>
1. Change X to do Y
2. Add Z functionality

## Technical Notes
- Relevant files: `src/components/Feature.tsx`, `src/utils/helpers.ts`
- Related functions: `handleSubmit()`, `validateInput()`
- Consider: <architectural notes, edge cases>

## Acceptance Criteria
- [ ] Specific testable requirement
- [ ] Another requirement
- [ ] Tests pass

## Additional Context
<Screenshots, error messages, related issues>

Field Selection Guidelines

Priority

  • Critical - Production broken, blocking issue
  • High - Important bug fix, urgent feature (most bugs default here)
  • Medium - Standard feature work
  • Low - Nice to have, can wait

Default guidance: Bugs default to High unless trivial. Enhancements default to Medium unless urgent.

Common Mistakes

MistakeFix
Create issue without researching code firstUse Explore agent to find relevant files
Generic issue descriptionInclude specific file paths, line numbers, code snippets
Missing acceptance criteriaAlways include testable requirements
No labelsAlways add at least a type label
Vague titleMake titles specific and searchable

GitHub リポジトリ

majiayu000/claude-skill-registry
パス: skills/creating-github-issues

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

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

llamaindex

メタ

LlamaIndex is a data framework for building RAG-powered LLM applications, specializing in document ingestion, indexing, and querying. It provides key features like vector indices, query engines, and agents, and supports over 300 data connectors. Use it for document Q&A, chatbots, and knowledge retrieval when building data-centric applications.

スキルを見る

canvas-design

メタ

The canvas-design skill generates original visual art in PNG and PDF formats for creating posters, designs, and other static artwork. It operates through a two-step process: first creating a design philosophy document, then visually expressing it on a canvas. The skill focuses on original compositions using form, color, and space while avoiding copyright infringement by never copying existing artists' work.

スキルを見る