pr:cmt-plan — community pr:cmt-plan, claudedot, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for GitHub Integration Agents needing advanced PR comment analysis and improvement planning capabilities. sorafujitani claude code settings user scope

sorafujitani sorafujitani
[0]
[0]
Updated: 3/5/2026

Agent Capability Analysis

The pr:cmt-plan skill by sorafujitani is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Perfect for GitHub Integration Agents needing advanced PR comment analysis and improvement planning capabilities.

Core Value

Empowers agents to analyze unresolved PR comments and devise systematic improvement plans using GitHub APIs and command-line tools like `git` and `gh`. It provides comprehensive PR context retrieval and metadata analysis.

Capabilities Granted for pr:cmt-plan

Analyzing PR comments for improvement opportunities
Generating systematic improvement plans for GitHub repositories
Automating PR review comment analysis

! Prerequisites & Limits

  • Requires GitHub API access
  • Limited to GitHub PRs
  • Depends on `git` and `gh` command-line tools
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

pr:cmt-plan

Install pr:cmt-plan, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

PR Comment Analysis & Improvement Planning

あなたはGitHub PRのレビューコメント分析と改善計画の専門家です。現在のブランチに関連するPRの未解決コメントを取得・分析し、体系的な改善計画を策定します。

実行手順

  1. PR特定

    • 現在のブランチ名を確認: git branch --show-current
    • 関連するPR番号を特定: gh pr list --head [branch-name] --json number,url --jq '.[0]'
  2. PRコンテキスト取得

    • ctx:github エージェント(Task ツールで subagent_type: "ctx:github")を呼び出し、PR情報を一括取得する
    • プロンプト例: "{owner}/{repo}#{PR番号} のPR情報を取得して"
    • 返却される構造化コンテキスト(=== GITHUB_CONTEXT: PR === ブロック)からメタデータ・BODY・REVIEW_STATUS・FILES・COMMENTSを利用する
    • インラインレビューコメント(ファイル・行単位)が必要な場合は追加で取得: gh api repos/{owner}/{repo}/pulls/{PR番号}/comments --jq '.[] | {path, line, body, user: .user.login, created_at}'
  3. コメント内容の分析

    • 重要度分類:
      • 🔴 Critical: バグ、セキュリティ、パフォーマンス問題
      • 🟡 Important: 設計改善、コード品質
      • 🟢 Minor: スタイル、命名、ドキュメント
    • カテゴリ分類:
      • Logic/Bug: ロジックエラーやバグ
      • Performance: パフォーマンス関連
      • Security: セキュリティ懸念
      • Design: 設計・アーキテクチャ
      • Code Quality: コード品質・可読性
      • Testing: テスト関連
      • Documentation: ドキュメント・コメント
  4. 改善計画の策定

    • コメントの優先順位付け
    • 依存関係の特定
    • 実装順序の決定
    • 各改善の影響範囲評価
  5. 実行計画の作成

    • 具体的な修正手順
    • 各修正のコミット計画
    • テスト・検証方法

出力形式

📊 PR情報

  • PR番号: #[番号]
  • タイトル: [PRタイトル]
  • URL: [GitHub URL]
  • 未解決コメント数: [数]

🔍 コメント分析

Critical Issues 🔴

  1. [コメント作成者]: [コメント内容の要約]
    • 場所: file.ts:L123
    • カテゴリ: [カテゴリ]
    • 原文: "[実際のコメント]"
    • 影響: [影響範囲の説明]

Important Issues 🟡

[同様の形式で記載]

Minor Issues 🟢

[同様の形式で記載]

📝 改善実行計画

Phase 1: Critical修正

bash
1# 1. [修正内容の説明] 2# 対象: file.ts 3# 理由: [コメント#1への対応] 4[具体的なコマンドや修正内容] 5 6git add file.ts 7git commit -m "fix: [修正内容]"

Phase 2: Important修正

[同様の形式で記載]

Phase 3: Minor修正

[同様の形式で記載]

✅ 検証チェックリスト

  • すべてのCriticalコメントに対応
  • テストが通過することを確認
  • 新たな問題を導入していないことを確認
  • コメントへの返信を準備

📃 関連Reference

markdown
1# コメント内容に関連するReference URL 2 3- [Reference 1](https://example.com/ref1) 4- [Reference 2](https://example.com/ref2)

考慮事項

  • 優先順位: Criticalから順に対応し、ブロッカーを解消
  • 一貫性: 同種の問題は一括で修正
  • 透明性: 各修正がどのコメントに対応するか明確化
  • 検証可能性: 修正が適切に機能することを確認
  • 情報の公式な引用: 正確な理解や対応を促す

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is pr:cmt-plan?

Perfect for GitHub Integration Agents needing advanced PR comment analysis and improvement planning capabilities. sorafujitani claude code settings user scope

How do I install pr:cmt-plan?

Run the command: npx killer-skills add sorafujitani/claudedot. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for pr:cmt-plan?

Key use cases include: Analyzing PR comments for improvement opportunities, Generating systematic improvement plans for GitHub repositories, Automating PR review comment analysis.

Which IDEs are compatible with pr:cmt-plan?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for pr:cmt-plan?

Requires GitHub API access. Limited to GitHub PRs. Depends on `git` and `gh` command-line tools.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add sorafujitani/claudedot. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use pr:cmt-plan immediately in the current project.

Related Skills

Looking for an alternative to pr:cmt-plan or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI