一键导入
refactor-team
Team-based code refactoring with analysis and user-approved changes. Use when: "refactor this code", "リファクタリング", "コード整理", "refactor team", "リファクタチーム".
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Team-based code refactoring with analysis and user-approved changes. Use when: "refactor this code", "リファクタリング", "コード整理", "refactor team", "リファクタチーム".
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Web search using Google Antigravity CLI (agy, formerly Gemini CLI). Use for: latest information, documentation lookup, current events, or when up-to-date web data is needed.
Team-based PR review with specialized parallel agents, CI integration, and iterative fix loop. Use when: "review this PR", "PR review", "PRレビュー", "PRをレビューして", "チームでPRレビュー".
Surface things worth considering before merging a PR: simplify run, pr-review-team iterate, security scan (trufflehog), .gitignore patterns, tests, docs, and any project-specific items from CLAUDE.md. This is a reminder, not a verifier. Use when: "merge 前チェック", "チェックリスト", "何か漏れてない?", "pre-merge", "checkup", "マージ前確認".
Research topics or review code using OpenAI Codex CLI. Use for: technical research, documentation lookup, code analysis, or when external AI perspective is needed.
Research AWS topics using Kiro CLI as an AWS expert (readonly mode). Use for: AWS documentation, error investigation, CloudFormation/CDK questions, AWS best practices. Note: Uses Kiro's training knowledge only (no web search).
X (Twitter) Articles のエディタ仕様・記事構造・ベストプラクティス。 Use when: "X Articlesの記事を書く", "Twitter Article", "X Articlesのエディタ", "DraftJSの制約", "ヘッダー画像を作る", "記事を公開する", "X Articlesに投稿", "ヘッダー画像を生成する", "publish to X Articles".
| name | refactor-team |
| description | Team-based code refactoring with analysis and user-approved changes. Use when: "refactor this code", "リファクタリング", "コード整理", "refactor team", "リファクタチーム". |
| user-invocable | false |
Resolve target files:
git diff --name-only <base-branch> for changed filesDetect context:
git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||' (fallback: main)package.json, Makefile, pytest.ini, etc.MANDATORY: Use TeamCreate to create the team, then spawn agents with Task tool.
Team structure:
Team Lead (yourself)
├─ Analyzer: pr-review-toolkit:code-simplifier
└─ Refactorer: general-purpose (refactorer)
MANDATORY: Always specify an explicit model parameter when spawning each agent. Choose the appropriate model based on task complexity (haiku for lightweight, sonnet for standard, opus for complex reasoning). Never omit model (default inherit may fail in parallel spawning).
Analyzer examines target files using criteria from ${CLAUDE_PLUGIN_ROOT}/skills/refactor-team/references/analysis-criteria.md.
Analysis output format:
| # | Category | File:Line | Description | Priority | Risk |
|---|---|---|---|---|---|
| 1 | DRY | src/a.ts:42 | ... | High | Low |
| 2 | Naming | src/c.ts:8 | ... | Medium | None |
MANDATORY: Present the analysis table to user and wait for approval. Do NOT proceed without explicit user selection of which items to execute.
User selects items by number (e.g., "1, 3, 5" or "all").
For each approved item:
refactor: <description>Rules:
refactor:Report summary:
Send shutdown_request to all agents individually via SendMessage (one message per agent):
Wait up to 30 seconds for shutdown_response from each agent.
Then call TeamDelete.
If TeamDelete fails (agents did not respond to shutdown):
dangerouslyDisableSandbox: true:
rm -rf ~/.claude/teams/<team-name>/ ~/.claude/tasks/<team-name>/