メニュー
Multi-agent code review for GitHub PRs. Use when reviewing a pull request, running security/performance/architecture/style checks on a diff, or coordinating specialized review agents and posting findings back to a PR.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/DreamLab-AI/agentbox --skill github-code-reviewコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Implement features with tests and quality gates, debug hard bugs, and stress-test designs. Use when building a feature with TDD/EDD, chasing a stubborn multi-function bug (feedback-loop-first), interrogating a design before coding, or running a coverage/security/accessibility quality-gate pass. Supersedes agentic-qe, reasoningbank-*, and pair-programming.
Plan-execute-reflect loop over a persistent Python kernel (the `code-interpreter` MCP): write Python, execute, observe the returned trace (stdout / exception / last value), then revise. Variables, imports, and dataframes survive across every tool call in the session. Use for multi-step numerical reasoning, data wrangling, scientific Q&A, hypothesis-test loops, or any task where intermediate state must persist between turns and a runtime result should drive the next step.
Fires as a post-task hook after a non-trivial completed task (3+ tool calls, observable terminal outcome) to distil 0-N generalisable IF/THEN lessons from the trajectory and store them in RuVector so they surface at the start of similar future tasks; also invocable manually to record a lesson after a complex or failed task. NOT for trivial (<3 tool calls) or interrupted tasks, and NOT a general memory-write tool — it writes only ex:DistilledLesson records to the code-harness-lessons namespace. Schema, gates, prompt, and contradiction/archive policy live in references/.
SOC 職業分類に基づく
SKILL.md を表示中
| name | github-code-review |
| version | 1.0.0 |
| description | Multi-agent code review for GitHub PRs. Use when reviewing a pull request, running security/performance/architecture/style checks on a diff, or coordinating specialized review agents and posting findings back to a PR. |
| category | github |
| tags | ["code-review","github","swarm","pr-management","automation"] |
| author | Claude Code Flow |
| requires | ["github-cli","ruv-swarm","claude-flow"] |
| capabilities | ["Multi-agent code review","Automated PR management","Security and performance analysis","Swarm-based review orchestration","Intelligent comment generation","Quality gate enforcement"] |
Deploy specialized review agents (security, performance, architecture, style, accessibility) to review PRs in parallel and post findings back through the GitHub CLI — beyond traditional single-pass static analysis.
# Initialize review swarm for PR
gh pr view 123 --json files,diff | npx ruv-swarm github review-init --pr 123
# Post review status
gh pr comment 123 --body "🔍 Multi-agent code review initiated"
# Get PR context with gh CLI
PR_DATA=$(gh pr view 123 --json files,additions,deletions,title,body)
PR_DIFF=$(gh pr diff 123)
# Initialize comprehensive review across specialized agents
npx ruv-swarm github review-init \
--pr 123 \
--pr-data "$PR_DATA" \
--diff "$PR_DIFF" \
--agents "security,performance,style,architecture,accessibility" \
--depth comprehensive
Detailed agent catalogs, config schemas, and end-to-end recipes live in . Load the one you need on demand:
references/.github/review-swarm.yml, custom path triggers, quality-gate thresholds, status
checks, security considerations/checklist, and review/comment best practices.github-release-management — version management and deployment orchestrationgithub-workflow-automation — CI/CD pipeline managementgithub-project-management — issue tracking and sprint planninggithub-multi-repo — cross-repository coordinationLast Updated: 2026-07-28 · Version: 1.0.0 · Maintainer: Claude Code Flow Team · Licensed under the MIT License as part of the Claude Code Flow project.