review-pull-request
О программе
Этот навык Claude выполняет автоматизированный сквозной анализ пул-реквеста на GitHub с использованием GH CLI. Он анализирует изменения и историю коммитов, проверяет статусы CI/CD и предоставляет структурированную обратную связь с уровнями серьёзности, такими как «критическое» или «рекомендация». Используйте его, когда пул-реквест назначен вам, чтобы обеспечить тщательную проверку перед привлечением ревьюеров-людей или аудитом слитого кода.
Быстрая установка
Claude Code
Рекомендуетсяnpx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/review-pull-requestСкопируйте и вставьте эту команду в Claude Code для установки этого навыка
Документация
Review Pull Request
Review GH PR end-to-end — understand change → submit structured feedback. Uses gh CLI for all GH interactions + produces severity-leveled review comments.
Use When
- PR ready for review + assigned to you
- Second review after author addresses feedback
- Self-review before req others
- Audit merged PR for post-merge quality
- Want structured review process not ad-hoc scanning
In
- Required: PR id (number, URL,
owner/repo#number) - Optional: Review focus (security, perf, correctness, style)
- Optional: Codebase familiarity (familiar, somewhat, unfamiliar)
- Optional: Time budget (quick scan, std, thorough)
Do
Step 1: Understand Ctx
Read PR description + understand what change accomplishes.
- Fetch PR metadata:
gh pr view <number> --json title,body,author,baseRefName,headRefName,labels,additions,deletions,changedFiles,reviewDecision - Read title + description:
- What problem does PR solve?
- What approach did author take?
- Specific areas author wants reviewed?
- Check PR size + assess time req:
PR Size Guide:
+--------+-----------+---------+-------------------------------------+
| Size | Files | Lines | Review Approach |
+--------+-----------+---------+-------------------------------------+
| Small | 1-5 | <100 | Read every line, quick review |
| Medium | 5-15 | 100-500 | Focus on logic changes, skim config |
| Large | 15-30 | 500- | Review by commit, focus on critical |
| | | 1000 | files, flag if should be split |
| XL | 30+ | 1000+ | Flag for splitting. Review only the |
| | | | most critical files. |
+--------+-----------+---------+-------------------------------------+
- Review commit history:
gh pr view <number> --json commits --jq '.commits[].messageHeadline'- Commits logical + well-structured?
- History tells story (each commit coherent step)?
- Check CI/CD status:
gh pr checks <number>- All checks passing?
- If failing, note which → affects review
→ Clear understanding of what PR does, why exists, how big, CI green. Ctx shapes review approach.
If err: PR description empty/unclear → note as first feedback. PR w/o ctx = review antipattern. gh cmds fail → verify auth (gh auth status) + repo access.
Step 2: Analyze Diff
Read actual code changes systematically.
- Fetch full diff:
gh pr diff <number> - Small/medium PRs: read entire diff sequential
- Large PRs: review by commit:
gh pr diff <number> --patch # full patch format - Each changed file eval:
- Correctness: Code does what PR says?
- Edge cases: Boundary conditions handled?
- Error handling: Caught + handled appropriately?
- Security: Injection, auth, data exposure risks?
- Perf: Obvious O(n^2), missing indexes, mem issues?
- Naming: New vars/fns/classes named clearly?
- Tests: New behaviors covered by tests?
- Take notes as read, classifying each by severity
→ Set of obs covering correctness, security, perf, quality for every meaningful change. Each obs has severity.
If err: diff too large to review effectively → flag: "This PR changes {N} files and {M} lines. I recommend splitting it into smaller PRs for more effective review." Still review highest-risk files.
Step 3: Classify Feedback
Organize obs into severity levels.
- Classify each obs:
Feedback Severity Levels:
+-----------+------+----------------------------------------------------+
| Level | Icon | Description |
+-----------+------+----------------------------------------------------+
| Blocking | [B] | Must fix before merge. Bugs, security issues, |
| | | data loss risks, broken functionality. |
| Suggest | [S] | Should fix, but won't block merge. Better |
| | | approaches, missing edge cases, style issues that |
| | | affect maintainability. |
| Nit | [N] | Optional improvement. Style preferences, minor |
| | | naming suggestions, formatting. |
| Praise | [P] | Good work worth calling out. Clever solutions, |
| | | thorough testing, clean abstractions. |
+-----------+------+----------------------------------------------------+
- Each Blocking explain:
- What's wrong (specific issue)
- Why matters (impact)
- How to fix (concrete suggestion)
- Each Suggest explain alternative + why better
- Keep Nits brief — one sentence enough
- Include ≥1 Praise if anything positive stands out
→ Sorted feedback list w/ clear severity. Blocking has fix suggestions. Ratio: few Blocking, some Suggest, minimal Nit, ≥1 Praise.
If err: everything seems blocking → PR may need rework not patch. Consider req changes at PR level vs line-by-line. Nothing wrong → say so — "LGTM" valid when code good.
Step 4: Write Comments
Compose review w/ structured actionable feedback.
- Write review summary (top-level):
- One sentence: what PR does (confirm understanding)
- Overall: approve, req changes, comment
- Key items: list Blocking (if any) + top Suggest
- Praise: call out good work
- Write inline comments for specific code locations:
# Post inline comments via gh API gh api repos/{owner}/{repo}/pulls/{number}/comments \ -f body="[B] This SQL query is vulnerable to injection. Use parameterized queries instead.\n\n\`\`\`suggestion\ndb.query('SELECT * FROM users WHERE id = $1', [userId])\n\`\`\`" \ -f commit_id="<sha>" \ -f path="src/users.js" \ -F line=42 \ -f side="RIGHT" - Format feedback consistent:
- Start each comment w/ severity tag:
[B],[S],[N],[P] - Use GH suggestion blocks for concrete fixes
- Link to docs for style/pattern suggestions
- Start each comment w/ severity tag:
- Submit review:
# Approve gh pr review <number> --approve --body "Review summary here" # Request changes (when blocking issues exist) gh pr review <number> --request-changes --body "Review summary here" # Comment only (when unsure or providing FYI feedback) gh pr review <number> --comment --body "Review summary here"
→ Submitted review w/ clear actionable feedback. Author knows exactly what to fix (Blocking), consider (Suggest), what went well (Praise).
If err: gh pr review fails → check perms. Need write access or be requested reviewer. Inline comments fail → fall back to all feedback in review body w/ file:line refs.
Step 5: Follow Up
Track resolution.
- After author responds or pushes updates:
gh pr view <number> --json reviewDecision,reviews - Re-review only changes addressing feedback:
gh pr diff <number> # check new commits - Verify Blocking resolved before approving
- Resolve comment threads as issues addressed
- Approve when all Blocking fixed:
gh pr review <number> --approve --body "All blocking issues resolved. LGTM."
→ Blocking verified fixed. Conversation resolved. PR approved or further changes req'd w/ specific remaining items.
If err: author disagrees → discuss in PR thread. Focus on impact (why matters) not authority. Disagreement persists on non-blocking → yield gracefully. Author owns code.
Check
- PR ctx understood (purpose, size, CI status)
- All changed files reviewed (or highest-risk for XL PRs)
- Feedback classified by severity (Blocking/Suggest/Nit/Praise)
- Blocking has specific fix suggestions
- ≥1 Praise for positive aspects
- Review decision matches feedback (approve only if no Blocking)
- Inline comments ref specific lines w/ severity tags
- CI/CD checks verified (green before approval)
- Follow-up done after author revisions
Traps
- Rubber-stamping: Approving w/o reading diff. Every approval = assertion of quality.
- Nit avalanche: Drowning author in style prefs. Save nits for mentoring; skip in time-sensitive reviews.
- Miss forest: Reviewing line-by-line w/o understanding overall design. Read description + commit history first.
- Block on style: Formatting + naming almost never blocking. Reserve Blocking for bugs, security, data integrity.
- No praise: Only pointing problems = demoralizing. Good code deserves recognition.
- Scope creep: Commenting on code not changed in PR. Pre-existing issues → file separate issue.
→
review-software-architecture— system-level architecture review (complementary)security-audit-codebase— deep security analysis for security-sensitive PRscreate-pull-request— other side: creating PRs easy to reviewcommit-changes— clean commit history makes PR review easier
GitHub репозиторий
Похожие навыки
llamaguard
ДругоеLlamaGuard — это модель от Meta с 7–8 миллиардами параметров для модерации входных и выходных данных больших языковых моделей по шести категориям безопасности, таким как насилие и разжигание ненависти. Она обеспечивает точность 94–95% и может быть развернута с помощью vLLM, Hugging Face или Amazon SageMaker. Используйте этот навык, чтобы легко интегрировать фильтрацию контента и защитные механизмы в ваши ИИ-приложения.
cost-optimization
ДругоеЭтот навык Claude помогает разработчикам оптимизировать облачные расходы за счет правильного подбора ресурсов, стратегий тегирования и анализа затрат. Он предоставляет framework для сокращения облачных расходов и внедрения управления затратами в AWS, Azure и GCP. Используйте его, когда вам нужно проанализировать расходы на инфраструктуру, оптимизировать ресурсы или уложиться в бюджетные ограничения.
quantizing-models-bitsandbytes
ДругоеЭтот навык выполняет квантизацию LLM до 8-битной или 4-битной точности с использованием библиотеки bitsandbytes, обеспечивая сокращение использования памяти на 50-75% при минимальной потере точности. Он идеально подходит для запуска больших моделей при ограниченной памяти GPU или для ускорения вывода, поддерживая форматы INT8, NF4 и FP4. Навык интегрируется с HuggingFace Transformers и позволяет использовать обучение QLoRA и 8-битные оптимизаторы.
dispatching-parallel-agents
ДругоеЭтот навык Claude распределяет нескольких агентов для исследования и устранения трёх и более независимых проблем параллельно. Он предназначен для сценариев с несвязанными сбоями, которые можно устранить без общего состояния или зависимостей. Ключевая возможность — параллельное решение проблем, где за каждую независимую предметную область назначается отдельный агент для максимальной эффективности.
