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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/oimiragieo/agent-studio --skill requesting-code-review命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Agent frontmatter enhancements — disallowedTools, mcpServers scoping, fork_eligible field
Context management — pre-compact persistence, threshold alignment, microcompact/circuit breaker detection
Hook enhancements — updatedInput for bash safety prefixes, suppressOutput for verbose blocks, denial-based routing feedback
正在显示 SKILL.md
基于 SOC 职业分类
| name | requesting-code-review |
| description | Dispatch code-reviewer agent for two-stage review. Use after completing implementation tasks. |
| version | 1.1.0 |
| category | Development Workflow |
| agents | ["developer","code-reviewer"] |
| tags | ["code-review","git","diff","pull-request","review-request"] |
| model | sonnet |
| invoked_by | both |
| user_invocable | true |
| tools | ["Read","Bash","Task"] |
| best_practices | ["Capture BASE_SHA and HEAD_SHA before review","Provide full context to reviewer","Request review at mandatory checkpoints"] |
| error_handling | graceful |
| streaming | supported |
| verified | true |
| lastVerifiedAt | "2026-02-22T00:00:00.000Z" |
| source | builtin |
| trust_score | 100 |
| provenance_sha | 3ce59765f5cea843 |
Dispatch code-reviewer subagent to catch issues before they cascade.
Core principle: Review early, review often.
Mandatory:
Optional but valuable:
1. Get git SHAs:
BASE_SHA=$(git rev-parse HEAD~1) # or origin/main
HEAD_SHA=$(git rev-parse HEAD)
2. Dispatch code-reviewer subagent:
Use Task tool with code-reviewer type, fill template at code-reviewer.md
Placeholders:
{WHAT_WAS_IMPLEMENTED} - What you just built{PLAN_OR_REQUIREMENTS} - What it should do{BASE_SHA} - Starting commit{HEAD_SHA} - Ending commit{DESCRIPTION} - Brief summary3. Act on feedback:
[Just completed Task 2: Add verification function]
You: Let me request code review before proceeding.
BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
HEAD_SHA=$(git rev-parse HEAD)
[Dispatch code-reviewer subagent]
WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
PLAN_OR_REQUIREMENTS: Task 2 from docs/plans/deployment-plan.md
BASE_SHA: a7981ec
HEAD_SHA: 3df7661
DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
[Subagent returns]:
Strengths: Clean architecture, real tests
Issues:
Important: Missing progress indicators
Minor: Magic number (100) for reporting interval
Assessment: Ready to proceed
You: [Fix progress indicators]
[Continue to Task 3]
Task({
task_id: 'task-1',
: ,
: ,
: ,
: ,
});
Subagent-Driven Development:
Executing Plans:
Ad-Hoc Development:
Never:
If reviewer wrong:
See template at: requesting-code-review/code-reviewer.md
| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| Skipping review for "small" changes | Small changes introduce the same classes of bugs as large ones; "simple" is subjective and unreliable | Request review at every mandatory checkpoint regardless of perceived complexity |
| Dispatching reviewer without git SHAs | Reviewer cannot produce an accurate diff without a commit range; the review is inaccurate or incomplete | Capture BASE_SHA and HEAD_SHA before every review dispatch |
| Proceeding past Critical issues | Critical issues compound; later tasks build on broken foundations that are expensive to fix retroactively | Fix all Critical issues before advancing to the next task |
| Treating reviewer feedback as optional | Optional review degrades code quality over time and compounds technical debt that can't be traced | Follow severity escalation: Critical → fix now, Important → fix before next task, Minor → note for later |
| Requesting review after batches of tasks instead of after each task | Errors from Task 1 contaminate Tasks 2–N; reviewers cannot isolate which task introduced which issue | Review after each individual task before starting the next one |
Before starting:
Read .claude/context/memory/learnings.md
After completing:
.claude/context/memory/learnings.md.claude/context/memory/issues.md.claude/context/memory/decisions.mdASSUME INTERRUPTION: If it's not in memory, it didn't happen.