agentleFS
iadr-deviadr-dev/colab/skills/requesting-code-review/SKILL.md

requesting-code-review

Skill2 starsChanged 7 months agoMITView on GitHub

Senior-engineer code review: spec compliance first, then SOLID, security, performance, and code quality. Produces a structured P0-P3 severity report. Blocking issues (P0/P1) must be resolved before merge. Triggers on keyword "review" or when REVIEW workflow is active.

187 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use chinese-code-review, chinese-commit-conventions and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Leodorareluctant259Skill

    chinese-code-review

    中文代码审查规范——在保持专业严谨的同时,用符合国内团队文化的方式给出有效反馈

    Also in 8 projects that use this

  • Leodorareluctant259Skill

    chinese-commit-conventions

    中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化

    Also in 8 projects that use this

  • obraSkill

    diagnosing-superpowers

    Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.

    Also in 20 projects that use this

  • math-incSkill

    heartmula

    Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.

    Also in 9 projects that use this

  • Tommy-ywSkill

    webhook-subscriptions

    Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR push notifications to chats.

    Also in 5 projects that use this

  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 7 projects that use this

  • +3 more from Leodorareluctant259

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 173 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do NOT comment on code quality in this pass.

    line 47
  2. Distinctive:

    When proposing a refactor, explain *why* and outline a minimal, safe, incremental plan.

    line 58
  3. Distinctive:

    Clean review: If no issues found, explicitly state:

    line 128
  4. Distinctive:

    After presenting findings, ask:

    line 135
  5. Distinctive:

    Important: Do NOT implement any changes until user explicitly confirms.

    line 149

“Common” is measured: kept by at least 6 in 10 of the 173 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Code Review — Senior Engineer Protocol

Default: review-only output. Do NOT implement fixes unless user explicitly confirms.

Severity Levels

LevelNameDescriptionAction
P0CriticalSecurity vulnerability, data loss, correctness bugMust block merge
P1HighLogic error, significant SOLID violation, performance regressionShould fix before merge
P2MediumCode smell, maintainability concern, minor violationFix now or create follow-up
P3LowStyle, naming, minor suggestionOptional improvement

Workflow

Step 1 — Preflight Context

git status -sb
git diff --stat
git diff
  • Identify entry points, auth boundaries, and critical paths (payments, data writes, network).
  • If no diff: inform user, ask if they want staged changes or a specific commit range.
  • If large diff (>500 lines): summarize by file first, then review in batches by module.

Step 2 — Spec Compliance (Pass 1)

Compare against .ohc/plans/ success criteria and user requirements.

For each requirement:

  • ✓ Implemented — code clearly implements this
  • ⚠ Partial — implemented with a gap (name the gap)
  • ✗ Missing — not implemented (blocking)

Do NOT comment on code quality in this pass. Only: does it do what was asked?

Step 3 — SOLID + Architecture

Load references/solid-checklist.md. Look for:

  • SRP: Modules with unrelated responsibilities
  • OCP: Behavior added by editing, not extending
  • LSP: Subclasses that break parent contract
  • ISP: Wide interfaces with unused methods
  • DIP: High-level logic coupled to concrete implementations

When proposing a refactor, explain why and outline a minimal, safe, incremental plan.

Step 4 — Removal Candidates

Load references/removal-plan.md. Identify:

  • Unused code, redundant logic, feature-flagged-off code
  • Distinguish safe delete now vs defer with plan

Step 5 — Security & Reliability Scan

Load references/security-checklist.md. Check for:

  • XSS, injection (SQL/NoSQL/command), SSRF, path traversal
  • AuthZ/AuthN gaps, IDOR, missing tenancy checks
  • JWT issues: algorithm confusion, weak secrets, missing exp/iss/aud
  • Secret/PII leakage, excessive logging, missing data masking
  • Race conditions: TOCTOU, check-then-act, missing DB transactions
  • Runtime risks: unbounded loops, missing timeouts, ReDoS
  • Weak crypto (MD5/SHA1), hardcoded IVs, missing HMAC

Step 6 — Code Quality Scan

Load references/code-quality-checklist.md. Check for:

  • Error handling: swallowed exceptions, unhandled promise rejections, missing context
  • Performance: N+1 queries, sync I/O in async context, unbounded collections, missing cache
  • Boundary conditions: null/undefined, empty collections, off-by-one, integer overflow

Step 7 — Output Format

## Code Review Summary

**Files reviewed**: X files, Y lines changed
**Overall assessment**: [APPROVE / REQUEST_CHANGES / COMMENT]

---

## Findings

### P0 - Critical
(none or list)

### P1 - High
1. **[file:line]** Brief title
   - Description of issue
   - Suggested fix

### P2 - Medium
2. (continue numbering across sections)

### P3 - Low
...

---

## Spec Compliance
✓ Implements: ...
⚠ Partial: ...
✗ Missing: ...

## Removal/Iteration Plan
(if applicable)

Inline comment format for file-specific findings:

::code-comment{file="path/to/file.ts" line="42" severity="P1"}
Description of the issue and suggested fix.
::

Clean review: If no issues found, explicitly state:

  • What was checked
  • Areas not covered (e.g., "Did not verify database migrations")
  • Residual risks or recommended follow-up tests

Step 8 — Next Steps Confirmation

After presenting findings, ask:

## Next Steps

I found X issues (P0: _, P1: _, P2: _, P3: _).

**How would you like to proceed?**
1. **Fix all** — I'll implement all suggested fixes
2. **Fix P0/P1 only** — Address critical and high priority issues
3. **Fix specific items** — Tell me which issues to fix
4. **No changes** — Review complete, no implementation needed

Important: Do NOT implement any changes until user explicitly confirms.


See references/review-checklist.md for quick checklist reference. See references/solid-checklist.md, references/security-checklist.md, references/code-quality-checklist.md, references/removal-plan.md for full coverage.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.