agentleFS
Sign inStart free
basidiocarpbasidiocarp/pileus/.claude/skills/code-review-process/SKILL.md

code-review-process

Skill0 starsChanged 6 months agoMITView on GitHub

Runs an end-to-end code review workflow with subagent feedback and technical evaluation.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    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:

    Mandatory: After completing major features, before merge to main, after each task in agent-driven development.

    line 11
  2. Distinctive:

    Optional: When stuck, before refactoring, after fixing complex bugs.

    line 13
  3. Distinctive:

    If ANY item is unclear: STOP.

    line 48
  4. Distinctive:

    If reviewer suggests "implementing properly": grep for actual usage.

    line 60
  5. Distinctive:

    Test each fix individually

    line 68
  6. Distinctive:

    Use technical reasoning, not defensiveness.

    line 78
  7. Distinctive:

    Do: "Fixed. [Brief description]" or "Good catch — [issue].

    line 82
  8. Distinctive:

    Don't: "You're absolutely right!", "Great point!", "Thanks for catching that!"

    line 84

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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 Process

Requesting Reviews

When to Request

Mandatory: After completing major features, before merge to main, after each task in agent-driven development.

Optional: When stuck, before refactoring, after fixing complex bugs.

How to Request

  1. Get SHAs: BASE_SHA=$(git rev-parse HEAD~1) and HEAD_SHA=$(git rev-parse HEAD)
  2. Dispatch code-reviewer subagent with: what was implemented, plan/requirements, base/head SHAs
  3. Act on feedback:
    • Fix Critical issues immediately
    • Fix Important issues before proceeding
    • Note Minor issues for later
    • Push back with reasoning if reviewer is wrong

Review Cadence

  • Agent-driven development: Review after EACH task
  • Executing plans: Review after each batch (~3 tasks)
  • Ad-hoc: Review before merge

Receiving Reviews

The Response Pattern

1. READ: Complete feedback without reacting
2. UNDERSTAND: Restate requirement in own words (or ask)
3. VERIFY: Check against codebase reality
4. EVALUATE: Technically sound for THIS codebase?
5. RESPOND: Technical acknowledgment or reasoned pushback
6. IMPLEMENT: One item at a time, test each

Handling Unclear Feedback

If ANY item is unclear: STOP. Do not implement anything yet. Ask for clarification on all unclear items before proceeding — items may be related.

From External Reviewers

Before implementing:

  1. Is it technically correct for THIS codebase?
  2. Does it break existing functionality?
  3. Is there a reason for the current implementation?
  4. Does the reviewer understand full context?

YAGNI Check

If reviewer suggests "implementing properly": grep for actual usage. If unused → suggest removal (YAGNI).

Implementation Order

  1. Clarify anything unclear FIRST
  2. Blocking issues (breaks, security)
  3. Simple fixes (typos, imports)
  4. Complex fixes (refactoring, logic)
  5. Test each fix individually

When to Push Back

  • Suggestion breaks existing functionality
  • Reviewer lacks full context
  • Violates YAGNI
  • Technically incorrect for this stack
  • Conflicts with architectural decisions

Use technical reasoning, not defensiveness. Reference working tests/code.

Acknowledging Correct Feedback

Do: "Fixed. [Brief description]" or "Good catch — [issue]. Fixed in [location]." or just fix it.

Don't: "You're absolutely right!", "Great point!", "Thanks for catching that!"

Common Mistakes

MistakeFix
Performative agreementState requirement or just act
Blind implementationVerify against codebase first
Batch without testingOne at a time, test each
Assuming reviewer is rightCheck if breaks things
Avoiding pushbackTechnical correctness > comfort

Reference Files

  • Code Reviewer

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.

Check your setup, free