agentleFS
Sign inStart free
LucasCooperBeyLucasCooperBey/claude-skills/skills/requesting-code-review/SKILL.md

requesting-code-review

Skill1 starsChanged 5 months agoMITView on GitHub

Structures code review requests with context, commit hashes, and requirements. Facilitates early and frequent review cycles.

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 173 edited versions we read keep these.

  • 2

    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:

    If feedback seems incorrect:

    line 131
  2. Distinctive:

    Don't dismiss it immediately

    line 133

“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

Requesting Code Review

Structure code review requests for effective feedback.

Core Principle

Review early, review often. Prevents issues from compounding.

When Reviews Are Required

ScenarioPriority
After each task in subagent workflowRequired
Upon finishing major featuresRequired
Before merging to mainRequired
When stuckOptional
Before refactoringOptional
After fixing complex bugsOptional

Request Process

1. Gather Context

# Get commit range
BASELINE=$(git merge-base HEAD main)
CURRENT=$(git rev-parse HEAD)

echo "Baseline: $BASELINE"
echo "Current: $CURRENT"

# Show what changed
git log $BASELINE..$CURRENT --oneline
git diff $BASELINE..$CURRENT --stat

2. Dispatch Review Request

Task({
  prompt: `
    Code review request.

    ## What Was Built
    [Brief description of feature/fix]

    ## Requirements
    [Original requirements or task description]

    ## Commits
    - Baseline: ${BASELINE}
    - Current: ${CURRENT}

    ## Description
    [What changed and why]

    ## Areas of Concern
    [Specific things to look at closely]

    Please review for:
    - Spec compliance
    - Code quality
    - Test coverage
    - Potential issues
  `,
  subagent_type: "general-purpose"
})

3. Act on Findings

SeverityAction
CriticalFix immediately
ImportantFix before proceeding
MinorDocument for later

Request Template

## Code Review Request

### Summary
[One sentence describing what this code does]

### Requirements Fulfilled
- [x] Requirement 1
- [x] Requirement 2

### Changes
**Files modified:**
- `src/feature.ts` - Added validation logic
- `src/feature.test.ts` - Added tests

**Commits:**

abc123 - Add user validation def456 - Add error handling


### How to Test
```bash
bun test src/feature.test.ts

Concerns

  • Performance of X might be an issue with large data
  • Not sure if Y pattern is idiomatic

Questions

  • Should we also handle edge case Z?

## Reviewer Categories

Reviewers will categorize feedback:

| Category | Meaning | Your Action |
|----------|---------|-------------|
| Critical | Blocks merge | Fix now |
| Important | Should fix | Fix before continuing |
| Minor | Nice to have | Schedule for later |
| Question | Clarification | Answer promptly |

## Handling Disagreement

If feedback seems incorrect:

1. Don't dismiss it immediately
2. Provide technical evidence
3. Explain your reasoning
4. Be open to being wrong

I hear your concern about X. Here's why I chose this approach:

  1. [Technical reason]
  2. [Evidence from testing]
  3. [Alternative considered and why rejected]

If you still think Y is better, I'm happy to change it.


## Post-Review

After receiving feedback:

```bash
# Fix issues
# ...

# Verify fixes
bun test

# Commit fixes
git commit -m "Address review feedback: [summary]"

# Re-request if changes were significant

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