agentsclimarketplace
Sign in

Code review

Skill a5c-ai/babysitter/library/methodologies/rpikit/skills/code-review

Structured code quality assessment with Conventional Comments format, scaled review depth, and soft-gating verdicts preserving user autonomy.From its SKILL.md

Install
npx -y skills add a5c-ai/babysitter --skill code-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.5 KB, 245 tokens by cl100k_base, as published. Nobody here has run it

  • When reviewing code changes before merge
  • As part of the /review-code command

Process

  1. Identify modified files via git
  2. Assess change magnitude for review depth
  3. Execute 9-step review: context, correctness, design, testing, security flags, operations, maintainability
  4. Synthesize findings in standardized report
  5. Deliver verdict with rationale

Review Depth Scaling

  • Under 200 lines: full detail review
  • 200-1000 lines: focused review on critical areas
  • Over 1000 lines: architectural-level review only

Verdicts

  • APPROVE: Ready for security review
  • APPROVE WITH NITS: Non-blocking suggestions only
  • REQUEST CHANGES: Blocking issues exist (user may override)

Key Rules

  • Provide specific file paths and line numbers
  • Include at least one positive comment per review
  • Use Conventional Comments format with decorations
  • Explain reasoning, not just observations
  • Limit critical issues to top 5 per category
  • Reviews are soft gates preserving user autonomy

Tool Use

Invoke via babysitter process: methodologies/rpikit/rpikit-review

What ships with it: 1 file

445 B alongside SKILL.md

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.