Skip to content
cccskills
FreePublished on GitHub

pr-reviewer

Automated Git PR review — diff analysis + quality checks.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md2.1 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

PR Reviewer

Review code changes against the current repository contracts. A review request does not authorize code edits, PR mutations, or memory writes. Use only available, permitted read-only inspection; a supplied diff can be reviewed without shell access, with any missing context stated explicitly.

Review Perspectives (5-lens)

1. Consistency

  • Do changes match the PR title/description
  • Are changes within the scope specified in plan documents (docs/plans/)
  • Are there unrelated changes mixed in

2. Safety

  • Are there DANGEROUS tool additions/modifications
  • Secret/key exposure risks
  • SQL injection, command injection patterns

3. Testing

  • Are there corresponding tests for the changed code
  • Have tests been deleted/disabled (anti-deception)
  • Coverage regression

4. Architecture

  • core/, evals/, and evolve/ ownership and dependency-direction violations; use AGENTS.md and docs/architecture/package-classification.md for the current contract, not the retired 6-layer map
  • Circular import introduction
  • God Object bloat

5. Style

  • ruff/mypy pass status
  • Naming consistency
  • Unnecessary comments/docstrings

Usage

Review PR #520

or

Review the last 3 commits

Output Format

## PR Review — #NNN

### Summary
- Files changed: N
- Additions/Deletions: +XX / -YY

### Findings
| Severity | File:Line | Issue |
|----------|-----------|-------|
| HIGH | core/x.py:42 | ... |
| LOW | tests/y.py:10 | ... |

### Verdict
- [ ] Consistency OK
- [ ] Safety OK
- [ ] Testing OK
- [ ] Architecture OK
- [ ] Style OK

Guidelines

  • Review based on actual diff via git diff or gh pr diff
  • No guessing — read the code and judge
  • Severity levels: HIGH (blocks merge), MEDIUM (recommended fix), LOW (improvement suggestion)
  • If no findings, say so with the inspected scope and verification limits; do not imply unrun tests passed or the PR is ready to merge

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Audit agent runtimes and their tests for lifecycle inference, capability overload, context pollution, correlated verification, prompt-only control, false success, dead compatibility paths, test-only seams, and complexity without contribution. Use for whole-repository agent audits, slop or dead-code triage, test contribution reviews, large refactors, tool/context simplification, and cleanup requests that need proof before deleting code or tests.

The English summary is being prepared. Showing the original description.

mangowhoiscloud/geode15Updated Oct 22, 2026

Diagnose agent operational failures through default-policy checks, multi-gap analysis, explicit service ownership, request-context lifetime, and degradation-versus-correctness checks.

The English summary is being prepared. Showing the original description.

mangowhoiscloud/geode15Updated Oct 22, 2026

Align, run, audit, and publish GEODE benchmark comparisons against Agent-World arXiv 2604.18292v1 across MCP-Mark, BFCL V4, and tau2-bench. Use for Agent-World or AgentWorld comparison requests, cross-suite agent benchmark design, Tau2 comparator/profile diagnosis, paired thin-runtime-versus-GEODE experiments, mean-accuracy@8 replication, or benchmark comparability and artifact reviews.

The English summary is being prepared. Showing the original description.

mangowhoiscloud/geode15Updated Oct 22, 2026

Verification checklist to prevent fake success. Detects test deletion/disabling, coverage regression, lint bypass, secret exposure. Triggered by "deception", "fake" ("가짜"), "fake success", "verification" ("검증"), "checklist" ("체크리스트"), "deletion detection" ("삭제 탐지"), "regression" keywords.

The English summary is being prepared. Showing the original description.

mangowhoiscloud/geode15Updated Oct 22, 2026

Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use when architecting complex backend systems or refactoring existing applications for better maintainability.

The English summary is being prepared. Showing the original description.

mangowhoiscloud/geode15Updated Oct 22, 2026

Auto-search and summarize latest AI/agent papers.

The English summary is being prepared. Showing the original description.

mangowhoiscloud/geode15Updated Oct 22, 2026

See all skills by mangowhoiscloud

Report a problem with this skill