免费在 GitHub 公开

pr-reviewer

Automated Git PR review — diff analysis + quality checks.

中文简介正在准备中。当前显示原文说明。

mangowhoiscloud/geode

查看安装方法

包含的文件（1）

SKILL.md2.1 KB

SKILL.md（原文）

安装前可以查看交给 AI 代理的指令内容。

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

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

评价

还没有评价。欢迎分享你的使用感受。

无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

同一仓库的技能

agent-anti-pattern

免费

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.

中文简介正在准备中。当前显示原文说明。