Install
$ agentstack add skill-tao12345666333-amcp-gh-pr-review ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
GitHub PR Review Skill
Review Pull Requests by fetching the diff, analyzing changes, and posting structured review comments.
Prerequisites
ghCLI authenticated (gh auth status)- Repository must be a git clone with a GitHub remote
Review Workflow
- Fetch PR metadata: Run
gh pr view --json title,body,files,additions,deletions,author,baseRefName,headRefName - Fetch the diff: Run
gh pr diffto get the full diff - Analyze the changes by category:
- Architecture: New files/modules, structural decisions
- Correctness: Logic bugs, edge cases, error handling
- Security: Input validation, secrets, auth
- Performance: Unnecessary allocations, N+1 queries, blocking I/O
- Style: Naming, consistency with codebase conventions
- Tests: Coverage, edge cases, test quality
- Produce a structured review (see format below)
Review Output Format
## PR Review:
**PR**: # | **Author**: | **Branch**: →
**Files changed**: | **+** / **-**
### Summary
### 👍 Strengths
-
### 🔍 Issues Found
#### Critical
- [ ] : —
#### Suggestions
- [ ] : —
#### Nits
-
### 📋 Checklist
- [ ] Tests added/updated
- [ ] No secrets or credentials
- [ ] Error handling adequate
- [ ] Documentation updated if needed
### Verdict
—
Posting the Review
After generating the review, offer to post it as a PR comment:
gh pr review --comment --body ""
Or for approve/request-changes:
gh pr review --approve --body ""
gh pr review --request-changes --body ""
Tips
- For large PRs (>500 lines), focus on architectural decisions and critical issues first
- Check for consistency with the existing codebase patterns
- Look at test coverage relative to the complexity of changes
- Use
gh pr checksto see CI status - When reviewing Python, pay attention to type hints, docstrings, and error handling
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: tao12345666333
- Source: tao12345666333/amcp
- License: Apache-2.0
- Homepage: https://x.com/zhangjintao9020/status/1995170132973466018?s=20
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.