Review skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, required sections, and repo conventions. WHEN: \"review skill\", \"review skill PR\", \"review skill changes\", \"check skill quality\", \"skill PR feedback\".
Scanned 5/28/2026
Install via CLI
openskills install microsoft/GitHub-Copilot-for-Azure---
name: skill-reviewer
description: "Review skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, required sections, and repo conventions. WHEN: \"review skill\", \"review skill PR\", \"review skill changes\", \"check skill quality\", \"skill PR feedback\"."
license: MIT
metadata:
author: Microsoft
version: "1.0.3"
---
# Skill PR Reviewer
Performs thorough, structured code reviews of skill PRs — severity-classified findings with actionable fixes, positive acknowledgment, and a summary table.
## When to Use
- Reviewing a PR that adds or modifies a skill under `plugin/skills/` or `.github/skills/`
- Checking skill compliance before submitting a PR
- Auditing an existing skill for quality issues
> 💡 **Note:** `.github/skills/` meta-skills have different conventions — checklist sections 8-9 apply only to `plugin/skills/` service skills.
## Review Workflow
1. **Collect** — Identify all changed skill files (SKILL.md, references, tests, scripts)
2. **Check** — Run each category from the [review checklist](references/review-checklist.md)
3. **Classify** — Assign severity per the [severity guide](references/severity-classification.md)
4. **Analyze Routing** — Check triggers for conflicts per [routing analysis](references/routing-analysis.md)
5. **Draft** — Write the review per the [output format](references/output-format.md)
6. **Validate** — Verify suggested fixes are actionable with accurate file/line references
## Error Handling
| Error | Remediation |
|-------|-------------|
| Cannot determine changed files | Ask user for the file list or PR number |
| Token counting unavailable | Estimate at ~4 chars per token |
## References
- [Review Checklist](references/review-checklist.md)
- [Severity Classification](references/severity-classification.md)
- [Routing Analysis](references/routing-analysis.md)
- [Output Format](references/output-format.md)
No comments yet. Be the first to comment!
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
一个全面的 Claude Code 会话验证系统。