Skip to main content
ClaudeWave
Skill155 estrellas del repoactualizado 18d ago

pr-review-agent

Full PR review orchestrator. Use when asked to review a PR or check if it is ready to merge. Runs blast radius + drift check on changed files, then hands off to pr-review for comment triage and fixes. Do NOT use pr-review directly for full reviews — use this.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/wednesday-solutions/ai-agent-skills /tmp/pr-review-agent && cp -r /tmp/pr-review-agent/skills/agents/pr-review-agent ~/.claude/skills/pr-review-agent
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# PR Review Agent

## When to use
- "Review this PR"
- "Is this PR ready to merge?"
- "Check this PR for issues"
- PR is open and review comments have been posted

## What to do

1. **triage-read** — Fetch all review comments via `gh pr view --comments`. Sort by impact: security → breaking → logic → performance → naming → style. Present the full categorised list to the dev.

2. **In parallel:**
   - **brownfield-fix** — Run `wednesday-skills score` and `wednesday-skills blast` on every file changed in the PR. Flag any file with risk > 60.
   - **brownfield-drift** — Run `wednesday-skills drift --since <base-sha>`. Report any architecture violations introduced by this PR.

3. Present a unified report:
   - Review comments (categorised)
   - High-risk changed files (score + dependent count)
   - Architecture violations (if any)

4. **triage-fix** — Wait for dev approval: "@agent fix #N" or "@agent fix all". Apply fixes in priority order. Read git-os skill before committing. One commit per fix item.

## Never
- Fix without explicit dev approval
- Skip blast radius check — always run even for small PRs
- Skip drift check — always run even if no violations are expected
- Bundle multiple file fixes in one commit
- Force-push or silently skip a failed fix
module-audit-agentSkill

Use when asked to audit a module, check its health, or assess whether it should be refactored. Runs structural query, risk check, and test generation automatically.

onboard-dev-agentSkill

Use when a dev is new to the project, asks for an overview, or wants to get oriented quickly. Fills graph gaps then runs a guided codebase interview.

brownfield-driftSkill

Enforces architecture boundaries defined in PLAN.md. Use when a PR crosses module/service boundaries, when the dev asks "are we following the architecture?", or as a scheduled architecture health check. Not for querying what a module does — use brownfield-chat for that.

codebase-intelSkill

Unified codebase intelligence. Handles all questions about structure, logic, risk, and dependencies. Combines natural-language Q&A with deterministic lookups and pre-edit blast radius checks.

deploy-checklistSkill

Pre-deploy and post-deploy checklist skill. Ensures env vars, migrations, CI, rollback plan, smoke tests, and monitoring are verified before and after every deployment.

greenfieldSkill

Parallel persona planning for new projects. Research agent runs first to build domain context, then Architect, PM, and Security agents run in parallel. Synthesis agent combines all perspectives into a detailed GSD-style PLAN.md with Tensions section.

pr-reviewSkill

Fix engine for PR review comments. Fetches review comments (Gemini bot or human), categorizes by impact, posts a prioritized fix queue, and applies fixes on dev approval. Called directly for quick fixes, or internally by pr-review-agent as part of full PR review.

standards-kitSkill

Unified development and design standards. Enforces code quality (complexity < 8), strict naming conventions, and the mandatory use of approved UI component libraries.