Review existing feedback: gh pr view <number> --comments for all comments and previous reviews
Verify all issues addressed: Ensure bot failures, reviewer requests, and discussion points are resolved
Call out unresolved feedback: Explicitly mention any discussions/requests that remain unaddressed
Critical Review Elements
Licensing: Verify GPLv3/BSD-2-Clause compatibility for any new dependencies
Test scope: Tests must exercise actual changed code, not just add random coverage
Changelog validation: Fragment structure follows sections defined in changelogs/config.yaml
Each step is tracked in TodoWrite for visibility and systematic completion. A review round should not exceed 20 feedback items.
1---2name: review-33description: Review4---56PR Review Command7=================89Review an Ansible PR following the project's standardized process from `CLAUDE.md`.1011Usage12-----1314```bash15/review <pr_number>16```1718Arguments19---------2021- `pr_number` (required): The GitHub PR number to review2223Implementation24--------------2526This command implements the PR Review Guidelines documented in the `PR Review Guidelines` section of CLAUDE.md.2728Review Process Steps29--------------------3031The command follows these numbered steps from CLAUDE.md:32331. **Create TodoWrite list** for systematic review tracking342. **Get PR details**: `gh pr view <number>` to understand scope, motivation and the desired outcome353. **Get PR diff**: `gh pr diff <number>` to see all changes364. **Check required components FIRST**:37 - Verify changelog fragment exists in `changelogs/fragments/`38 - Verify changelog uses correct section (check `changelogs/config.yaml`)39 - Verify tests exist and specifically cover the changed code paths40 - Unit tests should be pytest style, and functional rather than tightly coupled to mocking41 - Integration tests required for almost all plugin changes425. **Checkout PR branch**: `gh pr checkout <number>` to examine code holistically436. **Review existing feedback**: `gh pr view <number> --comments` for all comments and previous reviews447. **Verify all issues addressed**: Ensure bot failures, reviewer requests, and discussion points are resolved458. **Call out unresolved feedback**: Explicitly mention any discussions/requests that remain unaddressed4647Critical Review Elements48------------------------4950- **Licensing**: Verify GPLv3/BSD-2-Clause compatibility for any new dependencies51- **Test scope**: Tests must exercise actual changed code, not just add random coverage52- **Changelog validation**: Fragment structure follows sections defined in `changelogs/config.yaml`5354Each step is tracked in TodoWrite for visibility and systematic completion. A review round should not exceed 20 feedback items.
Run npx skillmds@latest add gabrielmoreira/review-3 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Review It is listed under DevOps & Infra on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
gabrielmoreira (@gabrielmoreira) published this skill. Their other Agent Skills are listed on their SkillMD profile.
gabrielmoreira