
w-coderabbit
Fetch CodeRabbit review comments, apply authorized fixes, and stop at local verification.
- Installs
- 647
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/blockmatic/basilic-skills --skill w-coderabbit- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads w-coderabbit automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Fetch CodeRabbit comments for the current PR or uncommitted diff. Apply high-confidence fixes. Follow git publish. Do not commit unless asked.
- Identify the branch and PR with
gh. If there is no PR, review the current task diff. - Fetch CodeRabbit comments via the available CodeRabbit MCP. Spawn read-only grouping by file and severity when threads span several files.
- Fix root causes starting with critical/high. Follow repository rules. Run the repo lint/type/w-test commands that match the change.
- Leave style-only or unclear items as a list. Do not invent security or quality bars.
- Docs:
/w-docsif behavior or commands changed.
FAQ
What does the w-coderabbit skill do?
Fetch CodeRabbit review comments, apply authorized fixes, and stop at local verification.
How do I install w-coderabbit?
Run npx skills add https://github.com/blockmatic/basilic-skills --skill w-coderabbit in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/w-coderabbit/ (personal) or .claude/skills/w-coderabbit/ (project).
Which AI agents can use w-coderabbit?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is w-coderabbit safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains w-coderabbit?
It is published by blockmatic in blockmatic/basilic-skills. It has 647 recorded installs.
More from blockmatic/basilic-skills
workflow
blockmatic/basilic-skills
Basilic /w- playbooks packed so install lands at .agents/skills/workflow/w-plan and the rest.
w-review-plan
blockmatic/basilic-skills
Review a plan's Goals, Assumptions, Tasks, Risks, and References.
w-api-test
blockmatic/basilic-skills
Add API tests that exercise public HTTP behavior against existing harnesses.
w-git-repair
blockmatic/basilic-skills
Resolve common Git problems and conflicts with inspected commands.
w-perf
blockmatic/basilic-skills
Measure bottlenecks with repository tools, then recommend or apply evidenced optimizations.
w-architecture
blockmatic/basilic-skills
Plan an implementation structure; durable decisions belong in ADRs and architecture docs.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.