Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Corrige rutas de reglas de "rules/*.md" a "references/*.md" en la sección de Detección de Lenguaje y Reglas. - No hay cambios en la funcionalidad o el formato de revisión; solo actualizaciones en las rutas de los archivos de referencia.
What This Skill Does
Automated code reviewer for Bitbucket Pull Requests. Analyzes diffs for syntax errors, security vulnerabilities, bad practices, and team convention violations across JavaScript, TypeScript, Node.js, PHP, and Python. Each finding is classified by severity and paired with a suggested fix.
It replaces running separate linters, security scanners, and manual review checklists by producing a single structured report with per-line corrections and a final merge verdict.
When to use it
- Catching SQL injection before a PHP PR merges to main
- Enforcing TypeScript naming conventions on a shared codebase
- Reviewing a Node.js API change for insecure dependency usage
- Getting a structured approve/reject verdict on a feature branch
- Identifying dead code and console.log leftovers before code review
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Review this PR diff for my Node.js API refactor
- 1Reads the full diff before commenting
- 2Detects file extensions and maps each to the relevant rule sets
- 3Classifies each finding as BLOCKER, WARNING, SUGGESTION, or NIT
- 4Generates per-file comments showing the problematic code and the corrected version
- 5Produces a final verdict with a summary of what must change before merge
Structured review report: 2 BLOCKER (hardcoded credentials, missing input validation), 3 WARNING (callback error not handled, var used instead of const), 1 NIT (inconsistent semicolons). Verdict: RECHAZAR.