- name
- code-review
- description
- Review code for correctness, security, performance, and maintainability.
- metadata
- author
- RedHat Dev
- version
- 1.0.0
- owner
- RedHat Dev Agent
- category
- core
SKILL: code-review
Purpose
Analyze code (or a diff) to detect bugs, security issues, performance problems, and maintainability risks, then propose concrete improvements.
When to Use
- Reviewing a PR/diff before merging.
- A bug is suspected but not yet reproduced.
- Hardening/security pass is requested.
Inputs
scope(required, string): files, diff, or code snippet to review.intent(optional, string): what the code is supposed to do.constraints(optional, string[]): security/perf/compat constraints.risk_tolerance(optional, enum:low|medium|high).
Steps
- Identify entrypoints, invariants, and trust boundaries.
- Check correctness:
- edge cases - error handling - concurrency/races (if applicable)
- Check security:
- input validation - authz/authn - secrets handling - injection risks
- Check performance and resource usage:
- hotspots - unbounded loops/data growth
- Check maintainability:
- naming - duplication - test coverage gaps
- Produce a prioritized, actionable report.
Validation
- Findings include concrete evidence (line references, behavior, or reproducible scenario).
- Suggestions are compatible with stated constraints.
- Distinguish “must-fix†from “nice-to-haveâ€.
Output
Review report (example schema):
summary: "<1 paragraph>"
findings:
- id: "CR-001"
severity: "high|medium|low"
category: "bug|security|perf|maintainability"
issue: "<what>"
impact: "<why it matters>"
recommendation: "<how to fix>"Safety Rules
- Do not claim vulnerabilities without evidence.
- Do not recommend unsafe patterns (e.g., disabling validation to “make it workâ€).
- Prefer minimal, targeted fixes.
Example
Input:
scope: “diff for auth middlewareâ€
Output:
- findings include missing
audiencecheck on JWTs and a failing negative test case.