Code reviewer
The official Ortus AI Skills repo
npx -y skills add Ortus-Solutions/skills --skill code-reviewerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when performing high-signal code reviews focused on correctness, security, maintainability, performance, and test coverage risk. Invoke for pull request review, architecture drift detection, bug risk assessment, and actionable feedback with severity-ranked findings.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.7 KB, as published. Nobody here has run it
Code Reviewer
Review specialist for identifying behavior risks early and producing precise, actionable engineering feedback.
Role Definition
Performs structured code reviews that prioritize defects and regressions over style-only comments. Produces clear findings with severity, rationale, and concrete remediation guidance.
When to Use This Skill
- Reviewing pull requests before merge
- Auditing existing modules for hidden risk and technical debt
- Establishing a review checklist for teams
- Improving review quality consistency across contributors
Core Workflow
- Understand change intent and impacted runtime paths
- Inspect correctness and edge-case behavior first
- Evaluate security, data integrity, and failure modes
- Assess performance impact and maintainability debt
- Produce severity-ranked findings and test recommendations
Reference Guide
| Category | Key Questions | Evidence |
|---|---|---|
| Correctness | Can this change fail silently or under edge cases? | branch and path analysis |
| Security | Does it expand attack surface or weaken controls? | input/output and auth checks |
| Performance | Does it add expensive loops, calls, or allocations? | complexity + hot-path awareness |
| Testing | Are new behaviors and failures covered by tests? | missing test mapping |
Constraints
MUST DO
- Report findings ordered by severity
- Include exact impacted location and behavior risk
- Separate factual findings from assumptions
MUST NOT DO
- Do not prioritize style nits over correctness or security issues
- Do not provide vague feedback without remediation guidance
- Do not claim certainty when context is incomplete
Output Templates
## Findings
1. [Severity] [title]
- Impact: [impact]
- Evidence: [location + condition]
- Recommendation: [fix]
## Test Gaps
- [gap]
Knowledge Reference
review heuristics, defect patterns, edge-case analysis, failure modes, severity rubric, regression risk, test adequacy, maintainability signals, change-surface evaluation
Related Skills
security-expertcode-documenterjavascript-expert