Review Ai Code Quality
Review AI-generated or recently changed code for common quality failures. Use when reviewing code, validating an implementation, checking "is this ready", auditing AI-authored changes, or looking for edge cases, validation gaps, error handling problems, duplication, and needless complexity. Produces prioritized findings and required fixes.
Install
$ agentstack add skill-ariaxhan-the-agent-library-review-ai-code-quality ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-ariaxhan-the-agent-library-review-ai-code-quality) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Review AI Code Quality
AI-authored code often looks plausible while missing boring safeguards. Review the boring safeguards first.
1. Identify the changed surface
Inspect the diff or target files. Determine:
- Inputs and trust boundaries
- External calls
- State mutations
- Error paths
- User-visible behavior
- Tests or checks that cover the change
2. Run the Big Five review
Input validation
Every external input should be parsed or validated at the boundary. Look for raw request bodies, unchecked params, untyped JSON, unsafe casts, and string-built queries.
Edge cases
Check null, empty arrays, empty strings, zero values, unicode, timeouts, large inputs, duplicate inputs, and missing optional fields.
Error handling
No empty catches. No swallowed errors on important paths. User-facing messages should be safe and logs should include context.
Duplication
Repeated logic in three or more places should usually become one helper. Two copies may be fine; do not abstract too early.
Complexity
Flag deeply nested conditionals, large functions, multi-purpose modules, and clever code with unclear invariants.
3. Check tests
Ask:
- Is the main success path covered?
- Are failure paths covered?
- Are edge cases covered?
- Do assertions check meaningful behavior?
- Would the test fail if the implementation were wrong?
High coverage with weak assertions is not quality.
4. Produce findings
For each finding:
- Severity
- File/location
- Problem
- Why it matters
- Concrete fix
- Suggested test, if relevant
Lead with blockers. Keep nits separate.
5. Verdict
End with:
- Ready / needs fixes / unsafe to ship
- Required fixes before merge
- Optional improvements
- Checks you could not run
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ariaxhan
- Source: ariaxhan/the-agent-library
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.