# 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.

- **Type:** Skill
- **Install:** `agentstack add skill-ariaxhan-the-agent-library-review-ai-code-quality`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ariaxhan](https://agentstack.voostack.com/s/ariaxhan)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ariaxhan](https://github.com/ariaxhan)
- **Source:** https://github.com/ariaxhan/the-agent-library/tree/main/code-engineering/review-ai-code-quality

## Install

```sh
agentstack add skill-ariaxhan-the-agent-library-review-ai-code-quality
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## 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](https://github.com/ariaxhan)
- **Source:** [ariaxhan/the-agent-library](https://github.com/ariaxhan/the-agent-library)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ariaxhan-the-agent-library-review-ai-code-quality
- Seller: https://agentstack.voostack.com/s/ariaxhan
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.