# Review Code with Structured AI Feedback

Manual code review can miss bugs, style problems, and risky patterns when context is limited. This skill reviews provided code and returns prioritized issues, suggestions, a summary, and a quality score.

## Install

```bash
npx skillstore add enact examples/enactprotocol-examples-code-reviewer
```

## Metadata

- Status: approved
- Slug: enactprotocol-examples-code-reviewer
- Version: 1.0.0
- Author version: 1.0.0
- Skillstore revision: r1
- Version status: valid
- Tree hash: 1d900cffda5fde17569e9a41c5b939cbb1878bc6194f43f40db6794fd2d84cc8
- Author: Enact Examples
- GitHub username: EnactProtocol
- License: MIT
- Repository: https://github.com/EnactProtocol/enact/tree/main/examples/code-reviewer
- Ref: a06681402992ceae98ba04d54cfd4ab004862696
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands
- Quality score: 80
- Quality tier: silver
- Public page: https://skillstore.pages.dev/skills/enactprotocol-examples-code-reviewer
- Manifest: https://skillstore.pages.dev/api/skills/enactprotocol-examples-code-reviewer/manifest

## Capabilities

- Identifies likely bugs such as null pointer risks, off-by-one errors, race conditions, and logic mistakes.
- Reviews naming, organization, readability, and other style concerns in submitted code.
- Flags performance concerns such as inefficient algorithms, unnecessary allocations, and N\+1 query patterns.
- Checks for security risks such as injection vulnerabilities, hardcoded secrets, and unsafe operations.
- Returns issues with severity, line references, messages, suggestions, a summary, and a quality score.

## Use Cases

- Pre-Merge Review: Review a function or file before opening a pull request.
- Teaching Feedback: Show learners bugs, style issues, and safer alternatives in example code.
- Security-Focused Triage: Request a focused pass on risky code before deeper manual review.

## Prompt Templates

### Review a Snippet

```
Review this code for bugs, style, performance, and security. Language: [language]. Code: [paste code].
```

### Find Logic Bugs

```
Review this code with focus set to bugs. Identify runtime errors, logic mistakes, and missing edge case handling. Code: [paste code].
```

### Check Security Risk

```
Review this code with focus set to security. Look for injection, hardcoded secrets, unsafe operations, and missing validation. Code: [paste code].
```

### Review Critical Change

```
Perform a senior-level review of this change. Prioritize correctness, security, performance, and maintainability. Include severity, line references, suggestions, summary, and score. Context: [brief context]. Code: [paste code].
```

## Limitations

- Reviews only the code provided in the prompt; it does not scan repositories by itself.
- Does not execute code, run tests, or prove that suggested fixes are correct.
- Accuracy depends on the available context and the specified programming language.
- Should not replace expert review for high-risk production changes.

## Best Practices

- Include enough surrounding code and expected behavior for meaningful review.
- Set the focus field to bugs, style, performance, security, or all.
- Verify suggested fixes with tests and project-specific review standards.

## Anti Patterns

- Do not submit secrets, tokens, or production credentials for review.
- Do not rely on the quality score alone to approve changes.
- Do not review incomplete snippets without context when behavior matters.

## Security Audit

- Audited at: 2026-07-06T15:28:19.018\+00:00
- Summary: All eight static detections are false positives caused by Markdown inline code and fenced examples in SKILL.md. The skill is a read-only code review prompt; no evidence found for shell execution, reconnaissance behavior, network access, or prompt injection.

## Stats

- Views: 123
- Downloads: 12
- Favorites: 0
- Popularity score: 0