# Review

> Review all uncommitted changes against project standards before committing

- **Type:** Skill
- **Install:** `agentstack add skill-smartwhale8-claude-playbook-review`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [smartwhale8](https://agentstack.voostack.com/s/smartwhale8)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [smartwhale8](https://github.com/smartwhale8)
- **Source:** https://github.com/smartwhale8/claude-playbook/tree/main/.claude/skills/review

## Install

```sh
agentstack add skill-smartwhale8-claude-playbook-review
```

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

## About

Review all uncommitted changes in this project. $ARGUMENTS

## Process

1. **Gather changes**: Run `git diff --staged` for staged changes, or `git diff` if nothing is staged. Also check `git status` for new untracked files.

2. **Check each changed file against the project rules** (`.claude/rules/*.md`):

   ### Code Quality
   - Is there dead code, unused imports, or commented-out code?
   - Are there bandaid fixes or workarounds instead of root-cause solutions?
   - Is anything over-engineered for what it needs to do?

   ### Architecture
   - Does this follow existing patterns in the codebase?
   - Is there duplicate logic that should use an existing shared component or utility?
   - Are dependencies pointing in the right direction (inward, not outward)?

   ### Consistency
   - Does the code match the style and structure of similar files in the project?
   - For frontend: are spacing, colors, and component usage consistent with the rest of the UI?
   - For backend: are error handling, response format, and validation patterns consistent?

   ### Reuse
   - Could any new component, function, or pattern already exist in the codebase? Search before approving.
   - If something similar exists, flag it — it should be reused or extracted into a shared utility.

   ### Security
   - Any hardcoded secrets, credentials, or API keys?
   - Is user input validated at the boundary?
   - Are there SQL injection, XSS, or other OWASP risks?

   ### Performance
   - Any N+1 query patterns (database calls inside loops)?
   - Any unbounded queries missing LIMIT/pagination?
   - Frontend: unnecessary re-renders, missing debounce on inputs?

3. **Verdict**: Provide one of:
   - **Ready to commit** — no issues found
   - **Minor issues** — list them, but committing is acceptable after acknowledging
   - **Needs changes** — list specific issues that must be fixed before committing

For each issue, provide: the file, the line(s), what's wrong, and what the fix should be.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [smartwhale8](https://github.com/smartwhale8)
- **Source:** [smartwhale8/claude-playbook](https://github.com/smartwhale8/claude-playbook)
- **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-smartwhale8-claude-playbook-review
- Seller: https://agentstack.voostack.com/s/smartwhale8
- 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%.