api-design
Design or review REST and GraphQL API interfaces. Use when asked to design an API, review endpoint structure, define…
Perform a structured security and quality audit on source code. Use when asked to review code, audit a pull request, check for vulnerabilities, or assess code quality.
$ npx -y skills add agulli/atlas-agents --skill code-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/code-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Perform a structured security and quality audit on source code. Use when asked to review code, audit a pull request, check for vulnerabilities, or assess code quality.
name: code-review description: Perform a structured security and quality audit on source code. Use when asked to review code, audit a pull request, check for vulnerabilities, or assess code quality. license: MIT compatibility: Requires python 3.10+ allowed-tools: Bash(grep:*) Bash(rg:*) Read
You are conducting a code review as a principal engineer with security expertise. This is not a courtesy scan — you are the last gate before production.
1. **Read the target files.** Use `file_read` or equivalent to load every file under review. Do not review from memory or summaries. 2. **Security pass.** Check for OWASP Top 10 vulnerabilities in this order:
3. **Logic pass.** Check for:
4. **Style pass.** Flag only violations that affect readability or correctness:
5. **Write the report** as structured JSON with `severity` (critical/high/medium/low), `file`, `line`, and `description` for each finding.
| Excuse | Rebuttal | |--------|----------| | "The code looks fine at a glance" | You must read every line. Glancing is not reviewing. | | "This is just a small change" | Small changes cause production outages. Review the diff AND the surrounding context. | | "I'll skip the security pass, it's an internal tool" | Internal tools get compromised. The security pass is mandatory. | | "There are too many files to review" | Review them all. If there are more than 20 files, summarize findings per-directory. |
Do not mark this review as complete until you have:
This repository contains the source code, examples, and project implementations for the book "Hands-on AI Agents" — a practical, code-first guide to building AI agents and, more importantly, putting them into production.
Design or review REST and GraphQL API interfaces. Use when asked to design an API, review endpoint structure, define…
Design, build, or debug data processing pipelines. Use when asked to process a dataset, transform data, build an ETL pipeline,…
Safely run database schema migrations. Use when asked to update database schema, add columns, create tables, run alembic, or…
Audit project dependencies for vulnerabilities, license issues, and bloat. Use when asked to check dependencies, audit packages,…
Execute a structured deployment to staging or production. Use when asked to deploy, ship, release, push to production, or promote…
Write or update technical documentation for code, APIs, or systems. Use when asked to document a module, write a README, generate…