/code-review
Systematic code review for bugs, security, style, and performance
$ npx -y skills add vstorm-co/pydantic-deepagents --skill code-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/code-review
Context preview
The summary Claude sees to decide when to auto-load this skill.
Systematic code review for bugs, security, style, and performance
SKILL.md
code-review.SKILL.mdname: code-review description: "Systematic code review for bugs, security, style, and performance" tags: [code-quality, review] version: "1.0.0"
Code Review
Perform a systematic code review covering these categories:
Review Checklist
1. Correctness
- Logic errors, off-by-one, null/None handling
- Edge cases: empty inputs, large inputs, concurrent access
- Error handling: are exceptions caught and handled properly?
2. Security
- Input validation and sanitization
- SQL injection, XSS, command injection
- Secrets in code, hardcoded credentials
- Authentication and authorization checks
3. Performance
- Unnecessary loops, N+1 queries
- Missing indexes for database queries
- Large memory allocations, unbounded collections
- Blocking calls in async code
4. Style & Maintainability
- Naming clarity (variables, functions, classes)
- Function length — split if >30 lines
- Dead code, commented-out code
- Missing type annotations
5. Testing
- Are new code paths covered by tests?
- Are edge cases tested?
- Are error paths tested?
Output Format
For each issue found:
- **File:line** — category — description — suggested fix
- Severity: critical / warning / suggestion
Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.
Repo: vstorm-co/pydantic-deepagents
Other skills on pydantic-deepagents.
- /build-and-compile
Building, compiling, and resolving dependency issues across languages
Open skill - /data-formats
Working with diverse data formats: binary, text, structured, and custom
Open skill - /environment-discovery
Systematic exploration of unknown environments before starting work
Open skill - /git-workflow
Git operations: commits, branches, PRs, and conflict resolution
Open skill - /performant-code
Writing efficient code that handles large data and tight constraints
Open skill - /refactor
Refactor code to improve structure and maintainability
Open skill

