AI Agent Skill HUB

Self-Review Skill

Run this skill before committing to catch issues early. It runs linting, structural tests, and verifies no debug artifacts remain.

14 stars
byextractumio
View on GitHubInstallation ↓

Best use case

Self-Review Skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Run this skill before committing to catch issues early. It runs linting, structural tests, and verifies no debug artifacts remain.

Teams using Self-Review Skill should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/self-review/SKILL.md --create-dirs "https://raw.githubusercontent.com/extractumio/ag3ntum/main/.claude/skills/self-review/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/self-review/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How Self-Review Skill Compares

Feature / AgentSelf-Review SkillStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Run this skill before committing to catch issues early. It runs linting, structural tests, and verifies no debug artifacts remain.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

AI Agents for Coding

Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.

SKILL.md Source

# Self-Review Skill

Run this skill before committing to catch issues early. It runs linting, structural tests, and verifies no debug artifacts remain.

## Steps

1. **Run linters**: Execute `./run.sh lint` and review any failures
2. **Check for debug artifacts**: Search modified files for:
   - `console.log` (frontend)
   - `print(` without `# noqa: print-ok` (backend)
   - `debugger` statements
   - `TODO` or `FIXME` comments added in this session
   - Commented-out code blocks
3. **Verify imports**: Ensure no unused imports were added
4. **Run structural tests**: `python3 -m pytest tests/structural/ -v`
5. **Review modified files**: Re-read each modified file and verify:
   - Changes match the intent of the task
   - No unintended side effects
   - Error handling is appropriate
6. **Report**: Summarize findings. If all checks pass, indicate ready to commit.

## When to Use

- Before every commit
- After implementing a feature or fix
- After refactoring

Related Skills

We are still matching the closest adjacent skills for this page. In the meantime, continue through the full directory.