agentsclimarketplace

Code review

Skill Triippz/ai-jesus-team/skills/code-review

Triggered when running architecture, code quality, and security review on code changesFrom its SKILL.md

Install
npx -y skills add Triippz/ai-jesus-team --skill code-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.0 KB, as published. Nobody here has run it

Code Review Skill

Dispatch three review agents in parallel for comprehensive code review.

Skill Type: Rigid — All three reviews run, even if one finds nothing.

Process

1. Identify Scope

  • What files/changes are being reviewed?
  • If reviewing a branch: git diff main...HEAD (or appropriate base branch)
  • If reviewing specific files: read those files
  • Collect the full list of changed files

2. Launch Review Agents (In Parallel)

Launch all three agents simultaneously:

Agent 1: Architecture Review (arch-reviewer)

  • Module boundary compliance
  • Dependency direction
  • Separation of concerns
  • Circular dependencies
  • Abstraction appropriateness

Agent 2: Code Quality Review (code-reviewer)

  • SOLID principles
  • DRY violations (3+ occurrences)
  • KISS compliance
  • Naming clarity
  • Function size and nesting depth
  • Magic literals
  • Dead code
  • Error handling

Agent 3: Security Review (security-auditor)

  • OWASP top 10
  • Hardcoded secrets
  • Injection vulnerabilities
  • Input validation
  • Sensitive data exposure
  • Insecure dependencies

3. Collect and Deduplicate

  • Gather findings from all three agents
  • Remove duplicates (same issue flagged by multiple agents)
  • Merge related findings into single items

4. Categorize and Present

Present findings in priority order:

Must Fix

Issues that will cause problems if merged:

  • Security vulnerabilities
  • Broken architecture boundaries
  • Bugs or incorrect behavior
  • Silent error swallowing

Should Fix

Issues that degrade quality:

  • DRY violations
  • Unclear naming
  • Missing error handling
  • Leaky abstractions

Consider

Suggestions for improvement:

  • Style preferences
  • Optional refactoring
  • Performance improvements
  • Better patterns available

5. Summary

  • Total findings by category
  • Overall assessment: Ready to merge / Needs work / Major issues
  • Specific action items for the developer

Keep looking

Skills are one crate of 608,475. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.