50ae997ab4
* chore(deps): add yaml package for skill parsing Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat(agent): add skills system Implement a skills system inspired by moltbot's approach: - Skills are markdown files (SKILL.md) with YAML frontmatter - Multi-source loading with precedence: bundled < user < workspace - Eligibility filtering based on platform, binaries, and env vars - Skills are automatically included in agent system prompt - New AgentOptions: enableSkills, skillsBaseDir, extraSkillDirs Includes two bundled skills: - commit: Git commit helper with conventional commit guidelines - code-review: Code review checklist and best practices Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * refactor(skills): use profile-based skills instead of workspace Change skill loading from workspace-based (.skills/) to profile-based: - Skills now load from ~/.super-multica/agent-profiles/<profileId>/skills/ - Remove workspace and user skill sources - Simplify to only bundled and profile sources - Profile skills have higher precedence than bundled This is more appropriate for non-coding agents where skills are associated with agent identity rather than working directory. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
1.8 KiB
1.8 KiB
| name | description | version | metadata | |||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Code Review | Review code for bugs, security issues, and best practices | 1.0.0 |
|
Instructions
When the user asks you to review code, follow these guidelines:
Review Checklist
-
Correctness
- Does the code do what it's supposed to do?
- Are there any logic errors?
- Are edge cases handled?
-
Security
- Input validation and sanitization
- SQL injection vulnerabilities
- XSS vulnerabilities
- Command injection
- Path traversal
- Sensitive data exposure
- Authentication/authorization issues
-
Code Quality
- Is the code readable and maintainable?
- Are variable/function names descriptive?
- Is there unnecessary complexity?
- Are there code duplications?
-
Performance
- Are there obvious performance issues?
- N+1 queries
- Unnecessary loops or computations
- Memory leaks
-
Error Handling
- Are errors properly caught and handled?
- Are error messages helpful?
- Is there proper logging?
-
Testing
- Are there tests for the new code?
- Do the tests cover edge cases?
Review Format
Structure your review as follows:
## Summary
[Brief overview of what the code does and overall assessment]
## Critical Issues
[Must-fix issues: bugs, security vulnerabilities]
## Suggestions
[Improvements and best practices recommendations]
## Questions
[Clarifications needed about intent or design decisions]
## Positive Aspects
[Good practices observed in the code]
Guidelines
- Be constructive, not critical
- Explain the "why" behind suggestions
- Provide concrete examples for improvements
- Prioritize issues by severity
- Acknowledge good practices