fstrent-code-reviewer
Skill1 starsChanged 13 months agoMITView on GitHub
Comprehensive code review following company standards with focus on security, performance, maintainability, and best practices
In this repository40 other files it gives its agents.
- agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/always.mdcCursor rule
- .cursor/rules/atlassian/atlassian_integration.mdcCursor rule
- .cursor/rules/computer_use/computer_use_agent.mdcCursor rule
- .cursor/rules/documentation.mdcCursor rule
- .cursor/rules/fstrent_spec_tasks/claude_code_cli.mdcCursor rule
- .cursor/rules/github/github_integration.mdcCursor rule
- .cursor/rules/powershell.mdcCursor rule
- .cursor/rules/silicon_valley_personality.mdcCursor rule
- .cursor/rules/virtual_environments_python.mdCursor rule
- .cursor/rules/web_tools/web_tools.mdcCursor rule
- artifacts-builderSkill
- atlassian-integrationSkill
- claude-code-cli-integrationSkill
- computer-use-agentSkill
- deep-researchSkill
- fstrent-planningSkill
- fstrent-qaSkill
- fstrent-task-managementSkill
- github-integrationSkill
- hanx-database-toolsSkill
- hanx-knowledge-baseSkill
- hanx-mediawikiSkill
- hanx-youtube-researcherSkill
- internal-commsSkill
- mcp-builderSkill
- oracle-apex-developmentSkill
- patent-filing-aiSkill
- Project SetupSkill
- research-methodologySkill
- skill-creatorSkill
- startup-business-formationSkill
- startup-product-developmentSkill
- startup-resource-accessSkill
- startup-vc-fundraisingSkill
- template-skillSkill
- web-toolsSkill
- youtube-rag-storageSkill
- youtube-video-analysisSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
Ask for a code review
- Distinctive: line 30
Check code before committing
- Distinctive: line 154
fstrent-task-management: Create tasks for review findings
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
fstrent Code Reviewer
Perform thorough code reviews following company-specific templates, security guidelines, and best practices.
Overview
This skill provides comprehensive code review capabilities with structured checklists, security scanning, performance analysis, and maintainability assessments. It ensures consistent code quality across your projects by following standardized review procedures.
When to Use
This skill activates automatically when you:
- Ask for a code review
- Request security scanning
- Need quality assessment
- Review pull requests
- Check code before committing
Capabilities
1. Security Review
- SQL injection vulnerability detection
- XSS attack vector identification
- Authentication/authorization checks
- Sensitive data exposure prevention
- Input validation review
- Secret/credential detection
2. Code Quality Assessment
- Code style compliance
- Naming conventions
- Documentation completeness
- Error handling patterns
- Code complexity analysis
- DRY principle adherence
3. Performance Analysis
- Algorithm efficiency
- Database query optimization
- Memory usage patterns
- Network request efficiency
- Caching opportunities
- Resource cleanup
4. Maintainability Review
- Code organization
- Function/class size (target: <100 lines, warn: >200 lines)
- Cyclomatic complexity
- Test coverage
- Documentation quality
- Technical debt identification
5. Best Practices
- Language-specific idioms
- Framework conventions
- Design patterns
- SOLID principles
- Clean code principles
- Team coding standards
Review Types
Quick Review
For small changes (<100 lines):
- Security scan
- Style check
- Basic quality assessment
- ~2-5 minutes
Standard Review
For typical changes (100-500 lines):
- Full security scan
- Code quality analysis
- Performance check
- Documentation review
- ~10-20 minutes
Comprehensive Review
For large changes (>500 lines) or critical code:
- In-depth security analysis
- Detailed performance profiling
- Architecture review
- Test coverage analysis
- Technical debt assessment
- ~30-60 minutes
Output Format
Reviews generate:
- Summary: Overall assessment (Approve/Request Changes/Comment)
- Security Issues: Critical/High/Medium/Low with recommendations
- Quality Issues: Categorized by severity
- Performance Concerns: Identified bottlenecks
- Best Practices: Suggestions for improvement
- Action Items: Specific tasks to address findings
Integration
Works with:
- GitHub Pull Requests
- GitLab Merge Requests
- Local file reviews
- Diff-based reviews
- Multi-file reviews
Examples
Quick Review:
"Review this authentication function for security issues"
→ Focused security scan with recommendationsFull PR Review:
"Review PR #123 for code quality and security"
→ Comprehensive review with checklist and ratingsPre-Commit Check:
"Check this code before I commit"
→ Quick scan for obvious issuesCompany Standards
This skill enforces your specific:
- Coding standards
- Security requirements
- Testing requirements
- Documentation standards
- Performance SLAs
For detailed review procedures, see rules.md.
For examples and templates, see examples/ folder.
Related Skills
- fstrent-task-management: Create tasks for review findings
- fstrent-qa: Track bugs found during review
- fstrent-planning: Plan refactoring based on review
Version: 1.0.0 Last Updated: 2025-10-19 Part of: fstrent-spec-tasks system
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

