Evaluates Claude skills across security, quality, utility, and compliance. Used by operations teams to assess skill performance and compliance with organizational standards. Integrates with Python workflows and Claude agents.
git clone https://github.com/bjulius/skill-evaluator.gitskill-evaluator is a comprehensive toolkit for analyzing Claude skills across four dimensions: security (35% weight), quality (25%), utility (20%), and compliance (20%). It performs pattern-based vulnerability detection with context-aware analysis and generates detailed markdown reports with executive summaries and risk assessments. The tool runs locally via Python scripts with cross-platform support for Windows, macOS, and Linux. Operations teams use it to assess skill performance before publication and validate alignment with organizational standards. v1.2.2 is production-ready with a 96.9/100 self-evaluation score.
Install via pip install pyyaml, then run python scripts/evaluate_skill.py /path/to/skill to evaluate. Use --mode security for security-focused checks or --mode pre-publish for pre-publication reviews. Reports save to markdown with optional JSON output using -o flag.
Pre-publication security review before deploying skills to production
Compliance validation against organizational skill-creator guidelines
Automated assessment of third-party skills before internal adoption
Security-focused evaluation of skills in sensitive environments
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/bjulius/skill-evaluatorCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Evaluate the following Claude skill for [COMPANY] in the [INDUSTRY] sector. Assess it across security, quality, utility, and compliance. Provide a detailed report including strengths, weaknesses, and recommendations for improvement. The skill is designed to [PURPOSE]. Here is the skill prompt: [SKILL_PROMPT].
# Skill Evaluation Report ## Security - **Strengths**: The skill uses parameterized inputs to prevent injection attacks. - **Weaknesses**: No explicit data validation for user inputs. - **Recommendation**: Implement input sanitization and validation. ## Quality - **Strengths**: The skill provides clear and concise outputs. - **Weaknesses**: Limited error handling for edge cases. - **Recommendation**: Add comprehensive error handling and user feedback mechanisms. ## Utility - **Strengths**: The skill integrates seamlessly with existing Python workflows. - **Weaknesses**: Limited customization options for different user roles. - **Recommendation**: Add role-based customization features. ## Compliance - **Strengths**: The skill adheres to industry standards for data privacy. - **Weaknesses**: No explicit compliance checks for regulatory requirements. - **Recommendation**: Implement compliance checks and logging for regulatory adherence.
AI assistant built for thoughtful, nuanced conversation
Get more done every day with Microsoft Teams – powered by AI
Automate security compliance and monitor real-time security posture seamlessly.
Automate your spreadsheet tasks with AI power
Agentic AI Workflow platform
Connected workspace for docs, wikis, and projects
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan