skill tester

Security Community

Skill notes

Description

The Skill Tester is a comprehensive meta-skill designed to validate, test, and score the quality of skills within the claude-skills ecosystem. This powerful quality assurance tool ensures that all skills meet the rigorous standards required for BASIC, STANDARD, and POWERFUL tier classifications through automated validation, testing, and scoring mechanisms. As the gatekeeping system for skill quality, this meta-skill provides three core capabilities:

Comprehensive Skill Validation

Structure Compliance: Validates directory structure, required files (SKILL.md, README.md, scripts/, references/, assets/, expected_outputs/) Documentation Standards: Checks SKILL.md frontmatter, section completeness, minimum line counts per tier File Format Validation: Ensures proper Markdown formatting, YAML frontmatter syntax, and file naming conventions

Advanced Script Testing

Syntax Validation: Compiles Python scripts to detect syntax errors before execution Import Analysis: Enforces standard library only policy, identifies external dependencies Runtime Testing: Executes scripts with sample data, validates argparse implementation, tests --help functionality Output Format Compliance: Verifies dual output support (JSON + human-readable), proper error handling

Multi-Dimensional Quality Scoring

Documentation Quality (25%): SKILL.md depth and completeness, README clarity, reference documentation quality Code Quality (25%): Script complexity, error handling robustness, output format consistency, maintainability Completeness (25%): Required directory presence, sample data adequacy, expected output verification Usability (25%): Example clarity, argparse help text quality, installation simplicity, user experience

Tier Classification System

Automatically classifies skills based on complexity and functionality: BASIC Tier Requirements Minimum 100 lines in SKILL.md At least 1 Python script (100-300 LOC) Basic argparse implementation

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Security
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@alirezarezvani · no license declared
Token usage
Lean
Setup complexity
Guided setup
External API key
Not required
Operating systems
Linux
Runtime requirements
Python
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
Network behavior
Local-only
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

Output preview skill-tester.preview
# Dual Output Support

=== SKILL VALIDATION REPORT ===
Skill: engineering/example-skill
Tier: STANDARD
Overall Score: 85/100 (B)

Structure Validation: ✓ PASS
├─ SKILL.md: ✓ EXISTS (247 lines)
├─ README.md: ✓ EXISTS  
├─ scripts/: ✓ EXISTS (2 files)
└─ references/: ⚠ MISSING (recommended)

Documentation Quality: 22/25 (88%)
Code Quality: 20/25 (80%)
Completeness: 18/25 (72%)
Usability: 21/25 (84%)

Recommendations:
• Add references/ directory with documentation
• Improve error handling in main.py
• Include more comprehensive examples

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.