Skill Analyzer - Comprehensive Skill Analysis Tool
name: skill-analyzer
by codeblackhole1024 · published 2026-03-22
$ claw add gh:codeblackhole1024/codeblackhole1024-skill-analyzer---
name: skill-analyzer
description: Quality scanner for OpenClaw skills. Evaluates functionality, security, usability, documentation, and best practices with weighted scoring. Use when: (1) Analyzing skill quality before publishing, (2) Finding improvement opportunities, (3) Security review of third-party skills. Pure Python - no dependencies.
---
# Skill Analyzer - Comprehensive Skill Analysis Tool
Overview
Skill Analyzer evaluates OpenClaw skills across 5 dimensions to provide a comprehensive quality assessment. It helps identify strengths, weaknesses, and improvement opportunities. Built with pure Python - no external dependencies required.
Analysis Dimensions (5 total)
1. Functionality Analysis (25%)
2. Security Analysis (25%)
3. Usability Analysis (20%)
4. Documentation Quality (15%)
5. Best Practices (15%)
Usage
Requirements
Analyze a Skill
# Analyze a local skill
python3 scripts/analyzer.py --path /path/to/skill
# Analyze with detailed output
python3 analyzer.py --path /path/to/skill --verbose
# Output to JSON
python3 analyzer.py --path /path/to/skill --output report.json
# Compare two skills
python3 analyzer.py --compare skill1 skill2Dimensions Scoring
Each dimension is scored 0-10:
Example Output
==========================================
Skill Analysis Report: example-skill
==========================================
Overall Score: 7.5/10
Dimension Scores:
Functionality: 8/10 ████████░░
Security: 9/10 █████████░
Usability: 7/10 ███████░░░
Documentation: 6/10 ██████░░░░
Best Practices: 7/10 ███████░░░
Strengths:
✓ Good security practices
✓ Clean code structure
✓ Proper error handling
Risk Level: LOWNotes
More tools from the same signal band
Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).
Sign plugins, rotate agent credentials without losing identity, and publicly attest to plugin behavior with verifiable claims and authenticated transfers.
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your...