Agent skill · software engineering · alirezarezvani
skill-tester
Use when authoring or auditing a skill in this ecosystem, before release. Validates structure with skill_validator.py, runs its scripts with script_tester.py and grades quality and security with quality_scorer.py and security_scorer.py.
Why this skill is useful
Adds 4 executable scripts for validating, testing, and scoring skills that enhance the quality assurance process in the claude-skills ecosystem.
What it needs
Requires python3 installed locally. About 2k tokens when loaded. Last updated 2026-08-05. 23,939 stars on the source repository.
What this skill does
Skill Tester Tier: POWERFUL · Category: Engineering Quality Assurance · Dependencies: None (Python stdlib only) Meta-skill that validates, tests, and scores skills in this repository. Four tools, run from the repo root with full paths: 1. scripts/skillvalidator.py — structure + documentation compliance 2. scripts/scripttester.py — Python script syntax/imports/runtime/output testing 3. scripts/qualityscorer.py — multi-dimensional scoring with letter grade 4. scripts/securityscorer.py — security posture scoring (also available via qualityscorer.py --include-security) Scope note: this skill's tier line-count minimums measure legacy skills. For authoring new skills, engineering/write-a-skill (SKILL.md under ~100 lines, Matt Pocock doctrine) is the binding standard — do not pad a new skill to satisfy a tier minimum here. Quick Start (exact, runnable from repo root) Consume the JSON: validator emits overallscore, compliancelevel, per-check checks{}; scorer emits overallscore, lettergrade, tierrecommendation, dimensions, and an improvementroadmap — work the roadmap top-down, then re-run until the target score is met. For repo-wide auditing prefer scripts/auditskills.py at the repo root (wraps the write-a-skill checklist runner across all skills). …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills alirezarezvani/skill-tester--60c8a7