Metadata-Version: 2.5
Name: skill-qa
Version: 1.0.2
Summary: A universal quality evaluation, benchmarking and regression framework for Agent Skills
License: Apache-2.0
License-File: LICENSE
Keywords: agent,benchmark,ci,evaluation,quality,regression,skills
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Quality Assurance
Classifier: Topic :: Software Development :: Testing
Requires-Python: >=3.10
Requires-Dist: jsonschema>=4.18
Requires-Dist: packaging>=23.0
Requires-Dist: pydantic>=2.0
Requires-Dist: pyyaml>=6.0
Requires-Dist: rich>=13.0
Requires-Dist: typer>=0.12
Provides-Extra: dev
Requires-Dist: build>=1.2; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Requires-Dist: ruff>=0.6; extra == 'dev'
Provides-Extra: llm
Description-Content-Type: text/markdown

# skill-qa

A universal quality evaluation, benchmarking and regression framework for Agent Skills.

## What it does

- Runs static quality checks for Agent Skill packages.
- Executes deterministic EvalCases through pluggable engines.
- Compares with-skill and without-skill benchmark results.
- Detects regressions against an explicit baseline.
- Produces CI-friendly reports and exit codes.

## Install

```bash
pip install skill-qa
```

## Quick Start

```bash
skill-qa init
skill-qa check
skill-qa eval --engine noop --format json
skill-qa benchmark --engine noop --format json
skill-qa regression --engine noop --format json
skill-qa test --ci --format junit
```

Commands that need the default `skill-qa.yaml` will create it automatically when it is missing.

LLM-backed judging is opt-in and only runs when you configure an adapter that needs it.
