Skill Quality Suite — Security skill for Claude Code

skill-quality-suite

[](https://github.com/letsloose501/skill-quality-suite/actions/workflows/quality.yml) [](LICENSE) [](https://github.com/letsloose501/skill-quality-suite/actions/workflows/quality.yml) [](#install) [](https://skills.sh/letsloose501/skill-quality-suite) [](https://github.com/marketplace/actions/skill-quality-suite)

**A quality, linting, security and validation toolkit for AI Agent Skills.** It validates a `SKILL.md` against the [Agent Skills specification](https://agentskills.io/specification), lints the instructions an agent will actually follow, scans a skill for secrets and prompt injection before you install it, checks whether it will work on another agent, and measures whether it improves the agent's work at all.

No dependencies: the static half is Python standard library only, offline and deterministic. The evaluation half runs an agent, costs money, and never runs unless you name it.

python scripts/sqs.py check    ./my-skill                # skill lint: the everyday five
python scripts/sqs.py security ./my-skill                # before you install a stranger's skill
python scripts/sqs.py compat   ./my-skill --harness all  # will it work anywhere else
python scripts/sqs.py eval     ./my-skill --trigger      # does it actually fire
python scripts/sqs.py explain  ST008                     # what a finding means, and the fix

Use it when:

• a skill does not fire, fires on a neighbour's work, or half-works and silently skips s