skill-testing

Playwright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.

Tests and scores any Agent Skill against the official anthropics/skills specification. Use this skill when you need to check if a skill repository or SKILL.md file is compliant with the Agent Skills standard, audit skill quality, get a compliance score, or receive specific improvement suggestions.

Test agent Skills, catch regressions, and improve with evidence. Evaluation CLI + MCP for Codex, Claude Code, and other agents; skilled-improve included.

Quality and trigger-evaluation gate for reusable AI agent skills.

Automated end-to-end testing for AI agent skills(agentskills.io). Launches Claude Code and Cursor as subprocesses, runs scenarios in real workspaces, and asserts what the model actually does.

B/O/E evaluation framework for SKILL.md-based LLM operating systems and agent hubs

Validate, pressure-test, and release-gate SKILL.md packages for OpenAI and portable agent runtimes.

Claude Code skill that tests if agents follow rules, checks tool order, and writes reports. Built on affaan-m/ECC by @affaan-m.

你的 Skill 到底有没有用？跑一次就知道——用真实任务做对照测试，看它在每个模型上是帮忙还是拖后腿。 | Measure whether a skill actually helps, per model, via paired with/without experiments and blind judge review.

Behavioral test harness for Claude Code skills — run a skill in an isolated fixture and assert on what it actually does

CLI runner for testing AI coding-agent Skills with sandboxed workspaces, deterministic assertions, provider adapters, and CI-ready reports.

A Claude Agent Skill validator for Claude Code: spec conformance, script testing, quality and security scoring, a Mermaid skill map, and per-skill token cost.

Test and validate OpenClaw skills locally before publishing to ClawHub — checks triggers, env vars, scripts, and SKILL.md completeness without needing a live agent. Zero dependencies.

Testing harness for AI agent skills and plugins — contract-driven YAML specs with mocked environments

Automated QA system for Claude Code skills. Discovers skills, generates tests, captures screenshots, scores quality (A-F grades), and publishes an interactive dashboard.

Agent Skill Infrastructure: quality check, behavior test runner, version awareness

Evergreen: self-maintaining skills, docs and codemaps for AI agents (research refresh, learnings, evals, git self-publishing)