agent-skills

This documentation library packages agents, instructions, and skills for UI, API, end-to-end, regression, accessibility, and flaky-test work. Teams can embed the material into projects using GitHub Copilot, Claude, Cursor, or similar assistants, with guidance for Playwright TypeScript, Selenium Java, and ISTQB-aligned planning. The repository is a knowledge base and has no build, lint, or test system of its own.

Inspect Evals gathers benchmarks for coding, cybersecurity, safeguards, reasoning, knowledge, and other model capabilities. Researchers can run individual tasks with Inspect AI, improve included evaluations, or register externally maintained implementations. The project recommends Python 3.11 or 3.12 for the most reliable development and execution experience.

Langfuse helps teams instrument LLM applications so they can inspect traces, sessions, retrieval steps, prompts, scores, and evaluations in one place. It also supports prompt versioning, datasets, playground experiments, and integrations with common SDKs and frameworks. You can use the hosted service or self-host with Docker Compose or Kubernetes. Self-hosted instances send basic usage telemetry by default, but it excludes raw traces and can be disabled.

MCP Inspector connects to servers over stdio, SSE, or Streamable HTTP and lets developers inspect tools, resources, prompts, and responses in a browser UI. Its CLI supports scripted checks and continuous integration, and server configurations can be exported for other clients. Because the local proxy can spawn processes and connect to specified servers, it should not be exposed to untrusted networks.