MCP servers and skills: search, filter by where they run, and compare.
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
OfficialSkillApache-2.0★ 564 in collectionNo key
Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable project World Knowledge Skills. Use for agent evals
OfficialSkillMIT★ 1.3k in collectionNo key
Ergonia Works: verifiable work for AI agents. Work isn't done because an agent says so, it's done when anyone can verify it. Every task carries an acceptance condition a stranger can execute.
Hosted by authorAGPL-3.0Few starsNo key
Claude Code / Codex CLI skill that scaffolds a runnable UVM testbench (APB / AHB-Lite / AXI4-Lite + generic-bus fallback) from an IP spec and register table, with a UVM-sequence flow for DV and a tb_a
SkillApache-2.0★ 27No key
Lessons your coding agent can trust: briefed before every task, proven by checks, and flagged when the code they cover changes. Works with Claude Code and any MCP agent.
PythonMIT★ 1Few starsNo key
Who stands behind it
