はてなブックマーク - GitHub - darkrishabh/agent-skills-eval: A test runner for agentskills.io-style AI agent skills
https://b.hatena.ne.jp/entry/s/github.com/darkrishabh/agent-skills-eval
Agent Skills — the open standard from Anthropic for giving agents domain knowledge — make it easy to ship a SKILL.md and assume your agent is now better at the task. The hard part is proving it. ag...kkeisuke
https://b.hatena.ne.jp/kkeisuke/20260507#bookmark-4787004892478953602
2026-05-07T14:14:10Z