lizhiyao
UserOMK — Evidence-backed evaluation and observability for prompts, RAG, skills, agents, and workflows. Native Codex, Claude Code, and DeepSeek Harness support.
Categories
Indexed Skills (5)
release-readiness
Release readiness reviewer that turns a skill folder into a visible Skill Map.
omk
OMK（Observe. Measure. Know.）让 AI 应用的知识改动有据可依。观测真实表现，受控测量 prompt / RAG / skill / agent / workflow 的版本差异，判断改动是否有效、版本能否发布，并支持自动迭代改进。 Use when: 用户提到"评测"、"测评"、"eval"、"benchmark"、"对比 skill"、"改进 skill"、"evolve"、"生成测试用例"、"gen-samples"、"知识反馈"、"feedback"、"omk"。
repo-navigator
Repository navigation skill for project-level runtime context.
code-review-v2
Structured code review skill with explicit risk dimensions.
rag-answerer
RAG answerer that only answers from supplied context.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.