oh-my-knowledge
Monitoringlizhiyao/oh-my-knowledge
Evidence-backed evaluation and observability for prompts, RAG, skills, agents, and workflows, with native support for Codex, Claude Code, and DeepSeek Harness.
- agent-evaluation
- ai
- benchmark
- bootstrap-ci
- claude
- claude-code
- deepseek-harness
- dsh-plugin
- evaluation-as-code
- evaluation-framework
- knowledge-engineering
- krippendorff-alpha
- llm
- llm-evaluation
- llm-judge
- multi-judge-ensemble
- prompt-engineering
- prompt-testing
- rag-evaluation
- skill-evaluation
Verification and compatibility
This section shows evidence collected by the catalog. Undeclared information is labeled as unknown.
- Current-version compatibility
- Verified on the catalog Harness version
- Declared Harness range
- Not declared
- Declared platforms
- Not declared
- Profiles
- web
- Build approval
- No requirement detected
- Permissions
- Not declared
- External services
- Not declared
- Telemetry
- Unknown
This is not a security endorsement. Review source, permissions, and configuration before installing.
View evidence and scope
Verification covers only the named source, version, and Harness environment. It does not guarantee future compatibility.
oh-my-knowledge@0.54.0- The plugin completed a load check in an isolated environment.