oh-my-knowledge is a tool for DeepSeek Harness. OMK — Evidence-backed evaluation and observability for prompts, RAG, skills, agents, and workflows. Native Codex, Claude Code, and DeepSeek Harness support.
A well-documented, actively maintained evaluation harness for prompts, RAG, and agents, though still in Beta.
Code quality8
README shows a CI badge, TypeScript codebase, npm publishing, and structured docs/reference layout, indicating solid engineering rigor.
Security7
README explicitly scopes the tool to local trusted environments and warns that some features execute local code, but no download-and-execute or plaintext-secret patterns are visible.
Utility9
Addresses a real pain point by providing controlled, evidence-backed A/B comparison of prompts, RAG, skills, and agents with statistical rigor and gap detection.
Maintenance8
Last updated 2026-08-25 with an active CI workflow, npm releases, and a documented v1-preview migration path, indicating ongoing development.
Docs8
README offers quickstart commands, goal-based entry points, environment variable tables, requirements, and links to CLI/sample/executor references and online docs.
Generated by AI after reading the project README, as a decision aid; neutral scores are given when information is thin. Not an official endorsement.
This command passed the install-plan safety check and can be executed by a DSH host; verification status is not equivalent to a security audit or official背书。
OMK — Evidence-backed evaluation and observability for prompts, RAG, skills, agents, and workflows. Native Codex, Claude Code, and DeepSeek Harness support.
How popular is oh-my-knowledge?
oh-my-knowledge has 18 stars and 2 forks on GitHub, last updated 2026-08-25.
What license does oh-my-knowledge use?
oh-my-knowledge is distributed under the MIT license.
Is oh-my-knowledge compatible with DeepSeek Harness?
oh-my-knowledge is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
/10类依据
项目类型技能
功能/10类开发工具
规则置信度High
System reads GitHub Topics first, then compares against the in-site category dictionary and word-root rules. Current match:skill-evaluation、benchmark、claude-code、evaluation-as-code、prompt-engineering、prompt-testing、rag-evaluation。
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.
Enterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for Codex Harness, DeepSeek Harness, and OpenCode, with unified plugins and Skills, multi-agent projects and tasks, and editable code, documents, presentations, design, and video.