oh-my-knowledge 0.25.0 → 0.25.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -11,7 +11,7 @@
11
11
  **omk** — The knowledge you give your LLM — what's it actually worth?
12
12
  omk answers with objective data, not gut feeling.
13
13
 
14
- **Fix the model, vary the knowledge artifact.**
14
+ **Evaluation framework for LLM knowledge inputs** — prompts, RAG corpora, skills, agent workflows. Fix the model, vary the artifact.
15
15
 
16
16
  <a id="statistical-rigor"></a>
17
17
  > Built-in: Bootstrap CI · Krippendorff α (judge ↔ human) · length-debias · saturation curves · construct-validity isolation. [Why these matter →](docs/statistical-rigor.md)
package/README.zh.md CHANGED
@@ -11,7 +11,7 @@
11
11
  **omk** — 你给 LLM 的知识,价值在哪里?
12
12
  omk 帮你用客观数据回答,而不是凭感觉。
13
13
 
14
- **固定模型,只变知识载体。**
14
+ **面向 LLM 知识输入(prompt / RAG / skill / agent)的评测框架** —— 固定模型,只变知识载体。
15
15
 
16
16
  <a id="statistical-rigor"></a>
17
17
  > 默认带:Bootstrap 置信区间 · Krippendorff α(评委 ↔ 人工)· 长度去偏 · 饱和曲线 · 用例隔离(construct validity)。[这些为什么重要 →](docs/zh/statistical-rigor.md)
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "oh-my-knowledge",
3
- "version": "0.25.0",
4
- "description": "LLM evaluation framework with built-in statistical rigor: bootstrap CI, Krippendorff α, length-debias, saturation curves. Native Claude Code skill / RAG / agent / prompt evaluation.",
3
+ "version": "0.25.1",
4
+ "description": "Evaluation framework for LLM knowledge inputs prompts, RAG corpora, skills, agent workflows. Fix the model, vary the artifact. Built-in statistical rigor: bootstrap CI, Krippendorff α, length-debias, saturation curves.",
5
5
  "type": "module",
6
6
  "bin": {
7
7
  "omk": "dist/src/cli/index.js"