Bläddra i källkod

chore: add 2.0 to titles in README/README_EN/SKILL.md

Make version explicit in headline:
- README.md: # 达尔文.skill → # 达尔文.skill 2.0
- README_EN.md: # darwin.skill → # darwin.skill 2.0
- SKILL.md: # Darwin Skill → # Darwin Skill 2.0
- SKILL.md description: prepend "2.0" + SkillLens/SkillOpt credit

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
alchain 3 veckor sedan
förälder
incheckning
3b477dd71e
3 ändrade filer med 6 tillägg och 4 borttagningar
  1. 1 1
      README.md
  2. 1 1
      README_EN.md
  3. 4 2
      SKILL.md

+ 1 - 1
README.md

@@ -14,7 +14,7 @@
 
 <div align="center">
 
-# 达尔文.skill
+# 达尔文.skill 2.0
 
 **像训练模型一样优化你的 Agent Skills。**
 

+ 1 - 1
README_EN.md

@@ -8,7 +8,7 @@ English | **[中文](README.md)**
 
 <div align="center">
 
-# darwin.skill
+# darwin.skill 2.0
 
 **Optimize your Agent Skills the way you train models.**
 

+ 4 - 2
SKILL.md

@@ -1,10 +1,12 @@
 ---
 name: darwin-skill
-description: "Darwin Skill (达尔文.skill): autonomous skill optimizer inspired by Karpathy's autoresearch and validated by SkillLens (arXiv 2605.23899). Evaluates SKILL.md files using a 9-dimension rubric (structure + effectiveness + meta-skill blacklists), runs hill-climbing with git version control, spawns independent judge agents for blind evaluation, validates improvements through test prompts with auto-break on diminishing returns, and generates visual result cards. Use when user mentions \"优化skill\", \"skill评分\", \"自动优化\", \"auto optimize\", \"skill质量检查\", \"达尔文\", \"darwin\", \"帮我改改skill\", \"skill怎么样\", \"提升skill质量\", \"skill review\", \"skill打分\"."
+description: "Darwin Skill 2.0 (达尔文.skill 2.0): autonomous skill optimizer, v2.0 integrates Microsoft Research SkillLens (arXiv 2605.23899) 9-dim rubric + SkillOpt (arXiv 2605.23904) validation-gated design + human-in-the-loop checkpoints. Evaluates SKILL.md files using a 9-dimension rubric (structure + effectiveness + meta-skill blacklists), runs hill-climbing with git version control, spawns independent judge agents for blind evaluation, validates improvements through test prompts with auto-break on diminishing returns, and generates visual result cards. Use when user mentions \"优化skill\", \"skill评分\", \"自动优化\", \"auto optimize\", \"skill质量检查\", \"达尔文\", \"darwin\", \"帮我改改skill\", \"skill怎么样\", \"提升skill质量\", \"skill review\", \"skill打分\"."
 ---
 
-# Darwin Skill
+# Darwin Skill 2.0
 
+> **v2.0 · 2026-05-28** — 吸收 Microsoft Research SkillLens(arXiv 2605.23899)的 9 维评分药方 + SkillOpt(arXiv 2605.23904)的 validation-gated 验证机制 + human in the loop 三层守关。
+>
 > 借鉴 Karpathy autoresearch 的自主实验循环,对 skills 进行持续优化。
 > 核心理念:**评估 → 改进 → 实测验证 → 人类确认 → 保留或回滚 → 生成成果卡片**
 > GitHub: https://github.com/alchaincyf/darwin-skill