docs: 双向credit微软SkillOpt — 顶部加集成徽章+[!NOTE]互认callout+References重构(仓库优先/pip/双向印证)

微软SkillOpt仓库2026-06-03已将darwin-skill列入官方集成名单，README回敬更强credit

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

README.md

@@ -26,6 +26,7 @@
 [![Version](https://img.shields.io/badge/version-2.0-blue.svg)](#whats-new-in-20)
 [![Agent Skill](https://img.shields.io/badge/Agent%20Skill-Compatible-blueviolet)](https://skills.sh)
 [![Skills](https://img.shields.io/badge/skills.sh-Compatible-green)](https://skills.sh)
+[![Microsoft SkillOpt](https://img.shields.io/badge/Microsoft_SkillOpt-Listed_Integration-0078D4?logo=microsoft&logoColor=white)](https://github.com/microsoft/SkillOpt)
 
 ```
 npx skills add alchaincyf/darwin-skill
@@ -35,6 +36,14 @@ npx skills add alchaincyf/darwin-skill
 
 ---
 
+> [!NOTE]
+> **🤝 微软研究院把达尔文列进了 SkillOpt 的官方集成名单。**
+> 2026-06-03，微软在 [SkillOpt 仓库](https://github.com/microsoft/SkillOpt) 的更新里写道：
+> *「gbrain, gbrain-evals, and **darwin-skill** have all integrated SkillOpt.」*
+> 我们吸收了它的 validation-gated 框架，它把达尔文写进了自己的集成名单。这是一次双向的致意。👉 [去 SkillOpt 仓库看看](https://github.com/microsoft/SkillOpt)
+
+---
+
 ## What's New in 2.0
 
 2.0 不是缝缝补补，是系统性吸收微软研究院 2026-05-22 两篇论文后的结构性升级。五个变化：
@@ -205,10 +214,11 @@ v2.0 的设计直接基于以下学术工作。强烈推荐 skill 生态的研
 
 > Microsoft Research. *SkillOpt: Executive Strategy for Self-Evolving Agent Skills.* arXiv:2605.23904, 2026.
 
-- 论文：https://arxiv.org/abs/2605.23904
+- 🔗 **代码仓库**：[github.com/microsoft/SkillOpt](https://github.com/microsoft/SkillOpt)（`pip install skillopt`，v0.1.0 已上 PyPI）
 - 项目页：https://microsoft.github.io/SkillOpt/
-- 代码：https://github.com/microsoft/SkillOpt
+- 论文：https://arxiv.org/abs/2605.23904
 - **贡献**：validation-gated edits 的形式化框架。把 skill 当作 frozen 模型的「外部可训练状态」，每次编辑都必须通过独立验证才能保留。达尔文.skill v2.0 的多评委独立审查、评委不复用、早停机制、干跑比例控制都对齐了该框架。
+- 🤝 **双向印证**：2026-06-03，SkillOpt 官方仓库把 darwin-skill 写进了集成名单，原文是 *"gbrain, gbrain-evals, and darwin-skill have all integrated SkillOpt."* 它给我们框架，我们给它实战验证。
 
 ### autoresearch
 

README_EN.md

@@ -20,6 +20,7 @@ Inspired by [Karpathy's autoresearch](https://github.com/karpathy/autoresearch).
 [![Version](https://img.shields.io/badge/version-2.0-blue.svg)](#whats-new-in-20)
 [![Agent Skill](https://img.shields.io/badge/Agent%20Skill-Compatible-blueviolet)](https://skills.sh)
 [![Skills](https://img.shields.io/badge/skills.sh-Compatible-green)](https://skills.sh)
+[![Microsoft SkillOpt](https://img.shields.io/badge/Microsoft_SkillOpt-Listed_Integration-0078D4?logo=microsoft&logoColor=white)](https://github.com/microsoft/SkillOpt)
 
 ```
 npx skills add alchaincyf/darwin-skill
@@ -29,6 +30,14 @@ npx skills add alchaincyf/darwin-skill
 
 ---
 
+> [!NOTE]
+> **🤝 Microsoft Research lists darwin-skill as an official SkillOpt integration.**
+> On 2026-06-03, the [SkillOpt repo](https://github.com/microsoft/SkillOpt) noted:
+> *"gbrain, gbrain-evals, and **darwin-skill** have all integrated SkillOpt."*
+> We absorbed its validation-gated framework; it added darwin to its integration list. A two-way nod. 👉 [Visit the SkillOpt repo](https://github.com/microsoft/SkillOpt)
+
+---
+
 ## What's New in 2.0
 
 v2.0 is not a patch release. It's a structural upgrade absorbing two Microsoft Research papers published on 2026-05-22. Five concrete changes:
@@ -201,10 +210,11 @@ v2.0's design directly builds on the following academic work. Recommended readin
 
 > Microsoft Research. *SkillOpt: Executive Strategy for Self-Evolving Agent Skills.* arXiv:2605.23904, 2026.
 
-- Paper: https://arxiv.org/abs/2605.23904
+- 🔗 **Code repo**: [github.com/microsoft/SkillOpt](https://github.com/microsoft/SkillOpt) (`pip install skillopt`, v0.1.0 on PyPI)
 - Project page: https://microsoft.github.io/SkillOpt/
-- Code: https://github.com/microsoft/SkillOpt
+- Paper: https://arxiv.org/abs/2605.23904
 - **Contribution**: The formal framework of validation-gated edits. Treats a skill as the "external trainable state" of a frozen model: every edit must pass independent validation to be kept. darwin.skill v2.0's multi-judge independent review, non-reuse of judges, early stopping, and dry-run ratio control all align with this framework.
+- 🤝 **Mutual recognition**: On 2026-06-03, the official SkillOpt repo listed darwin-skill as an integration: *"gbrain, gbrain-evals, and darwin-skill have all integrated SkillOpt."* They give us the framework; we give it real-world validation.
 
 ### autoresearch