nuwa-skill
女娲造人 — 输入人名/主题,自动深度调研蒸馏成可运行的Skill Skill: nuwa-skill Owner: dxy0905 Summary: 女娲造人 — 输入人名/主题,自动深度调研蒸馏成可运行的Skill Tags: latest:1.1.0 Version history: v1.1.0 | 2026-06-05T08:06:47.538Z | auto nuwa-skill-qszf 1.1.0 Changelog: - Updated documentation and usage instructions in SKILL.md to version 1.2.0. - Clarified the workflow for generating and optimizing new Skills. - Added detailed description of data sources for research and skill distillation (local fi
Rank
62
Safety
84
Downloads
1.1k
Updated
Oct 11, 2026
Version
1.1.0
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.
Avoid when
- Contract metadata is missing or unavailable for deterministic execution.
Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing
Public facts
Every fact links back to the source it came from.
- Vendor
- Clawhubvendor · observed Oct 11, 2026
- Protocol compatibility
- OpenClawcompatibility · observed Oct 11, 2026
- Adoption signal
- 1.1K downloadsadoption · observed Oct 11, 2026
- Latest release
- 1.1.0release · observed Jun 5, 2026
- Handshake status
- UNKNOWNsecurity
Install and run
Setup complexity: low.
clawhub skill install s17a9dzksytanvcnb2bjdbm4js87zftx:nuwa-skill-qszf- Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
- Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Contract: missing
curl -s "https://www.xpersona.co/api/v1/agents/clawhub-dxy0905-nuwa-skill-qszf/snapshot"
Documentation
CLAWHUB
5,634 characters of source documentation, loaded on request.
Extracted files
3 files captured from the source.
SKILL.md
---
name: nuwa-skill
description: 女娲造人 — 输入人名/主题,自动深度调研蒸馏成可运行的Skill
version: 1.2.0
category: company-skills
author: 邱数智方 · 技术局 李智
---
# 女娲 · Skill造人术
## 来源
- **GitHub 公司仓库:** https://github.com/dxy0905/qiushuzhifang-skills/tree/main/skills/nuwa-skill
- **原始上游:** https://github.com/alchaincyf/nuwa-skill
- **协议:** MIT
## 功能
自动深度调研任何人物 → 提炼思维框架 → 生成可运行的Skill。
支持两种入口:
1. **明确人名** → 直接蒸馏(如"蒸馏张爱军")
2. **模糊需求** → 诊断推荐 → 再蒸馏
## 安装方式
```bash
# 从 GitHub 安装(推荐)
hermes skills install https://raw.githubusercontent.com/dxy0905/qiushuzhifang-skills/main/skills/nuwa-skill/SKILL.md
```
## 蒸馏工作流(三源调研法)
当蒸馏人物/主题时,从以下三个渠道获取原始材料:
### 源一:本地文件
- 检查 `E:\\` 和 `D:\\` 下是否有相关书籍/文档/论文
- 使用 `python-docx` 提取 `.docx` 中的文字
- 使用 `read_file` 读取 `.md`/`.txt` 文件
### 源二:网络搜索(公众号内容)
- **搜索策略:** 使用"公众号名 + 关键词"组合搜索(type=2),比仅搜公众号名更精准
- **技术栈:** Python urllib获取cookie → Playwright无头浏览器 → 点击文章链接跟随JS重定向 → 滚动触发懒加载
- **子文章提取:** 如果文章内容短(<1000字),检查是否为目录索引文章,提取其中子文章链接逐个下载
- **详情参见:** `references/wechat-scraping-memo.md` + `scripts/wechat-article-downloader.py`
- **搜索引擎备选:** Bing(国内版)、搜狗网页搜索
### 源三:已有Skill复用
- 检查是否已有相关 Skill(如 `zhang-aijun-clta` 可复用为蒸馏起点)
- 使用 `skills_list` 列出,`skill_view` 加载
## Skill产出规范
每个新 Skill 应包含(参照 company-skills 标准):
- **SKILL.md** — 完整正文,含 YAML frontmatter(name/description/version/category/author)
- **references/** — 蒸馏来源说明、原文来源对应表
- **scripts/** — 可复用的工具脚本(如文章下载器)
- **templates/** — 模板文件(如教案模板)
## 版本管理
- v1.x:初版蒸馏(仅书本/已有资料)
- v2.x:整合公众号/网络资料
- v3.x:加入实战案例提炼
- 每次升级递增版本号,在 description 中标注
## 完整Skill生命周期:女娲 → 达尔文 → 技能总指挥 → 发布
女娲.skill 创建Skill初版后,必须配合**达尔文.skill**(darwin-skill)进行后续优化才能达到最佳效果。
优化完成后通过**技能总指挥(skill-orchestrator)** 进行发布(安全扫描→GitHub/ClawHub),署名"邱数智方"建立品牌输出。
``` text
🏺 女娲.skill(造人) → 创建 Skill 初版
↓
🧬 达尔文.skill(进化) → 9维评估 → 自动优化 → 测试验证 → 定稿
↓
🎯 技能总指挥(发布) → 安全扫描 → GitHub发布 / ClawHub提交
↓
🌍 全球社区可用 → 署名"邱数智方",品牌输出
```
### 达尔文评估体系概况(9维度/100分)
引用自微软SkillLens论文(arXiv 2605.23899):
1. 结构完整性 / 2. 清晰度 / 3. 内容完整性 / 4. 可操作性
5. 准确性 / 6. 一致性 / 7. 执行效率 / 8. 鲁棒性 / 9. 元技能合规
### 部署后的持续优化
- 每次公众号新案例下载后 → 用达尔文重新评估skill质量
- 每季度用达尔文做一次skill健康检查
- 评分低于75分 → 触发自动优化流程
## 适用人员
- 技术局全体员工(AI技能开发与人格蒸馏)
- 教育部全体员工(蒸馏教育专家)
## 触发词
「造skill」「蒸馏XX」「女娲」「造人」「达尔文」「优化skill」_meta.json
{
"ownerId": "kn78ze3mqxp4cbpvqn4wq5xnsx87zpw8",
"slug": "nuwa-skill-qszf",
"version": "1.1.0",
"publishedAt": 1780646807538
}skill-card.md
## Description: 女娲造人 — 输入人名/主题,自动深度调研蒸馏成可运行的Skill This skill is ready for commercial/non-commercial use. ## Publisher: [dxy0905](https://clawhub.ai/user/dxy0905) ### License/Terms of Use: MIT-0 ## Use Case: Developers and internal skill authors use this skill to research a person or topic, distill source material into a thinking framework, and produce a runnable agent skill. It is aimed at skill creation workflows that may generate SKILL.md files, references, scripts, templates, and lifecycle guidance. ### Deployment Geography for Use: Global ## Known Risks and Mitigations: Risk: The skill may search broad local drives for books, documents, or papers. Mitigation: Require explicit source paths, show a preview of candidate files before reading, and redact sensitive material before publishing generated skill artifacts. Risk: The skill may automate web collection without enough scoping or consent controls. Mitigation: Limit collection to approved domains and articles, review site terms before automation, and require operator approval before downloading or reusing collected content. Risk: The installation guidance references an unpinned raw URL. Mitigation: Use a pinned commit URL, checksum, or reviewed release artifact before installing the skill in a production agent environment. ## Reference(s): - [ClawHub skill page](https://clawhub.ai/dxy0905/skills/nuwa-skill-qszf) - [ClawHub publisher profile](https://clawhub.ai/user/dxy0905) ## Skill Output: **Output Type(s):** [text, markdown, code, shell commands, configuration, guidance] **Output Format:** [Markdown guidance with inline shell commands and generated skill file specifications] **Output Parameters:** [1D] **Other Properties Related to Output:** [May describe generated SKILL.md, references, scripts, and templates for downstream skill packaging.] ## Skill Version(s): 1.1.0 (source: ClawHub release metadata; artifact SKILL.md frontmatter states 1.2.0) ## Ethical Considerations: Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
AionUi
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
Machine-readable data
The same record, as JSON, for agents and crawlers.
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/dxy0905/skills/nuwa-skill-qszf",
"sourceUrl": "https://clawhub.ai/dxy0905/skills/nuwa-skill-qszf",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-11T10:10:01.547Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-dxy0905-nuwa-skill-qszf/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-dxy0905-nuwa-skill-qszf/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-11T10:10:01.547Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "1.1K downloads",
"href": "https://clawhub.ai/dxy0905/nuwa-skill-qszf",
"sourceUrl": "https://clawhub.ai/dxy0905/nuwa-skill-qszf",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-11T10:10:01.547Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "1.1.0",
"href": "https://clawhub.ai/dxy0905/nuwa-skill-qszf",
"sourceUrl": "https://clawhub.ai/dxy0905/nuwa-skill-qszf",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-06-05T08:06:47.538Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-dxy0905-nuwa-skill-qszf/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-dxy0905-nuwa-skill-qszf/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 1.1.0",
"description": "nuwa-skill-qszf 1.1.0 Changelog: - Updated documentation and usage instructions in SKILL.md to version 1.2.0. - Clarified the workflow for generating and optimizing new Skills. - Added detailed description of data sources for research and skill distillation (local files, web search, existing Skills). - Outlined new guidelines for Skill lifecycle, including cooperation with darwin-skill for evaluation and publishing process. - Specified nine evaluation criteria for Skill optimization and defined ongoing quality assurance procedures. - Expanded information on intended users and activation keywords.",
"href": "https://clawhub.ai/dxy0905/nuwa-skill-qszf",
"sourceUrl": "https://clawhub.ai/dxy0905/nuwa-skill-qszf",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-06-05T08:06:47.538Z",
"isPublic": true
}
]
}Record generated Oct 11, 2026.
