Nuwa Colleague Combined

Q: What does the Nuwa Colleague Combined AI skill do?

[合成体 · 工具×工具] nuwa-skill（公众人物蒸馏）× colleague-skill（真实同事蒸馏） 基因来源：nuwa-skill（50%）× colleague-skill（50%） 超级基因：「通用人格蒸馏引擎」——一套流程同时处理公众人物和私有个体 显性规则：nuwa 主导「信息采集策略」，colleague 主导「输出结构」 融合能力：支持「公众人物 + 真实同事」的混合素材蒸馏 由 gene-recombine skill 生成。

Q: Why use Nuwa Colleague Combined on TypingMind?

Because you install it once and use it with any model. Nuwa Colleague Combined is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

Q: How do I install Nuwa Colleague Combined in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Liuziyu77/gene-skill/tree/main/examples/nuwa-colleague-combined. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Q: Which AI models can use Nuwa Colleague Combined?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

Q: How many AI models can I use with Nuwa Colleague Combined?

As many as you like. As long as a model supports skills, you can use Nuwa Colleague Combined with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Q: Is the Nuwa Colleague Combined AI skill free?

Yes. It is published on GitHub by Liuziyu77 under the MIT license. You only pay your own AI provider for the tokens you use.

Q: What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

Q: How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Community

Liuziyu77

nuwa-colleague-combined

[合成体 · 工具×工具] nuwa-skill（公众人物蒸馏）× colleague-skill（真实同事蒸馏）基因来源：nuwa-skill（50%）× colleague-skill（50%）超级基因：「通用人格蒸馏引擎」——一套流程同时处理公众人物和私有个体显性规则：nuwa 主导「信息采集策略」，colleague 主导「输出结构」融合能力：支持「公众人物 + 真实同事」的混合素材蒸馏由 gene-recombine skill 生成。

Overview

Publisher	Liuziyu77
Repository	`gene-skill`
Skill name	`nuwa-colleague-combined`
Stars	56
Forks	0
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by Liuziyu77 on GitHub. Read the source before you install it.

Installation

Install the Nuwa Colleague Combined AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Liuziyu77/gene-skill/tree/main/examples/nuwa-colleague-combined
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/Liuziyu77/gene-skill.git /tmp/gene-skill
mkdir -p .claude/skills
cp -r /tmp/gene-skill/examples/nuwa-colleague-combined .claude/skills/nuwa-colleague-combined

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Nuwa Colleague Combined in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Nuwa Colleague Combined on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Nuwa Colleague Combined is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

通用人格蒸馏引擎

女娲造的是用公开信息构建的思维框架；同事蒸馏做的是用私有数据构建的工作伙伴。

这个合成体做的事情只有一件：不管素材来自哪里，把任何人蒸馏成可运行的 Skill。

触发条件

以下情况激活本 Skill：

需要蒸馏的对象同时有公开素材和私有素材（如：某位业内知名的同事）
素材类型混合（公开演讲 + 内部飞书消息 + 个人博客）
用户不确定用哪个蒸馏工具，输入模糊
需要把多个来源的碎片素材整合成一个人格 Skill

核心工作流（T1）⚡超级基因：通用蒸馏流程

来自：nuwa-skill（T1-6Agent调研）× colleague-skill（T1-5Step创建）协同融合

Step 0：素材来源分类

收到输入后，先判断素材性质：

素材来源	类型	后续策略
公开网络（书籍/演讲/访谈/社媒）	公开素材	→ 走 nuwa-skill 的 Agent Swarm 调研
飞书/钉钉/邮件/内部文档	私有素材	→ 走 colleague-skill 的工具采集
用户直接提供（PDF/截图/粘贴）	本地素材	→ 直接读取，两套维度都分析
混合（公开+私有）	混合素材	→ 并行，合并后统一提炼

Step 1：信息采集（按素材类型分流）

公开素材路径（调用 nuwa-skill 的 Agent Swarm）：

Agent 1-6 分别覆盖：著作、对话、表达DNA、他者视角、决策、时间线
信息源黑名单沿用 nuwa-skill 规则（排除知乎、微信公众号）

私有素材路径（调用 colleague-skill 的工具链）：

飞书/钉钉自动采集：feishu_auto_collector.py / dingtalk_auto_collector.py
消息、文档、邮件分别解析

本地素材路径：

PDF/图片：Read 工具直接读取
字幕/transcript：srt_to_transcript.py 清洗

Step 2：维度对齐

无论素材来自哪条路径，都统一提炼以下维度：

维度	说明
心智模型	反复出现的核心思维框架（来自 nuwa 维度）
工作规范	技术偏好、协作标准、输出习惯（来自 colleague 维度）
表达 DNA	语言风格、句式偏好
决策模式	面对不确定时的判断方式
人格边界	绝不做什么 / 最在乎什么

Step 3：输出结构（来自 colleague-skill，显性）

沿用 colleague-skill 的双轨输出结构：


PART A：能力层（Work Skill）
  - 技术/专业能力矩阵
  - 工作规范与输出偏好
  - 经验知识库

PART B：人格层（Persona）
  - 心智模型（nuwa 路径提供）
  - 表达 DNA
  - 决策模式与边界
  - Layer 0-4 人格结构

Step 4：质量验证

沿用 nuwa-skill 的质量标准（心智模型 3-7 个、诚实边界 ≥3 条、一手来源占比 > 50%）叠加 colleague-skill 的修正机制（用户可说「他不会这样」随时更新）

工具调用模式（T2）

场景	优先工具
网络调研	`WebSearch` + 可用的 research Skill
飞书采集	`feishu_auto_collector.py`
钉钉采集	`dingtalk_auto_collector.py`
PDF/图片读取	`Read`（原生支持）
字幕清洗	`srt_to_transcript.py`
版本管理	`version_manager.py`

输出格式（T3）

产物路径（以实际框架的 Skills 目录为准）：

公众人物 → {skills_dir}/{name}-perspective/SKILL.md
真实同事 → ./colleagues/{slug}/SKILL.md
混合素材人物 → {skills_dir}/{name}-hybrid-profile/SKILL.md（新路径）

交互模式（T4）

检查点	位置	内容
素材来源确认	Step 0 之后	告知采集路径，询问是否有额外素材
调研质量 Review	Step 1 之后	展示各维度覆盖情况，用户确认
提炼摘要确认	Step 2 之后	展示心智模型/工作规范草稿，用户调整
最终预览	Step 3 之后	展示 PART A + PART B 摘要，确认写入

错误处理（T5）

错误类型	处理
飞书 token 过期	引导刷新，或切换浏览器采集方案
网络调研来源不足	降低期望，心智模型减至 2-3 个，增加诚实边界
素材质量低（主要是二手转述）	明确标注，一手来源占比 < 50% 时在诚实边界注明
混合素材冲突（公开言论 vs 私下行为不一致）	保留矛盾，记录为「内在张力」，不调和

诚实边界

混合素材蒸馏的质量强依赖于素材覆盖的全面性——只有飞书消息而无公开演讲，人格层会不完整
本 Skill 不能替代直接与当事人深度交流
公众人物维度的信息有截止日期，私有素材则实时（两者时效性不同，输出时分别标注）

基因来源图谱

特质	来源	基因	遗传类型
Agent Swarm 调研策略	nuwa-skill	T1	显性
飞书/钉钉采集工具链	colleague-skill	T2	显性
通用蒸馏流程	协同涌现	超级基因	超显性
双轨输出结构（Work+Persona）	colleague-skill	T3	显性
6维度信息分层（著作/对话/表达…）	nuwa-skill	T1	共显性
对话纠正与版本管理	colleague-skill	T4/T5	显性
质量标准（心智模型数量/一手占比）	nuwa-skill	T5	共显性

本 Skill 由 gene.skill | 基因重组生成调研时间：2026-04-16

Frequently asked questions

What does the Nuwa Colleague Combined AI skill do?

Why use Nuwa Colleague Combined on TypingMind?

Because you install it once and use it with any model. Nuwa Colleague Combined is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Nuwa Colleague Combined in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Liuziyu77/gene-skill/tree/main/examples/nuwa-colleague-combined. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Nuwa Colleague Combined?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Nuwa Colleague Combined?

As many as you like. As long as a model supports skills, you can use Nuwa Colleague Combined with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Nuwa Colleague Combined AI skill free?

Yes. It is published on GitHub by Liuziyu77 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Pokemon Player

NousResearch

OrganizationPopular

Play Pokemon via headless emulator + RAM reads.

Docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document',…

Openclaw Docker E2e Authoring

openclaw

OrganizationPopular

Author OpenClaw Docker E2E and live provider Docker lanes.

Openclaw Parallels Smoke

openclaw

OrganizationPopular

Prepare, snapshot, run, rerun, debug, or interpret OpenClaw Parallels guest install, onboarding, gateway smoke, and upgrade checks across macOS, Windows, and Linux.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

通用人格蒸馏引擎

触发条件

核心工作流（T1）⚡超级基因：通用蒸馏流程

Step 0：素材来源分类

Step 1：信息采集（按素材类型分流）

Step 2：维度对齐

Step 3：输出结构（来自 colleague-skill，显性）

Step 4：质量验证

工具调用模式（T2）

输出格式（T3）

交互模式（T4）

错误处理（T5）

诚实边界

基因来源图谱

Frequently asked questions

Related AI Skills

Set up your own AI workspace now