Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Liuziyu77/gene-skill --skill nuwa-colleague-combinedgit clone --depth 1 https://github.com/Liuziyu77/gene-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/liuziyu77/gene-skill/nuwa-colleague-combined)<a href="https://agentmods.dev/skills/liuziyu77/gene-skill/nuwa-colleague-combined"><img src="https://agentmods.dev/badge/skills/liuziyu77/gene-skill/nuwa-colleague-combined/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/liuziyu77/gene-skill/nuwa-colleague-combined"><img src="https://agentmods.dev/badge/skills/liuziyu77/gene-skill/nuwa-colleague-combined.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00143 | $0.01884 |
| Opus 5 | $0.00072 | $0.00942 |
| Sonnet 5 | $0.00029 | $0.00377 |
| Haiku 4.5 | $0.00014 | $0.00188 |
Grade A, and why
nuwa-colleague-combined scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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）
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 162 lines · 143 tokens per session scan A c14271a99bc0
nuwa-colleague-combined is a skill published in the GitHub repository Liuziyu77/gene-skill (56 stars, last pushed 4mo ago), licensed MIT. It adds 143 tokens to every session and 1,884 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…