Immortal Skill logo

Immortal Skill

CommunityPopular
agenmod
immortal-skill

通用数字永生框架:从聊天记录、社交媒体、文档等多平台数据中蒸馏任何人的数字分身——支持自己、同事、导师、亲人、伴侣/前任、朋友、公众人物 7 种角色模板,接入国内外 12+ 数据平台。

Overview

Publisheragenmod
Repositoryimmortal-skill
Skill nameimmortal-skill
Stars
1.1K
Forks
99
Bundled files
66
LicenseMIT
Links
  • 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.

  • 66 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by agenmod on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/agenmod/immortal-skill/tree/main
  4. 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.
2

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/agenmod/immortal-skill.git \
  .claude/skills/immortal-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Immortal Skill 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 Immortal Skill 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 Immortal Skill 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.

数字永生

语言

根据用户第一条消息的语言,全程使用同一语言。

何时激活

  • 用户要「蒸馏 XX」「做数字分身」「保留 TA 的方式/记忆」「让 AI 像 XX 一样」。
  • 用户提供关于某人的材料,希望生成可加载的 Agent Skill 包。

核心理念

选择角色 → 多平台采集 → 分维度提取(procedure / interaction / memory / personality)→ 证据分级 → 冲突合并 → 输出符合 Agent Skills 的技能目录。

路径约定

  • 本 Skill 根目录记为 {baseDir}。
  • 生成物默认写入 ./skills/immortals/<slug>/。
  • slug:小写字母、数字、连字符,与最终 SKILL.md 的 name 一致。

操作顺序

Phase 0:选择角色模板

向用户询问蒸馏对象的角色,读取对应模板:

你想蒸馏谁?

  [1] 🪞 自己(全维度数字分身)
  [2] 🏢 同事(工作方式与沟通风格)
  [3] 🎓 导师/Mentor(教学方式与指导智慧)
  [4] 🏠 亲人(家族记忆与生活智慧)
  [5] 💕 伴侣/前任(关系记忆与互动模式)
  [6] 🤝 朋友(友谊互动与共同经历)
  [7] 🌐 公众人物(公开方法论)

读取 {baseDir}/personas/<选择>.md 了解该角色的特有维度与要求。 同时读取 {baseDir}/personas/_base.md 了解通用维度。

Phase 1:伦理确认

根据角色模板中的伦理要求,在收集材料前告知用户。不同角色的伦理侧重:

  • 同事/导师:限团队内部对齐与培训
  • 亲人(已故):确认其他家人是否应知情
  • 伴侣/前任:确认目的是正面回忆;严格脱敏
  • 公众人物:仅限公开资料;须有可追溯的公开出处
  • 自己:注意聊天中他人发言的脱敏

Phase 2:收集材料

读取 {baseDir}/recipes/intake-protocol.md,按角色类型确定数据源。

提供以下采集方式:

材料怎么提供?

  [A] 自动采集(推荐)
      飞书 / 钉钉 / Slack / Discord / Telegram / Email
      → 扫描频道 → 拉取消息

  [B] 本地数据库
      微信(需第三方导出或本地 SQLite)
      iMessage(macOS,需 Full Disk Access)

  [C] 归档文件
      WhatsApp 导出 / Twitter/X 归档 / Google Takeout
      Facebook 数据下载 / 微博导出

  [D] 上传/粘贴文件
      PDF / JSON / CSV / Markdown / 纯文本

  [E] 直接粘贴文字

可混用多种方式。

自动采集使用统一 CLI:

bash
python3 {baseDir}/kit/immortal_cli.py collect --platform <平台> [选项]

详见 {baseDir}/docs/PLATFORM-GUIDE.md。

Phase 3:分维度提取

根据角色模板确定所需维度,按需加载对应 Prompt:

维度PromptRecipe适用角色
程序性prompts/procedural-extractor.mdrecipes/procedural-mining.md同事、导师、自己、公众人物
互动性prompts/interaction-extractor.mdrecipes/interaction-mining.md所有
记忆prompts/memory-extractor.mdrecipes/memory-mining.md自己、亲人、伴侣、朋友、导师、公众人物
性格prompts/personality-extractor.mdrecipes/personality-mining.md所有(同事仅工作相关)

每条输出标注证据级别:verbatim / artifact / impression。

参考 {baseDir}/examples/ 下的示例查看产出物格式。

Phase 4:合并与冲突处理

读取 {baseDir}/recipes/merge-policy.md,执行证据分级合并。矛盾项写入 conflicts.md。

Phase 5:初始化目录并写入

bash
python3 {baseDir}/kit/manifest_tool.py init --slug <slug> --base ./skills/immortals --persona <角色>

用 Write 工具写入各维度文件,然后读取 {baseDir}/prompts/skill-assembler.md 生成 SKILL.md。

Phase 6:封包登记

bash
python3 {baseDir}/kit/manifest_tool.py stamp --slug <slug> --base ./skills/immortals --sources "<来源>"

Phase 7:告知用户

  • 生成路径与加载方式
  • 证据覆盖度统计
  • 各维度的局限性提示

追加材料(进化)

bash
python3 {baseDir}/kit/version_tool.py snapshot --slug <slug> --base ./skills/immortals --note "追加前"

然后按 Phase 2-6 增量更新。

用户纠正

先快照,再读取 {baseDir}/prompts/correction-handler.md 处理。

版本管理

bash
python3 {baseDir}/kit/version_tool.py list --slug <slug> --base ./skills/immortals
python3 {baseDir}/kit/version_tool.py rollback --slug <slug> --base ./skills/immortals --tag <快照>

不做的事

  • 不复制任何第三方仓库的脚本或提示词。
  • 不把通用常识当成被蒸馏者的个人特色。
  • 不模拟公众人物的私人对话。
  • 不用于跟踪、骚扰或欺骗。

自检清单

  • name 与目录名一致且符合命名规则。
  • 各维度文件中 verbatim + artifact 占比是否达标?
  • impression 是否隔离到专属区?
  • conflicts.md 是否反映了真矛盾?
  • 伦理声明是否与角色匹配?
  • SKILL.md 正文 < 100 行?

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 6 more files.

Frequently asked questions

What does the Immortal Skill AI skill do?

通用数字永生框架:从聊天记录、社交媒体、文档等多平台数据中蒸馏任何人的数字分身——支持自己、同事、导师、亲人、伴侣/前任、朋友、公众人物 7 种角色模板,接入国内外 12+ 数据平台。

Why use Immortal Skill on TypingMind?

Because you install it once and use it with any model. Immortal Skill 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 Immortal Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agenmod/immortal-skill/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Immortal Skill?

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 Immortal Skill?

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

Is the Immortal Skill AI skill free?

Yes. It is published on GitHub by agenmod 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇