Personal Ip Knowledge Builder logo

Personal Ip Knowledge Builder

OrganizationPopular
limecloud
personal-ip-knowledge-builder

将访谈稿、聊天记录、简历、公开内容、业务资料、案例和既有 DOCX/Markdown 文档,提炼成可被 AI 长期调用的个人 IP 知识库。适用于用户要求“生成个人知识库”“整理成个人 IP 成品知识库”“为创始人/专家/讲师/主播/顾问建立AI知识库”“把资料变成个人IP底层提示词/写作风格库/故事素材库/话术库”的场景。

Overview

Publisherlimecloud
Repositorylime
Skill namepersonal-ip-knowledge-builder
Stars
1.5K
Forks
207
Bundled files
6
LicenseApache-2.0
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.

  • 6 bundled files

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

  • Open source

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

Installation

Install the Personal Ip Knowledge Builder 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.
  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/limecloud/lime.git /tmp/lime
mkdir -p .claude/skills
cp -r /tmp/lime/lime-rs/resources/default-skills/personal-ip-knowledge-builder .claude/skills/personal-ip-knowledge-builder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Personal Ip Knowledge Builder 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 Personal Ip Knowledge Builder 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 Personal Ip Knowledge Builder 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.

个人 IP 知识库生成器

核心目标

把零散资料编译成一份结构化 Markdown 知识库,让后续 AI 能稳定调用这个人的事实、故事、观点、风格和边界,而不是每次临时总结。

默认输出中文;除非用户明确要求其他语言。

与 Agent Knowledge 的分工

本 Skill 只负责“怎么生产和维护知识”:

  • 读取来源资料、模板、访谈问题和质量检查表。
  • 生成或更新个人 IP 成品文档。
  • 标记缺失事实、冲突事实和待用户确认的信息。
  • 返回整理记录、质量诊断和 provenance 建议。

Agent Knowledge 负责“知识产物长什么样、如何安全进入上下文”:

  • KNOWLEDGE.md 保存 pack metadata、profile: document-firstruntime.mode: persona
  • documents/<pack-name>.md 保存本 Skill 生成的主文档。
  • runs/compile-*.json 记录本次 Builder Skill 输入、输出、版本和诊断。
  • 运行时 Resolver 只消费 KnowledgePack,不在回答用户问题时执行本 Skill。

工作流

  1. 先盘点输入资料:访谈、简历、聊天记录、文章、案例、产品服务、历史文案、DOCX/Markdown。
  2. 如果输入是 DOCX,优先使用 scripts/docx_to_markdown.py 转成 Markdown 草稿。
  3. 读取 references/personal-ip-template.md,按固定章节生成知识库。
  4. 读取 references/interview-questions.md,识别缺失的高价值信息。
  5. 缺少关键事实时,先问用户补齐;如果用户要求先生成,则用 待补充 标注,不要编造。
  6. 提炼事实、故事、案例、方法论、价值观、表达风格、金句、可引用素材和禁忌边界。
  7. 生成完整 Markdown,结尾必须包含“智能体应用指南”。
  8. references/quality-checklist.md 自检,必要时补一节“待补充信息清单”。

Lime Runtime Binding 契约

当 Lime 通过 App Server knowledgePack/compile runtime binding 调用本 Skill 时,输入输出必须保持下面的最小契约。

输入

text
packName: <当前知识包名>
packType: personal-profile
profile: document-first
runtime.mode: persona
sources[]: sources/ 下的来源文件摘要和相对路径
metadata.primaryDocument: documents/<packName>.md

输出

text
primaryDocument:
  path: documents/<packName>.md
  content: <按 references/personal-ip-template.md 生成的完整 Markdown>
status: draft | needs-review | ready | disputed
missingFacts[]: <待补充信息>
warnings[]: <质量或冲突提醒>
provenance:
  kind: agent-skill
  name: personal-ip-knowledge-builder
  version: 1.0.0

固定规则:

  1. 不输出独立于 KnowledgePack 的新目录结构;documents/<packName>.md 是主文档唯一写回目标。
  2. 不直接改写 KNOWLEDGE.md;由 Lime 写入 metadata.producedByruntime.mode 和状态。
  3. 不把模板复制进 Lime 代码;模板、访谈问题和质量检查表继续留在本 Skill 的 references/
  4. 不在运行时回答阶段执行;仅在用户导入、重新整理或维护 pack 时调用。

输出规则

  • 不写成简历,也不写成宣传软文;要写成 AI 可调用的底层知识库。
  • 区分事实、观点、推断和待补充信息。
  • 保留真实语气,不要把人物包装成虚假的“成功学大师”。
  • 尽量使用具体案例、数据、原话、场景和转折点。
  • 每个章节都要有清晰标题,适合长期维护。
  • 结尾必须包含:使用说明、AI 写作风格指南、核心价值观关键词、可引用故事素材、禁忌与边界。

推荐产物结构

在 Agent Knowledge v0.6.0 / Lime 中,优先写回:

text
<pack-name>/
  KNOWLEDGE.md                 # 由 Lime 维护 metadata
  documents/<pack-name>.md     # 本 Skill 生成的主文档
  runs/compile-*.json          # 由 Lime 记录本次整理 provenance

如果用户在普通对话中只要求一份独立文档,也可以输出单一 Markdown 作为临时交付;进入 Lime KnowledgePack 时必须回到上述 document-first 结构。

不再默认拆成:

text
[person-id]-personal-ip/
  knowledge.md
  facts.md
  voice.md
  stories.md
  boundaries.md

何时读取资源

  • 需要章节骨架时,读取 references/personal-ip-template.md
  • 资料不足或要做访谈表时,读取 references/interview-questions.md
  • 输出前做质量检查时,读取 references/quality-checklist.md
  • 用户只要空白模板时,可复制 assets/personal-ip-knowledge-skeleton.md

DOCX 转 Markdown

如果需要先转换 DOCX:

bash
python3 scripts/docx_to_markdown.py 输入.docx 输出.md

转换后再进行知识提炼。脚本只负责格式转换,不负责事实提炼。

Bundled files

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

Frequently asked questions

What does the Personal Ip Knowledge Builder AI skill do?

将访谈稿、聊天记录、简历、公开内容、业务资料、案例和既有 DOCX/Markdown 文档,提炼成可被 AI 长期调用的个人 IP 知识库。适用于用户要求“生成个人知识库”“整理成个人 IP 成品知识库”“为创始人/专家/讲师/主播/顾问建立AI知识库”“把资料变成个人IP底层提示词/写作风格库/故事素材库/话术库”的场景。

Why use Personal Ip Knowledge Builder on TypingMind?

Because you install it once and use it with any model. Personal Ip Knowledge Builder 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 Personal Ip Knowledge Builder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/limecloud/lime/tree/main/lime-rs/resources/default-skills/personal-ip-knowledge-builder. 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 Personal Ip Knowledge Builder?

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 Personal Ip Knowledge Builder?

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

Is the Personal Ip Knowledge Builder AI skill free?

Yes. It is published on GitHub by limecloud under the Apache-2.0 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 👇