← Back to Skills Marketplace
li-evan

Learn Graph

by Evan · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
44
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install learn-graph
Description
当用户要系统学一个新领域、不知道从哪入手、或担心「学得不够系统」时使用。用「知识图谱学习法」和用户一起构建该领域的概念/用途/父子节点图谱(自己建图的过程本身就是学习),标出复用价值最高的节点和「从常识就能入门的点」,给出有效学习路径并回答「学到哪算够」。触发场景:系统学 X 领域、从哪开始学、学得不系统、想要...
README (SKILL.md)

知识图谱学习法(learn-graph)

核心信条:自己一步步建图谱的过程,本身就是最有效的学习——不要直接套用别人给的图谱。 绝大部分知识,都有一个从常识就能入门的点。

何时用

用户要系统进入一个新领域,或焦虑"学得不够系统 / 不知何时算够"。

流程(关键:和用户一起建,不是直接灌一张完整图)

第一步:锁定目标领域 X 和目的

用户为什么学 X?(接 learn-occam 的"既定问题")目的决定图谱画到多细。

第二步:构建图谱——只抓三件事

概念/名称 · 用途 · 上下文关系(父子节点)

  • 子节点 = X 依托 / 基于什么;父节点 = X 服务于什么目标。
  • 以提问引导用户一起填(自己建图才学得到),别一次性灌完。先给骨架,留节点让他补。

第三步:标注两个关键

  • 复用价值:哪些节点父节点多(像 Python)→ 优先学,回报最高。
  • 入门点:哪个节点"从常识就能入门"→ 学习路径的起点。

第四步:输出学习路径 + 颗粒度

从入门点出发、沿父子关系排一条有效路径。颗粒度按需自由切换(领域图 → 细分学科图)。"学到哪算够"= 覆盖到能解决第一步那个目的的节点即可,不必学满。

第五步:交接

  • 拿不准某节点是不是缺前置知识 → 这正是图谱的强项,已在图上标出。
  • 找到入门点要动手 → 转 learn-prototype(在图上找"最垃圾原型"的起点)。

注意

⚠️ 铁律·只用确证的已会知识:判断用户「已经会什么」只能用他确证学过的知识(亲口确认或可靠背景);严禁把「正在讲的材料 / 文章作者背景 / 对话里别人的知识」当成用户会的。拿不准 → 直接问「⚠️ 你学过 ___ 吗?」,绝不替他假设。

  • 强调"自己建":多用提问让用户参与,别炫一张完美的图。
  • 同族 skill:learn-occam(该不该学) learn-crossover(已会什么) learn-prototype(动手) learn-feynman(自查)。
Usage Guidance
Install if you want an agent to help structure learning plans with concept maps. Expect it may activate for broad learning-path questions; users who only want a quick explanation may prefer not to invoke this skill.
Capability Assessment
Purpose & Capability
The artifact coherently teaches a knowledge-graph method for planning study in a new field and stays within educational guidance.
Instruction Scope
The trigger language is somewhat broad for learning and planning requests, but the runtime instructions remain limited to collaborative mapping, asking clarifying questions, and not assuming the user's prior knowledge.
Install Mechanism
The package contains only one markdown SKILL.md file, with no scripts, dependencies, install hooks, or clawpack URL.
Credentials
No API key, network access, file access, local indexing, or account integration is requested or needed for the stated purpose.
Persistence & Privilege
There is no persistence mechanism, background worker, scheduled task, privilege escalation, or mutation authority.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install learn-graph
  3. After installation, invoke the skill by name or use /learn-graph
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the learn-graph skill for systematic learning of new fields. - Guides users through building a knowledge graph by identifying key concepts, use cases, and relationships. - Highlights high-value nodes for efficient learning and entry points accessible from common knowledge. - Provides a tailored learning path and guidance on how much is "enough" to meet user goals. - Emphasizes collaborative mapping and user confirmation of prior knowledge for more effective learning.
Metadata
Slug learn-graph
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Learn Graph?

当用户要系统学一个新领域、不知道从哪入手、或担心「学得不够系统」时使用。用「知识图谱学习法」和用户一起构建该领域的概念/用途/父子节点图谱(自己建图的过程本身就是学习),标出复用价值最高的节点和「从常识就能入门的点」,给出有效学习路径并回答「学到哪算够」。触发场景:系统学 X 领域、从哪开始学、学得不系统、想要... It is an AI Agent Skill for Claude Code / OpenClaw, with 44 downloads so far.

How do I install Learn Graph?

Run "/install learn-graph" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Learn Graph free?

Yes, Learn Graph is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Learn Graph support?

Learn Graph is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Learn Graph?

It is built and maintained by Evan (@li-evan); the current version is v1.0.0.

💬 Comments