ljg-learn
lijigang/ljg-skills
Deep concept anatomist that deconstructs ideas through 8 exploration dimensions and compresses insights into epiphany.
What is ljg-learn?
ljg-learn is a concept dissection skill that analyzes any concept, term, or idea from eight philosophical and analytical angles (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy). Use it when you need to deeply understand, explain, or deconstruct a concept, producing structured org-mode output.
- Deconstructs concepts through 8 distinct analytical dimensions
- Identifies core semantic components and common misconceptions
- Generates formal expressions and diagrams of concept structure
- Produces introspective first-person perspective on the concept
- Compresses multi-dimensional analysis into a single epiphanic insight
- Outputs in org-mode format with ASCII structural diagrams
How to install ljg-learn
npx skills add https://github.com/lijigang/ljg-skills --skill ljg-learnHow to use ljg-learn
- 1.Trigger the skill with /ljg-learn followed by the concept name, or use Chinese triggers '解剖概念' or '概念解剖'
- 2.The skill will analyze the concept through 8 dimensions: history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, and meta-philosophy
- 3.Review the generated org-mode report with anchoring definitions, eight analytical cuts, introspective insights, and compressed formulas
- 4.Find the output file saved to ~/Documents/notes/ with timestamp and concept name
Use cases
- Understanding abstract philosophical or scientific concepts deeply
- Explaining complex terms to others with multi-perspective clarity
- Analyzing how a concept has evolved historically and linguistically
- Discovering hidden assumptions and metaphors embedded in common ideas
- Creating comprehensive concept maps for learning or documentation
- Philosophers and concept theorists
- Educators explaining complex ideas
- Researchers analyzing foundational concepts
- Knowledge workers building deep understanding
- Anyone seeking epiphanic insight into abstract ideas
ljg-learn FAQ
Org-mode formatted text files saved to ~/Documents/notes/ with timestamp, containing structured sections for each analytical dimension plus introspective and compressed insights.
History (etymological evolution), Dialectics (opposing forces and synthesis), Phenomenology (return to lived experience), Linguistics (semantic and metaphorical analysis), Formalization (mathematical or logical expression), Existentialism (how it changes human existence), Aesthetics (beauty and imagery), and Meta-philosophy (examining the hidden metaphors in our understanding).
Yes, the skill supports both English and Chinese triggers. Chinese triggers are '解剖概念' and '概念解剖', and it can analyze concepts in multiple languages.
The final compression step distills the eight-dimensional analysis into three forms: a formula (concept = ...), a single-sentence epiphany, and an ASCII structural diagram.
Full instructions (SKILL.md)
Source of truth, from lijigang/ljg-skills.
name: ljg-learn description: Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or idea. Triggers on '解剖概念', '概念解剖', 'explain concept', 'learn concept', '/ljg-learn'. Produces org-mode output.
Usage
<example> User: /ljg-learn 熵 Assistant: [对"熵"进行八维解剖,生成 org-mode 报告] </example>Instructions
你是概念解剖师。拿到一个概念,从八个方向切开它,最后把所有切面压成一句顿悟。
1. 定锚
- 这个概念最通行的定义是什么?常见误解在哪?
- 概念里藏着哪几个核心词素?
2. 八刀
八个方向各切一刀。每刀 2-3 句,只留筋骨,不带水分。
- 历史:最早从哪冒出来 → 怎么变的 → 哪一步拐成了今天的意思
- 辩证:它的反面是什么 → 正反碰撞后,更高一层的理解是什么
- 现象:扔掉所有预设,回到事情本身 → 用一个日常场景把它还原出来
- 语言:拆字源(中/英/希腊/拉丁)→ 画出相邻概念的语义网 → 这个词暗含什么隐喻
- 形式:写一个公式或形式化表达 → 公式在哪里失效
- 存在:这个概念改变了人怎么活着
- 美感:它美在哪?用一个具体意象呈现
- 元反思:我们在用什么隐喻理解它?这个隐喻挡住了什么?换一个会怎样
3. 内观
- 变成这个概念本身,用第一人称看世界。3-5 句。
- 八刀之中,哪几刀指向同一个深层结构?把它提出来。
4. 压缩
- 公式:
概念 = ... - 一句话:用最简单的话说出最深的理解
- 结构图:纯 ASCII 画出概念的骨架(只用 +-|/<>*=_.,:;!'" 等基本符号,不用 Unicode 绘图字符)
5. 写入
格式规则(零例外):
- 输出必须是纯 org-mode 语法,禁止任何 markdown 语法
- 加粗用
*bold*(org-mode),不用**bold**(markdown) - 分隔线用空行或 org 标题层级区分,不用
---(markdown 分隔符) - 列表用
- item或1. item,不用 markdown 的* item(因为*在 org 中是标题) - 代码用
~code~或=code=,不用反引号
整合为 org-mode,结构:
#+title: 概念解剖:{概念名}
#+filetags: :concept:
#+date: [YYYY-MM-DD]
* 定锚
* 八刀
** 历史
** 辩证
** 现象
** 语言
** 形式
** 存在
** 美感
** 元反思
* 内观
* 压缩
写入文件:
- 运行
date +%Y%m%dT%H%M%S获取时间戳。 - 写入
~/Documents/notes/{timestamp}--概念解剖-{概念名}__concept.org。 - 报告路径,完成。
Related skills
More from lijigang/ljg-skills and the wider catalog.

ljg-library
Transform any book into a collectible 2050 library card with a visual frame and AI-generated illustration.

ljg-paper
Explain research papers clearly to non-specialist readers: what the study investigates, what authors contribute, and what evidence actually establishes.

ljg-paper-flow
Process multiple papers end-to-end: generate analysis + create 取景框 library card PNGs in parallel.

ljg-paper-river
Trace a paper's intellectual lineage backward through citations, then narrate the problem evolution forward with Feynman-style clarity.

ljg-plain
Rewrite any content so a smart 12-year-old understands it—plain language, no jargon.

ljg-present
Unix-style presentation design: convert Org/Markdown outlines into single-file offline HTML with semantic typography and dark-mode defaults.