Ljg Learn
- 5.9k installs
- 6.7k repo stars
- Updated August 4, 2026
- lijigang/ljg-skills
ljg-learn is an agent skill for Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, m
About
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 --- 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'. --- ## 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. 八刀 八个方向各切一刀。每刀 2-3 句，只留筋骨，不带水分。 1. **历史**：最早从哪冒出来 → 怎么变的 → 哪一步拐成了今天的意思 2. **辩证**：它的反面是什么 → 正反碰撞后，更高一层的理解是什么 3. **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 4.
- 这个概念最通行的定义是什么？常见误解在哪？
- **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
Ljg Learn by the numbers
- 5,946 all-time installs (skills.sh)
- +102 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #85 of 2,245 Frontend Development skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
ljg-learn capabilities & compatibility
- Capabilities
- 这个概念最通行的定义是什么？常见误解在哪？ · **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
- Use cases
- documentation
What ljg-learn says it does
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'.
--- ## 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.
npx skills add https://github.com/lijigang/ljg-skills --skill ljg-learnAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 5.9k |
|---|---|
| repo stars | ★ 6.7k |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 4, 2026 |
| Repository | lijigang/ljg-skills ↗ |
When should developers use ljg-learn and what problem does it solve?
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and
Who is it for?
Developers working with ljg-learn patterns described in the skill documentation.
Skip if: Skip when cached docs are empty or the task is outside the skill's documented scope.
When should I use this skill?
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and
What you get
Grounded guidance and workflows from SKILL.md for ljg-learn.
- Org-mode concept anatomy report
- Epiphany insight summary
By the numbers
- Uses eight exploration dimensions for concept dissection
- Allocates two to three sentences per dimensional analysis before final synthesis
Files
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
1. 这个概念最通行的定义是什么？常见误解在哪？ 2. 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。
1. 历史：最早从哪冒出来 → 怎么变的 → 哪一步拐成了今天的意思 2. 辩证：它的反面是什么 → 正反碰撞后，更高一层的理解是什么 3. 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 4. 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 5. 形式：写一个公式或形式化表达 → 公式在哪里失效 6. 存在：这个概念改变了人怎么活着 7. 美感：它美在哪？用一个具体意象呈现 8. 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
1. 变成这个概念本身，用第一人称看世界。3-5 句。 2. 八刀之中，哪几刀指向同一个深层结构？把它提出来。
4. 压缩
1. 公式：概念 = ... 2. 一句话：用最简单的话说出最深的理解 3. 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： 1. 运行 date +%Y%m%dT%H%M%S 获取时间戳。 2. 写入 ~/Documents/notes/{timestamp}--概念解剖-{概念名}__concept.org。 3. 报告路径，完成。
Related skills
Vercel React Best PracticesAutomatically apply Vercel’s official React and Next.js performance rules during code generation and review.587k29.6kVercel Composition PatternsGenerate and refactor React components that stay maintainable as complexity grows without boolean prop explosion.267k29.6k
ShadcnAdd, compose, search, fix, and style production-grade React components directly from source without leaving their editor.257k120k
Develop UserscriptsCorrectly write, debug, and package userscripts for Tampermonkey and ScriptCat with proper metadata, GM APIs, and runtime decisions.224k72
Minimalist UiGenerate clean, editorial-style web interfaces with warm monochrome palettes, typographic hierarchy, bento grids and flat components that feel premium and utilita212k69.4kImage To CodeConvert high-fidelity design images into production-ready, visually accurate frontend code that avoids generic AI design pitfalls.177k69.4kFAQ
What does ljg-learn do?
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights
When should I invoke ljg-learn?
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights
Where is the source documentation?
Ground claims in SKILL.md excerpts and linked reference files from the cached docs.
Is Ljg Learn safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.