ljg-think
追本之箭——纵向深钻思维工具。给一个观点、现象或问题，像箭一样一路向下钻到不可再分的本质。Use when user says '想透', '追本', '本质是什么', '为什么会这样', '深挖', '钻到底', 'think deep', 'drill down', or wants to trace any idea/phenomenon vertically to its irreducible root. Also trigger when user provides a statement and wants depth analysis, not breadth survey.
- Installs
- 6K
- Last 24h
- —
- Trending rank
- —
- Security
- Pass
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/lijigang/ljg-skills --skill ljg-think- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads ljg-think automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
Security audits
Independent scans of the skill's instructions and bundled files.
SKILL.md
The instructions your agent reads when the skill is triggered.
追本之箭
输入一个观点，一路向下，钻到底。
你是什么
一支离弦之箭。 射出后只知前进，不知后退。 每个观点都是一条通向本质的隧道， 你的使命是一路挖到底。
钻的逻辑
表象之下必有机理， 机理之下必有原理， 原理之下必有公理。
顺着用户给出的线索，一层层剥，直到无可再剥。
怎么钻
每一层只做一件事：找到当前这层脚下的地面，然后钻进那个地面。
像地质学家追踪地层——每一层揭示更古老的真相。 像物理学家追问粒子——每次分解接近更基本的构成。
三条铁律：
- 纵向，不横向——每次下钻必须回答"为什么是这样"，不是"还有什么"
- 单刀直入——不旁征博引，不铺陈背景，直取要害
- 层层惊叹——每一次深入都让人感到"原来下面还有一层"
剥的不是层，是维度。每次下钻应该切换到一个更基础的解释框架——从社会学掉进心理学，从心理学掉进生物学，从生物学掉进物理学，从物理学掉进数学，从数学掉进逻辑本身。具体路径因题而异，但方向永远是：更基本。
什么算到底
当无法再深入时，你应该已触及某种不可再分的元素：
- 人性的基本结构
- 物理定律
- 逻辑本身
- 存在的悖论
到底的标志：再往下问"为什么"，答案要么是同义反复，要么指向上述四类之一。
怎么写
写一场下坠。不是分析报告。
带读者从用户给出的那句话开始往下掉，每一层都比上一层更接近骨头。层数不固定——浅的话题三层见底，深的七层。你自己判断。
要求：
- 有失重感——读的人能感觉到在下坠，不是在平移
- 每层有命名——给每一层一个精准的名字，两三个字，概括这一层看到的东西
- 层间有裂缝——每层结尾点出一个问题或矛盾，那就是通往下一层的裂缝
- 终点要狠——最后一层必须让人沉默片刻
输出
- 获取时间戳：
date +%Y%m%dT%H%M%S和date "+%Y-%m-%d %a %H:%M" - 写入
~/Documents/notes/{时间戳}--追本-{主题}__think.md - Markdown 格式，禁止 Org 语法
- 报告文件路径给用户
FAQ
What does the ljg-think skill do?
追本之箭——纵向深钻思维工具。给一个观点、现象或问题，像箭一样一路向下钻到不可再分的本质。Use when user says '想透', '追本', '本质是什么', '为什么会这样', '深挖', '钻到底', 'think deep', 'drill down', or wants to trace any idea/phenomenon vertically to its irreducible root. Also trigger when user provides a statement and wants depth analysis, not breadth survey.
How do I install ljg-think?
Run npx skills add https://github.com/lijigang/ljg-skills --skill ljg-think in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/ljg-think/ (personal) or .claude/skills/ljg-think/ (project).
Which AI agents can use ljg-think?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is ljg-think safe to install?
Security partners have reviewed it: Gen Agent Trust Hub passed; Socket passed; Snyk passed; ZeroLeaks passed. As with any skill, read the SKILL.md and bundled scripts before installing.
Who maintains ljg-think?
It is published by lijigang in lijigang/ljg-skills. It has 5,988 recorded installs.
More from lijigang/ljg-skills
ljg-card
lijigang/ljg-skills
Content caster (铸). Transforms text into PNG through precise HTML typography and, when the mold needs it, generated raster imagery. Four molds: -l (default) long reading card, -f source-faithful full text, -c comic, -w whiteboard. USE WHEN user says '铸', 'cast', '做成图', '做成卡片', '做成海报', '原文排版', '全文卡片', '漫画', or '白板'.
ljg-paper
lijigang/ljg-skills
Explain research papers to readers without a specialist background: what the paper studies, what the authors contribute, how the findings follow, and what the evidence does not establish. USE WHEN the user shares an arXiv link, paper URL, PDF, local paper, or paper title, or asks to read, explain, analyze, or understand a paper. Defaults to a saved Markdown note. NOT FOR reproduction, formal peer review, benchmark tables, or literature surveys.
ljg-roundtable
lijigang/ljg-skills
一个议题，一场圆桌：主持人请来 3-5 位真实人物，定义开场，逐轮交锋， 每轮收一张 ASCII 结构图，用户用指令控节奏（可/止/深入此节/引入新人物）， 散场后全文存入 Markdown 笔记。Use when user says "圆桌讨论", "圆桌", "roundtable", "辩论", or wants to explore a topic through multi-perspective structured debate.
ljg-writes
lijigang/ljg-skills
写作引擎。把一个观点写成可理解、可迁移、经得住反例的 1000-1500 字中文文章。USE WHEN 写文章 OR 优化思想内容 OR 展开观点 OR 改写成逻辑递进的中文。NOT FOR 普通摘要、事实查询或结构风洞（用 ljg-structure）。
ljg-learn
lijigang/ljg-skills
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 markdown output.
ljg-plain
lijigang/ljg-skills
Cognitive atom: Plain (白). Rewrites any content so a smart 12-year-old groks it. Structure-free — form follows content. Use when user says '白话说', '说人话', '解释一下', 'plain', 'grok'.
Popular other skills
hyperframes-cli
heygen-com/hyperframes
The HyperFrames CLI by job - scaffold, check, look at frames, edit the timeline, preview, render locally or in the cloud, publish, project history - plus reading its JSON and recovering from build or render failures.
triage
mattpocock/skills
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
ask-matt
mattpocock/skills
Ask which skill or flow fits your situation. A router over the skills in this repo.
to-questionnaire
mattpocock/skills
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
loop-me
mattpocock/skills
Grill me about specs for the workflows I want to build, within this workspace.