Ljg Think
- 5.4k installs
- 6.7k repo stars
- Updated August 4, 2026
- lijigang/ljg-skills
ljg-think is a user-invocable agent skill that vertically drills one idea or phenomenon to its irreducible root and saves the descent as an org-mode note.
About
The ljg-think skill, titled Arrow of Root-seeking, is a user-invocable vertical thinking tool for drilling one claim, phenomenon, or question down to an irreducible root. Instead of surveying breadth, each layer answers why this is so, peeling appearance into mechanism, principle, and axiom until logic, physics, human nature, or paradox blocks further descent. Writing reads like a fall: named layers, cracks that open the next question, and a silent-ending terminus. Three iron rules enforce vertical-only descent, direct focus without background padding, and surprise at each deeper stratum. Dimensions shift across frameworks such as sociology to psychology to biology to physics to mathematics to logic. On completion the agent timestamps the session, writes an org-mode file to ~/Documents/notes/{timestamp}--追本-{topic}__think.org without markdown syntax, and returns the saved path to the user.
- Vertical drill from surface claim to irreducible root cause or axiom.
- Layered narrative with named strata, cracks, and a hard silent endpoint.
- Triggers on 想透, 追本, think deep, drill down, and depth-not-breadth requests.
- Dimension shifts across progressively more basic explanatory frameworks.
- Persists org-mode notes under ~/Documents/notes with timestamped filenames.
Ljg Think by the numbers
- 5,437 all-time installs (skills.sh)
- +93 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #109 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
ljg-think capabilities & compatibility
- Capabilities
- single thread vertical why descent across named · framework shifts toward more basic explanatory d · org mode note export with timestamped filename u
- Use cases
- research · planning · documentation
What ljg-think says it does
写一场下坠。不是分析报告。
写入 `~/Documents/notes/{时间戳}--追本-{主题}__think.org`
npx skills add https://github.com/lijigang/ljg-skills --skill ljg-thinkAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 5.4k |
|---|---|
| repo stars | ★ 6.7k |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 4, 2026 |
| Repository | lijigang/ljg-skills ↗ |
How do I trace why something is true layer by layer instead of collecting parallel opinions or surface explanations?
Vertical deep-drill analysis that traces a claim or phenomenon down to irreducible roots and saves an org-mode note.
Who is it for?
Users who want depth analysis, root-cause excavation, or philosophical why drills on a single statement.
Skip if: Skip for breadth surveys, literature reviews, brainstorming lists, or tasks needing code or design deliverables.
When should I use this skill?
User says 想透, 追本, 本质是什么, 深挖, think deep, drill down, or asks for vertical depth on one claim not a wide survey.
What you get
A layered fall narrative ending at logic, physics, human nature, or paradox, written to a timestamped org-mode file under ~/Documents/notes.
By the numbers
- Follows 3 strict drilling rules for vertical analysis
Files
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： 1. 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" 2. 单刀直入——不旁征博引，不铺陈背景，直取要害 3. 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
1. 获取时间戳：date +%Y%m%dT%H%M%S 和 date "+%Y-%m-%d %a %H:%M" 2. 写入 ~/Documents/notes/{时间戳}--追本-{主题}__think.org 3. org-mode 格式，禁止 markdown 语法 4. 报告文件路径给用户
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493kHow it compares
Pick ljg-think for one-thread root-cause depth; pick a research survey skill when you need breadth across many sources or options.
FAQ
How is ljg-think different from a broad research summary?
It drills vertically on one thread answering why, not what else exists; breadth surveys are explicitly out of scope.
Where does the output go?
An org-mode file at ~/Documents/notes/{timestamp}--追本-{topic}__think.org with no markdown syntax inside.
When has the drill reached the bottom?
When further why questions collapse to tautology or land in human nature, physical law, logic, or existential paradox.
Is Ljg Think safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.