Agent skill · Audited from source
ljg-think
skill · lijigang/ljg-skillsMIT licenceAudited 14 Nov 2026 · source 0575fc3a74e1
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 0575fc3a74e1 and found no filesystem, network or shell access and no hard-coded secrets. What it does: 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…
Cite
Cite this page
ModelsAtlas. “ljg-think (lijigang/ljg-skills)”. Retrieved 14 Nov 2026. https://modelsatlas.com/skills/lijigang/ljg-think
Trust audit
Audit 0.4.1 · source read 14 Nov 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (0)
No findings at any severity. We re-audit when the source changes.
Audit 0.4.1 · source sha 0575fc3a74e1 · 14 Nov 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisherlijigang GitHub userOwner of the repository this skill is read from
- Source folderlijigang/ljg-skills/skills/ljg-thinkThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdict0575fc3a74e1A new audit runs when the source changes
- Repository statusNot archivedLast push 11 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: 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…
---
name: ljg-think
description: 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.
user_invocable: true
---
# 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.md`
3. Markdown 格式,禁止 Org 语法
4. 报告文件路径给用户Excerpt, first 1,312 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 0575fc3
git clone https://github.com/lijigang/ljg-skills git -C ljg-skills checkout 0575fc3a74e1
The author documents no install command, so this uses the repository directly. Our verdict covers commit 0575fc3a74e1 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
0575fc3a74e1
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/lijigang/ljg-think/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
mattpocock/skills
Implement a piece of work based on a spec or set of tickets.
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
mattpocock/skills
Pursue a long-running goal in a single session by co-ordinating subagents.
Add this badge to your README
[](https://modelsatlas.com/skills/lijigang/ljg-think/)
<a href="https://modelsatlas.com/skills/lijigang/ljg-think/"><img src="https://modelsatlas.com/skills/lijigang/ljg-think/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about ljg-think
Is ljg-think safe to install?
What can ljg-think access on my machine?
How current is this page?
Sources
- github.com/lijigang/ljg-skills/tree/master/skills/ljg-think — the audited source at commit 0575fc3a74e1 and every finding aboveObserved · 14 Nov 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- Is ljg-think safe to install?
- What can ljg-think access on my machine?
- How current is this page?