ljg-skills is a collection of custom Codex skills for tasks such as learning, writing, reading, relationship analysis, image creation, and investment analysis. Codex users install selected skills or the whole collection through a skills command-line interface. The catalogue entries are the collection's individual skills, plugin, and instruction.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add lijigang/ljg-skills --skill ljg-isgit clone --depth 1 https://github.com/lijigang/ljg-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lijigang/ljg-skills/ljg-is)<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-is"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-is/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-is"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-is.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00140 | $0.01709 |
| Opus 5 | $0.00070 | $0.00855 |
| Sonnet 5 | $0.00028 | $0.00342 |
| Haiku 4.5 | $0.00014 | $0.00171 |
Grade A, and why
ljg-is scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
把一个名词讲到能用
只给定义,读者可能记住了词,却仍不知道怎样认出它。只讲动词,读者又可能知道它做了什么,却不清楚它究竟是哪一类东西、边界在哪里。
ljg-is 把两者接起来:名词回答「它是什么」,让概念在认知地图里站稳;动词回答「它怎样起作用」,让概念在现实里动起来。真正完成的理解还要继续走一步:它改写了读者原来的什么判断,下次遇到它时又能怎样行动。
它是什么,和什么不一样?
它靠什么动作产生结果?
知道这一点后,我不再怎样想?
下次遇到它,我先看什么、怎样做?
这四个问题是一条理解路径,不是四个正文栏目。文章要像一个人顺着疑惑把事情讲明白,而不是把答案依次填进表格。
赵汀阳的「动词」思想在这里仍然重要,但它是一副有条件的透镜。面对制度、平台、角色或规范,可以继续追问谁选择了这种做法,它怎样改变参与者;面对目标函数、递归这类技术概念,动词首先是对象自身的运算与作用。材料没有显示社会反制,就不把技术说明硬拽成制度批判。
Workflow Routing
| Workflow | Trigger | File |
|---|---|---|
| UnderstandInUse | 把「是什么」与「怎样运作」接成可辨认、可判断、可行动的 Org 解读 | Workflows/TraceCreation.md |
成品标准
一篇合格解读会让读者发生四个连续变化:
-
能用一句普通话说出 X 属于什么,以及它与最容易混淆的对象差在哪里。定义要给边界,不能只给比喻或用途。
-
能顺着一个真实例子说明 X 怎样起作用。技术概念讲清输入、关键动作和结果;制度概念讲清参与者、规则怎样进入行动以及实际后果。只写对象真正具有的机制。
-
能指出自己原来哪种看法需要修改。认知变化必须由前面的定义和机制推出,不另起炉灶追求「深刻」。
-
能在一个具体情境里使用这番理解。行动指导要说清先看什么、怎样判断、何时调整,并能解释为什么。
正文从一个普通读者真的会有的疑惑、误解或使用场景进入,不强制编造人物故事。概念要尽早出现,例子负责验证解释,不负责制造戏剧性。
最后可以落在一句判断、一个行动原则或一个真实未决问题上。哪一种自然,由前文决定;问号不是深度证明。
默认写入:
~/Context/{时间戳}--理解-{目标片段}__is.org
新成品使用 ljg-is-v5 schema。正文使用两到四个随内容生出的标题和四到十个自然段,不把「是什么 / 怎样运作 / 认知改变 / 行动指导」直接用作四个栏目。
判断边界
-
定义与理解不同。 用户若只要形式化定义、公式证明或术语翻译,直接回答即可;只有当他想理解概念如何工作、意味着什么或怎样使用时,才进入本技能。
-
动词不等于社会创制。 技术对象可以通过计算、映射、比较、压缩或递归起作用,不必虚构一个创造者故事。制度对象才追问选择者、规则与反作用。
-
行动指导不是操作手册。 本技能给判断抓手,不替代某个软件、流程或行业的逐步教程。
-
理由不能伪造。 区分材料支持的事实和分析者的推断。不知道就缩小判断,不替人物补写动机,也不把一般机制冒充具体案例事实。
Gotchas
-
不要把新合同写成新清单。 「定义、机制、启发、建议」若各占一栏,文章仍然生硬。它们应当像一条推理:因为 X 是这样运作的,所以原来的判断不够准确,下一次才应当这样做。
-
不要只给用途当定义。 「目标函数用来优化」没有说明它是什么;要补上它怎样给候选方案建立可比较关系,读者才可能把它与约束、指标或奖励区分开。
-
不要强制具体场景。 一个真实疑惑往往比虚构工程师或司机更自然。只有当人物行动确实承载机制时才使用故事。
-
不要强造赵汀阳式转折。 未选可能、反制、本源和未来不是必填项。它们只有能解释对象,并且有现实根据时才进入正文。
-
不要在结尾突然升级尺度。 前文讲算法,结尾忽然质问社会正义,通常不是深刻,而是换了问题。认知改变与行动指导必须能够逐句追溯到已经讲清的机制。
-
不要给万能建议。 「保持关注」「综合考虑」「具体问题具体分析」删除概念名后仍然成立,说明它没有使用前文的理解。
-
不要让元数据替正文说话。
definition、operation、recognition与guidance是后台索引;正文可以用更自然的说法,但全文读回必须找到同一内容。
Examples
目标函数
不要写:目标函数是优化的灵魂,它最终会反过来支配设计者。
可以写:目标函数是一把供求解过程比较方案的尺子。它给每个候选方案一个
可比较的结果,让程序知道往哪边改进。因此看到「最优」时,先补问一句:
这是按照哪把尺子得到的最优?
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 110 lines · 140 tokens per session scan A c3490ae27d2a
ljg-is is a skill published in the GitHub repository lijigang/ljg-skills (7,340 stars, last pushed 3d ago), licensed MIT. It adds 140 tokens to every session and 1,709 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.