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-structuregit 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-structure)<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-structure"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-structure/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-structure"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-structure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00121 | $0.02396 |
| Opus 5 | $0.00060 | $0.01198 |
| Sonnet 5 | $0.00024 | $0.00479 |
| Haiku 4.5 | $0.00012 | $0.00240 |
Grade A, and why
ljg-structure 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
母题结构风洞
输入一段信息,穿过表象找到它反复上演的母题,再把真正起作用的几根结构画清楚,送进风洞校准。默认结果要轻:读者带走一个说得明白的母题、一张能运行的关系图、一个既能迁移又会改口的结论。
四个概念,不能混
- 主题:信息在谈什么对象,如「团队讨论」「AI 注意力」。它只圈定语义范围。
- 母题:不同领域反复遭遇的同一类根本困境。它不是把原题换成更大的抽象词,而是用更普通的话保留那条可迁移的关系。
- 类比:两个案例看起来相像,如「团队像陪审团」。它只是发现入口。
- 结构:删掉领域名词后仍成立的因果骨架。它说明什么关系会生成什么结果。
一句话:主题是名字,母题是难题,类比是线索,结构是因果机器。
理解契约
结构分析不是让读者记住一组抽象名词,而是让他能在心里把关系跑一遍。完成的解读必须做到:
- 概念明确:每个承重概念都能用普通话说明「这里具体指什么」,并给出一个可见标志。
- 关系明确:读者能复述「在什么条件下,谁怎样影响谁,先出现什么变化,最后得到什么结果」。
- 示例承载关系:例子不只让人觉得相似;其中的角色、作用方向和结果都能对应抽象关系。
- 边界可以判断:条件变化时,读者能预判关系会怎样变化,也知道什么观察会迫使自己修改判断。
案例负责让模型运行,不负责证明模型普遍为真;风洞负责在内部改变条件、寻找边界和校准判断,最终只把有信息量的试压结果交给结论。
风洞如何进入结论
- 风洞是内部方法:沿用同一个示例,改变一个关键条件,观察预测怎样变化,并找出模型何时失效、什么信号会让判断改口。它不再单列为可见章节。
- 结论是校准后的交付物:先呈现同一示例在条件变化后的关键差异,给读者具体抓手;再把差异压成一条可迁移的抽象规则,回到原现象说明现在应该看见什么。
风洞的完整推演留在内部,结论只带出最能区分模型的条件变化、边界或改口信号。它们与抽象规则必须形成递进,而不是把同一因果链说两遍。
适用边界
适合:问题机制不明、现成方案贫乏、多个现象彼此牵动,或需要超出普通 AB 测试的探索。
不适合:纯事实查询、只有一个确定步骤的执行题、输入中没有可识别的困境。医疗、法律、安全等高风险领域可以借结构生成假设,但不能用类比代替本领域证据。
Workflow Routing
| Workflow | Trigger | File |
|---|---|---|
| FindStructure | 从信息中找母题、结构关系与风洞实验 | Workflows/FindStructure.md |
Gotchas
- 「团队沟通」「AI 认知」仍是主题;「怎样做得更好」又宽得没有约束。母题必须保留真正的关系或张力。
- 母题不是更抽象的标题。若一句母题仍含两个以上无法用普通话解释的承重词,先解码,再输出。
- 母题下只放一个最小示例,用来让关系第一次运行;不要展开跨域案例清单。
- 默认只设一个贯穿全文的示例锚点。结构卡指回其中的具体瞬间,关系图串起全局,风洞改变它的条件;不要在四处重讲同一个故事。
- 「像免疫系统」「采用双盲」只是来源或方案名。拿掉来源名后仍能说清因果,才叫结构。
- 跨域搜索是内功,不是默认目录。把三个领域逐项铺开,往往只会压住真正的母题。
- 结构卡默认只留一至两个,第三个必须证明不能并入前两者。每张卡都要完成「概念明确、关系明确、示例映射」,但不强制显示成三个字段。
- 例子必须映射角色与因果。只说「这像某某」会制造熟悉感,不会让关系变明确。
- 有多个结构时,先判断它们是串联、并联、嵌套、制衡还是反馈,再画图;不要看到多个结构就排成链。
- 默认不做笛卡尔积、不算组合数。多母题也先找结构关系;只有用户明确要求组合时才展开。
- 风洞是方法,不是章节。它先锁定基准预测,再改变一个条件,比较最先出现的差异,最后指出适用边界和判断更新规则;成文只保留其中最能改变理解的一次试压。
- 结论不是全文摘要。它依次完成「具体试压 -> 抽象规则 -> 回到现象」,让例子提供抓手,让抽象关系获得迁移力。
- 具体试压与抽象规则必须递进:前者回答「条件变了会怎样」,后者回答「这说明哪条更一般的关系」。若两段只是换词复述,删掉较弱的一段。
- 最小可逆实验只用于行动问题。概念解读默认给判别检验,不把每个思想问题都改造成行动建议。
- 概念模型不能靠事后收窄边界逃避反例。先声明适用条件和区别性预测;边界外案例只负责画边界,不算支持或反驳。
- 风洞不引入一套新术语。若必须发明新概念才能解释试压结果,先回到结构卡重新解码。
- 证据边界只在结尾交代一次。不要在每张结构卡反复插入警告,打断推理。
- 不确定事实时,把它留在内部候选层;若必须输出,明确写成待核验,不把记忆中的故事当事实。
What ships with it
1 file 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 · 127 lines · 121 tokens per session scan A 76436d8d19f3
ljg-structure is a skill published in the GitHub repository lijigang/ljg-skills (7,327 stars, last pushed 3d ago), licensed MIT. It adds 121 tokens to every session and 2,396 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…