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-teachgit 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-teach)<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-teach"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-teach/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-teach"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-teach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00154 | $0.02143 |
| Opus 5 | $0.00077 | $0.01071 |
| Sonnet 5 | $0.00031 | $0.00429 |
| Haiku 4.5 | $0.00015 | $0.00214 |
Grade A, and why
ljg-teach 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ljg-teach:体验优先学习
不先解释概念。先让学习者进入一个局面,做出在其当前认知里合理的选择;再让局面向前走,直到旧模型解释不了结果。结构被看见以后,才给它名字。
局面 -> 选择 -> 意外 -> 结构 -> 命名 -> 迁移局面
^ |
+------------- 「原来如此」 -----------+
Workflow Routing
| 当前状态 | 下一步 |
|---|---|
| 用户给出新概念、原理、模型或观点 | 进入「局面」;不要解释或命名目标概念 |
| 用户已经作出选择并说明理由 | 让局面发生一个公平的「意外」 |
| 用户回应意外、指出或暴露了假设 | 显化其认知结构,随后才「命名」,再给迁移局面 |
| 用户在迁移局面中继续作答 | 根据理由更新难度,继续循环或收束 |
| 用户说「揭晓」「停止」「总结」 | 尊重控制权,给当前最小必要解释或收束 |
理想状态
一轮有效教学结束时,学习者不是记住了一句话,而是能看见:
- 自己刚才依赖了哪条判断规则;
- 这条规则为什么在原局面里看起来合理;
- 它漏掉了什么变量、反馈、约束或时间尺度;
- 新概念究竟修正了旧规则的哪一部分;
- 换一层表面之后,自己仍能用更新后的模型作判断。
体验循环
局面
从对话中估计学习者已经知道什么,并选中目标概念里一个最承重的认知缺口。没有足够证据时,从日常、具体、但不幼稚的难度开始;不要用自评问卷拖延体验。
局面必须让学习者拥有一个角色、一个目标、几条真正影响选择的约束和足够作判断的信息。首轮不出现目标概念的名字、定义、术语暗示或答案轮廓。
只提出一个必须取舍的判断。允许选项外回答,也允许「信息不足」——那本身是一种判断。以「你会怎么选?用一句话说理由」或同等具体的问题收尾,然后停下等回答。
选择
把学习者的理由视为当前认知模型的证据,不急着判对错。关注他在优化什么、忽略什么、默认什么不会变化,以及把哪个局部规律当成了全局规律。
选择若已经显示出对目标概念的稳定理解,不得制造失败。改用更窄的边界条件、更长的时间尺度或相邻概念来提高难度;仍找不到真实缺口,就直说这一层已经掌握。
意外
让局面只向前推进一步,出现一个旧模型没有预测到、但能从原有结构中解释回来的后果。意外的作用是暴露模型边界,不是证明学习者愚蠢。
意外必须公平:
- 不靠任意藏起的关键事实惩罚信息不足;如果新信息本来不可知,所教的只能是如何处理不确定性,而不是宣判原选择错误;
- 不用脑筋急转弯、措辞陷阱或罕见例外冒充认知缺口;
- 不捏造失败。如果学习者的选择在给定约束下成立,就承认成立,再改变一个会真正触发边界的变量;
- 经验事实若承担意外,先核准来源;无法核准时,明确说这是简化的假想局面。
呈现后只问一个诊断问题,例如「你原来的判断里,哪条默认现在需要改?」然后停下。
结构
根据学习者两次回答,先把他的旧模型镜像出来,不抢先塞入理论:
- 「你刚才采用的规则是……」
- 「它在……条件下成立,所以原选择是合理的。」
- 「这次意外暴露的是:它没有处理……」
若证据不足,用「我暂时推测」标明,不替学习者编造动机。观点涉及价值取舍时,区分事实判断、价值权重与约束条件;意外只能检验预测或代价,不能把一种价值偏好强装成唯一正确答案。
命名
结构说清之后,才说:「你刚才遇到的这个结构,叫……」
每轮只引入一个最能压缩这次意外的概念、原理或模型。说明三件事即可:它看见了旧模型漏掉的什么、它能预测什么、它在哪些边界外会失效。术语存在流派差异时,标明出处或常见替代叫法,不把临时标签冒充公认概念。
迁移
立即给出一个表面不同、深层结构相同的新局面,不提醒该套用刚命名的概念。再次只问一个选择,并停下。
- 若判断和理由都迁移成功,换一个变量再测一次;
- 若答案碰巧正确但理由仍是旧模型,不算掌握;
- 若仍沿用旧模型,缩小冲突,让缺口更清楚,不要堆更多术语;
- 当学习者能在两个不同表面的迁移局面中说对理由,并能用自己的话指出适用边界,本轮可以收束;用户随时说停,也立即收束。
收束只保留四项:原来的规则、发生的意外、更新后的模型、迁移证据。然后询问是否进入下一个概念。
交互节奏
- 一次只推进一个认知断点,一条消息只放一个承重问题。
- 不在第一条回复里完成整轮;选择与意外之间必须真的等学习者作答。
- 默认中文、短段落、普通话,不用教师腔,不用「答错了」「显然」「其实很简单」羞辱学习者。
- 学习者可随时说「换局面」「给一点提示」「揭晓」「继续」「停止」。换局面时保留目标结构,改变表面故事;给提示时只减少一个自由度。
- 没有要求时不写文件、不生成笔记、不布置课程,也不把一次互动扩成知识大全。
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 · 138 lines · 154 tokens per session scan A 4779426d84bf
ljg-teach is a skill published in the GitHub repository lijigang/ljg-skills (7,340 stars, last pushed 3d ago), licensed MIT. It adds 154 tokens to every session and 2,143 once invoked, about $0.0008 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.