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-readgit 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-read)<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-read"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-read/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-read"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-read.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 | $0.00113 | $0.02376 |
| Opus 5.5 | $0.00045 | $0.00950 |
| Sonnet 5.5 | $0.00023 | $0.00475 |
| Haiku 4.5 | $0.00011 | $0.00238 |
Grade A, and why
ljg-read 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 26d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ljg-read · 伴读
把一段文本讲到读者能看见它说的事情、认出其中的概念、跟上关键推理,并知道换个情境还能不能成立。默认完整讲解当前所给文本,直接在对话中展示。
Workflow Routing
| 请求 | 执行 |
|---|---|
| 粘贴文本、提供文件或 URL,希望讲透 | 按「下上结构」与「讲解约定」交付 |
| 「快进」「展开」「等一下」或希望提问伴读 | 按「可选交互」调整当前讲解 |
| 明确要求保存 | 按用户指定位置与格式保存;未要求时只在对话中展示 |
《学习观》的下上结构
依据于建国《学习观:从感觉懂了到真正学会》关于「下上结构」、判别模型、联结模型与学习验证的论述。以下是用于伴读的转述;讲解安排是本技能的应用设计。
下层是实际问题,上层是理解问题的工具。 下层放这次要理解的具体对象、情境及其变化;上层放相关概念与概念之间的通用关系。作者将「下」放在前面,强调实际问题优先。两层是相对的:这次作为工具的概念,换个问题也可以成为研究对象,不能把「下」固定成物质、「上」固定成语言。
判别模型接通对象与概念。 它回答「眼前这个情况,凭什么算这一类?」讲一个概念时,要让读者看见所指、归类依据,以及容易混淆的边界。定义或名称本身不足以证明读者能在新情境认出它。
联结模型接通概念之间的关系。 它回答「知道了这一类情况,在什么条件下能推出什么?」归类正确与关系成立要分别说明;会背规律不保证会识别适用场景,认出类别也不自动证明规律。
材料和验证承担不同作用。 具体例子帮助建构,抽象表述帮助整理,未见情况用来检验迁移。复述已讲例子不足以证明会迁移;给出新情境、请读者判断并观察回答,才可能发现理解断在哪里。没有读者反馈时,只能说讲解提供了迁移检查,不能声称读者已学会。
讲解约定
原文与范围
- 先读到实际内容。粘贴文本直接使用;文件读取指定内容;URL 用当前可用的网页获取能力。拿不到正文时说明缺口,不根据标题或摘要补写全文。
- 围绕用户给定范围讲解。短段可直接深入;长文按完整语义单元组织,保留主线、重要分支与转折,不逐句平均用力,不切断承重论证。
- 中文直接解释。英文先给自然、准确的中文译文,保留影响判断的英文短句或术语作为校验锚点;仅在语言歧义、行话或文化典故影响理解时补充说明,不固定叠加三套翻译。
把下层与上层接通
先用一句普通话点明作者在回答什么问题、作出什么判断。随后围绕承重处展开,通常从一个能看见细节的情境进入,再提炼概念与关系,最后回到具体情境说明所得判断。安排随文本而变;以下是讲清楚的要求,不是必须逐项打印的栏目。
- 让事情可见。 优先使用原文例子;原文太抽象时补一个贴近日常的教学设例,并就地标明。例子有具体的人或对象、条件、变化与结果;「好人也会死」这类只给抽象词加限定的句子,不能替代真正的下层材料。
- 让概念可辨。 用普通话说明关键概念是什么、与相邻概念差在哪里。结合例子指出哪些事实使它属于这一类;容易误认时给一个只差关键条件的近邻情境。仅有描述或比喻时,保留其模糊处,不替作者发明精确标准。
- 让关系可追。 把作者从前提走到结论的关键一步展开,说明中间发生了什么、依靠哪些条件。区分定义、分类、相关、因果、类比、价值判断和行动主张;箭头或公式按实际关系使用,不把所有文字改造成因果定律。
- 让两层对得上。 明说例子里的什么对应哪个概念,凭什么对应;若有预测,再说明如何使用关系、所得结果在例子里意味着什么。不能从生活故事直接跳到大道理,也不能把抽象结论换个说法就当作讲解。
- 让边界改变判断。 选能触及承重前提的条件变化、反例或未决处,说明它使归类变化、关系失效,还是只收窄结论。原文没有足够依据时留下未知,不为了完整替作者补成已证实的机制。
- 让迁移可检查。 适合迁移的内容可收一个与已讲例子不同的小情境,让读者判断「是否适用、依据是什么、能推出什么」。默认可附简短参考分析;若用户选择互动自测,先只给题,等其回答再反馈。答案揭晓后,该题就属于讲解材料。
论证文本重在概念、依据与推理;叙事或抒情文本重在具体处境、人物变化、意象与表达效果。解释人物动机时区分原文所示与推测,诗意和多义性可以保留,不强求预测公式或唯一答案。
对话成品
默认中文 Markdown,以连贯段落讲解。短文本不硬分章;长文本用贴合内容的小标题。并列比较才用表格,承重关系确实难以看清时才加简短文本图或公式;符号先解释,再使用。
正文应让读者看见原文的主要意思、概念与情境的对应、推理的成立条件,以及一个足以改变判断的边界。结尾用一句话收住最值得带走的理解;不例行堆术语表、延伸书单或强制读后提问。
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.
- 26d ago Changed · -186 lines · +7 tokens per session 9d43696fda00
- 1mo ago First seen · 274 lines · 106 tokens per session scan A 07c9138e6675
ljg-read is a skill published in the GitHub repository lijigang/ljg-skills (7,571 stars, last pushed 2d ago), licensed MIT. It adds 113 tokens to every session and 2,376 once invoked, about $0.0005 per session on Opus 5.5. 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
toolbox-talk-generator
Generate safety toolbox talks for construction crews. Create contextual safety briefings based on weather, work activities, and recent incidents. Support multiple languages.
wjs-explaining-tv-slang
A guide for explaining American or British television and film lines, idioms, slang, and jokes in context. It covers what the words mean, what the speaker is doing with them, their tone, and when they are appropriate.
lov-subtitle-freedom
Create learner-friendly English subtitles with level-aware glosses and optional spoiler-safe subtitle sidecars.
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
stage-and-commit
Stage changed files and create a commit following the repo's translation, formatting, and git workflow rules. Use when the user asks to stage, commit, or both.
bilingual-courseware
A system for maintaining university course materials in two languages, usually English and Simplified Chinese. It keeps terminology, teaching expectations, and matching versions aligned.