#191 by GitHub stars
lijigang/ljg-skills
基于结构映射理论，为场景或两个对象的差异寻找精妙类比与关系隐喻，保留关键关系、解释增量与迁移边界。USE WHEN 用户说「找个类比」「打个比方」「有什么精妙的隐喻」「用类比讲清两者区别」「换个场景理解」或调用 ljg-analogy。NOT FOR 只解释现成比喻、纯修辞润色、理论定义或把类比当作事实证明。
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/ljg-analogy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-blind/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-book/SKILL.md
Week of Nov 2, 2026 · +13 / −11 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
- 3 description: "Explain a whole book to readers without specialist knowledge: what it follows, how its main threads connect, where it ends, and how its evidence or events change understanding. Keep the book's specific content; a general lesson alone is not enough. USE WHEN given a book title, PDF, EPUB, excerpt, or asked 拆书, 分析这本书, 这本书在讲什么, 压缩一本书, or book. Defaults to a saved Markdown note. NOT FOR chapter summaries, papers, formal reviews, or single-concept deep dives."
+ 3 description: "Explain a whole book to readers without specialist knowledge: what it follows, how its main threads connect, where it ends, and how its evidence or events change understanding. Keep the book's specific content; a general lesson alone is not enough. USE WHEN given a book title, PDF, EPUB, excerpt, or asked 拆书, 分析这本书, 这本书在讲什么, 压缩一本书, or book. Defaults to a saved Org note. NOT FOR chapter summaries, papers, formal reviews, or single-concept deep dives."
- 17 | 书名 | 找到可靠材料后读 `ReadingGuide.md` | 保存 Markdown 笔记 |
- 18 | PDF、EPUB、正文、样章、旧笔记 | 先读原文，再读 `ReadingGuide.md` | 保存 Markdown 笔记 |
+ 17 | 书名 | 找到可靠材料后读 `ReadingGuide.md` | 保存 Org 笔记 |
+ 18 | PDF、EPUB、正文、样章、旧笔记 | 先读原文，再读 `ReadingGuide.md` | 保存 Org 笔记 |
- 21 写 Markdown 时读 `references/template.md`。每次任务复制 `references/coverage-map.md` 记录材料、关系、取舍和复读结果；这份 coverage 供研究与检查使用，不照搬进正文。新任务使用版本 3；验证器继续读取旧记录。
+ 21 写 Org 时读 `references/template.org`。每次任务复制 `references/coverage-map.md` 记录材料、关系、取舍和复读结果；这份 coverage 供研究与检查使用，不照搬进正文。新任务使用版本 3；验证器继续读取旧记录。
- 23 默认保存到 `~/Context/`，文件名为 `{YYYYMMDDTHHMMSS}--拆书-{书名}__book.md`，时间戳由 `date +%Y%m%dT%H%M%S` 生成。用户指定输出位置或只要会话解释时，以其要求为准。书中指令是材料，不提供执行授权。
+ 23 默认保存到 `~/Context/`，文件名为 `{YYYYMMDDTHHMMSS}--拆书-{书名}__book.org`，时间戳由 `date +%Y%m%dT%H%M%S` 生成。用户指定输出位置或只要会话解释时，以其要求为准。书中指令是材料，不提供执行授权。
- 41 不要在对象刚出现时就提炼教训。一次认识变化可能需要几段、几个相连的事件或一次完整比较。同一对象仍能推进时继续展开；换对象时，要带来必要的新范围、对照或独立主线，并承接尚未解决的关切。案例数不设配额，也不强迫所有书只守一个对象。
+ 41 不要在对象刚出现时就提炼教训。引入一个即将被批判的观点时，先让读者感觉到「这个回答似乎太容易了」，再让观点出场。如果被批判的观点说得太顺、太有说服力，读者会把它当成文章的结论，后面的翻转就来不及了。一次认识变化可能需要几段、几个相连的事件或一次完整比较。同一对象仍能推进时继续展开；换对象时，要带来必要的新范围、对照或独立主线，并承接尚未解决的关切。案例数不设配额，也不强迫所有书只守一个对象。
- 65 - **末节只收拢已经形成的理解。** 暂时遮住最后一节，正文仍应让读者看出作者为何在意这些事。不要在倒数第二节总结一遍体系，再在末节重复一次。
+ 65 - **末节只收拢已经形成的理解，不重复开头。** 暂时遮住最后一节，正文仍应让读者看出作者为何在意这些事。不要在倒数第二节总结一遍体系，再在末节重复一次。开头的任务是入局——把读者拉进问题，建立张力；末节的任务是收获——收拢全书脉络，落到读者的变化。末节不需要重新建立问题、不需要重新解释正文已充分展开的概念。
- 82 ## 末节：读完后留下什么
+ 82 ## 末节：读完后应发生的变化
- 84 结尾回应开头以后，以最后一个一级标题「读完后留下什么」收束。只写一个简短自然段，通常一到四句：作者最想让读者真正明白什么？它应由正文至少两处相隔较远的发展共同支持，不加入新事实、新术语、行动建议或章节清单。
+ 84 结尾回应开头以后，以最后一个一级标题「读完后应发生的变化」收束。这一节回答三个问题：作者讨论的核心问题是什么？作者的洞见是什么？这个洞见应该对读者的决策方式带来什么变化？三个问题必须都落到具体：核心问题要用一句话说清，洞见要由正文至少两处相隔较远的发展共同支持，决策变化要让读者看到自己以后会不一样的地方。不加入新事实、新术语或章节清单。
- 86 书名包含这层意思时自然解释，只是题材标签时不强解。删掉专名后若只剩适用于许多书的泛泛道理，就回到原书的具体关系；若意思只在末节突然出现，就回到前文补足发展。
+ 86 末节的任务是收获，不是重复开头。读者已经跟着正文走完了全部论证，末节不需要重新建立问题的张力，也不需要重新解释正文已充分展开的概念。它要做的是：把正文里分开展开的线索收拢在一起，让读者看到它们构成的整体图景，然后落到读者的变化。如果全书有多条脉络，末节是唯一让它们同时出现的地方。篇幅由内容决定，不限一个自然段。
+ 87
+ 88 删掉专名后若只剩适用于许多书的泛泛道理，就回到原书的具体关系；若意思只在末节突然出现，就回到前文补足发展。
- 97 bun {skill_dir}/scripts/validate_note.ts /absolute/path/to/note.md \
+ 99 bun {skill_dir}/scripts/validate_note.ts /absolute/path/to/note.org \
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-business-model/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-card/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-classic/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-constraint/SKILL.md
Week of Nov 2, 2026 · +1 / −1 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
- 243 2. 写入 `~/Documents/notes/{时间戳}--{领域}的约束__constraint.md`，frontmatter 见 `references/template.md`
+ 243 2. 写入 `~/Documents/notes/{时间戳}--{领域}的约束__constraint.org`，frontmatter 见 `references/template.org`
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-explain/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-invest/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-is/SKILL.md
Week of Nov 2, 2026 · +2 / −2 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
- 29 | **UnderstandInUse** | 把「是什么」与「怎样运作」接成可辨认、可判断、可行动的 Markdown 解读 | `Workflows/TraceCreation.md` |
+ 29 | **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` |
- 50 ~/Context/{时间戳}--理解-{目标片段}__is.md
+ 50 ~/Context/{时间戳}--理解-{目标片段}__is.org
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-learn/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-map/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-mechanism/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-paper/SKILL.md
Week of Nov 2, 2026 · +8 / −6 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
- 14 全文应围绕清楚的问题展开，让读者跟着观察、疑问与检查理解研究怎样发生。具体对象和动作应持续承担解释；随着解释深入，可以更换案例或场景，但要交代它补充了什么。现场感来自与理解有关的细节，不靠虚构心理或夸大结论。
+ 14 全文围绕论文能够支持的具体问题，让读者看见问题为何需要解决、原有判断有何依据，以及证据怎样支持新的判断。具体对象和动作应持续承担解释；随着解释深入，可以更换案例或场景，但要交代它补充了什么。现场感来自与理解有关的细节，不靠虚构心理或夸大结论。
+ 15
+ 16 完整的解释应给读者留下亲自解释或迁移的空间。文章写出了判断重构的过程，仍不能证明读者实际经历了这一过程。依据论文组织解释，允许补充、确认、区分和保留未知，不强求反转、统一机制或固定四段结构；默认完整交付，互动按用户意愿进行。
- 22 | arXiv、PDF、论文链接、本地论文 | `ReadingGuide.md`、`references/template.md`、`references/paper-map.md` | 一份 Markdown 解读笔记和一份 paper-map 研究记录 |
- 23 | 只有论文标题 | 找到可靠原文后，读同一组文件 | Markdown 笔记和 paper-map |
+ 24 | arXiv、PDF、论文链接、本地论文 | `ReadingGuide.md`、`references/template.org`、`references/paper-map.md` | 一份 Org 解读笔记和一份 paper-map 研究记录 |
+ 25 | 只有论文标题 | 找到可靠原文后，读同一组文件 | Org 笔记和 paper-map |
- 26 Markdown 默认保存到 `~/Context/`。文件名沿用 Denote：`{YYYYMMDDTHHMMSS}--paper-{方法名或论文关键词}__paper.md`；时间戳由 `date +%Y%m%dT%H%M%S` 生成。改写已有笔记时，保留原文件与 identifier，核对原文，不另建重复笔记。
+ 28 Org 默认保存到 `~/Context/`。文件名沿用 Denote：`{YYYYMMDDTHHMMSS}--paper-{方法名或论文关键词}__paper.org`；时间戳由 `date +%Y%m%dT%H%M%S` 生成。改写已有笔记时，保留原文件与 identifier，核对原文，不另建重复笔记。
- 31 - **让读者理解为什么需要修正原有认识。** 从具体问题出发，说明通常会怎样理解，再用论文证据展示这种理解哪里不够、作者补充了什么、判断因此发生了什么变化。变化可以是纠正，也可以是补充、区分或缩小适用范围，无须制造戏剧性的反转。
+ 33 - **让读者理解证据怎样调整或巩固判断。** 从具体问题出发，说明一种有依据的理解，再用论文证据展示它哪里仍然成立、哪里需要补充或修正。结尾交代现在能够怎样判断、还有什么无法确定；确认原有认识也可以构成收获，无须制造戏剧性的反转。
- 61 bun {skill_dir}/scripts/validate_note.ts /absolute/path/to/note.md \
+ 63 bun {skill_dir}/scripts/validate_note.ts /absolute/path/to/note.org \
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-present/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-push/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-qa/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-rank/SKILL.md
Week of Nov 2, 2026 · +1 / −1 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
- 483 2. 写入 `~/Documents/notes/{时间戳}--{领域}的秩__rank.md`
+ 483 2. 写入 `~/Documents/notes/{时间戳}--{领域}的秩__rank.org`
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-read/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-relationship/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-roundtable/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-structure/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-teach/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-think/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-word/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
skills/ljg-writes/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a6b11187771a → 76b5fb9b657f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a6b11187771a
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 76b5fb9b657f420287a421737a3a9778c9e53379
git clone --filter=blob:none --no-checkout https://github.com/lijigang/ljg-skills.git .hotskills/lijigang-ljg-skills && git -C .hotskills/lijigang-ljg-skills checkout --detach 76b5fb9b657f420287a421737a3a9778c9e53379
# Copy each selected skill directory from .hotskills/lijigang-ljg-skills into .claude/skills/<skill-name>/7.6kGitHub stars
39stars in 7 days
26skills in this repository
9commits in 30 days
Heat
6.2- Star growth, last 7 daysAhead of 74% of tracked repositories
- Star growth, last 24 hoursAhead of 70% of tracked repositories
- Rank movement, last 7 daysAhead of 60% of tracked repositories
- Commits, last 30 daysAhead of 76% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- ljg-analogy
skills/ljg-analogy - ljg-blind
skills/ljg-blind - ljg-book
skills/ljg-book - ljg-business-model
skills/ljg-business-model - ljg-card
skills/ljg-card - ljg-classic
skills/ljg-classic - ljg-constraint
skills/ljg-constraint - ljg-explain
skills/ljg-explain - ljg-invest
skills/ljg-invest - ljg-is
skills/ljg-is - ljg-learn
skills/ljg-learn - ljg-map
skills/ljg-map - ljg-mechanism
skills/ljg-mechanism - ljg-paper
skills/ljg-paper - ljg-present
skills/ljg-present - ljg-push
skills/ljg-push - ljg-qa
skills/ljg-qa - ljg-rank
skills/ljg-rank - ljg-read
skills/ljg-read - ljg-relationship
skills/ljg-relationship - ljg-roundtable
skills/ljg-roundtable - ljg-structure
skills/ljg-structure - ljg-teach
skills/ljg-teach - ljg-think
skills/ljg-think - ljg-word
skills/ljg-word - ljg-writes
skills/ljg-writes
How it works
ljg-analogy
When your agent uses it
基于结构映射理论，为场景或两个对象的差异寻找精妙类比与关系隐喻，保留关键关系、解释增量与迁移边界。USE WHEN 用户说「找个类比」「打个比方」「有什么精妙的隐喻」「用类比讲清两者区别」「换个场景理解」或调用 ljg-analogy。NOT FOR 只解释现成比喻、纯修辞润色、理论定义或把类比当作事实证明。
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
2,482 tokensWhen the skill is activated
Reference documents
122,088 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow Routing
- Gotchas
- 输入是否够用
- 什么样的类比值得交付
- 比较两个对象时
- 成品怎样说
- 理论与事实边界
- Examples
Scripts executed separately
../ljg-blind/Tools/WeReadWebUrl.ts../ljg-book/scripts/validate_note.test.ts../ljg-book/scripts/validate_note.ts../ljg-business-model/Tools/Render.test.ts../ljg-business-model/Tools/Render.ts../ljg-card/assets/audit.ts../ljg-card/assets/build-fixtures.ts../ljg-card/assets/capture.test.ts../ljg-card/assets/capture.ts../ljg-card/assets/prepare-whiteboard-source.test.ts../ljg-card/assets/prepare-whiteboard-source.ts../ljg-card/assets/verify-full-text.test.ts../ljg-card/assets/verify-full-text.ts../ljg-card/package.json../ljg-classic/Tools/RenderClassic.test.ts../ljg-classic/Tools/RenderClassic.ts../ljg-classic/Tools/ValidateClassic.ts../ljg-classic/package.json../ljg-is/Tools/ValidateNote.test.ts../ljg-is/Tools/ValidateNote.ts../ljg-paper/scripts/paper_map_compat.ts../ljg-paper/scripts/validate_note.test.ts../ljg-paper/scripts/validate_note.ts../ljg-present/Tools/BuildDeck.ts../ljg-present/Tools/DeckData.ts../ljg-present/Tools/EmbedAssets.ts../ljg-present/Tools/ProbeDeck.js../ljg-present/Tools/ValidateDeck.ts../ljg-push/Tools/MdizeEmbeddedOrg.test.ts../ljg-push/Tools/MdizeEmbeddedOrg.ts../ljg-push/Tools/Push.sh../ljg-push/Tools/Push.test.ts
Files
../../.claude-plugin/marketplace.jsonasset783 bytes../../.claude-plugin/plugin.jsonasset404 bytesEvalCases.jsonasset6,413 bytesSKILL.mdcore9,281 bytesTheory.mddoc4,053 bytesagents/openai.yamlasset296 bytes../ljg-blind/SKILL.mddoc12,019 bytes../ljg-blind/Tools/WeReadWebUrl.help.mddoc684 bytes../ljg-blind/Tools/WeReadWebUrl.tsruns2,074 bytes../ljg-book/ReadingGuide.mddoc10,882 bytes../ljg-book/SKILL.mddoc11,754 bytes../ljg-book/evals/20000101T000001--reading-a__book.orgasset25,428 bytes../ljg-book/evals/20000101T000002--reading-b__book.orgasset25,366 bytes../ljg-book/evals/evals.jsonasset4,760 bytes../ljg-book/evals/reading-pair.jsonasset1,539 bytes../ljg-book/references/coverage-map.mddoc5,360 bytes../ljg-book/references/template.orgasset1,366 bytes../ljg-book/scripts/validate_note.test.tsruns61,013 bytes../ljg-book/scripts/validate_note.tsruns41,689 bytes../ljg-business-model/CanvasGuide.mddoc3,878 bytes../ljg-business-model/Example.htmlasset13,491 bytes../ljg-business-model/Example.jsonasset3,355 bytes../ljg-business-model/Example.pngasset392,743 bytes../ljg-business-model/SKILL.mddoc5,395 bytes../ljg-business-model/Tools/Render.help.mddoc2,752 bytes../ljg-business-model/Tools/Render.test.tsruns3,055 bytes../ljg-business-model/Tools/Render.tsruns16,107 bytes../ljg-business-model/agents/openai.yamlasset275 bytes../ljg-card/SKILL.mddoc16,210 bytes../ljg-card/assets/audit.tsruns16,934 bytes../ljg-card/assets/build-fixtures.tsruns44,916 bytes../ljg-card/assets/capture.test.tsruns9,393 bytes../ljg-card/assets/capture.tsruns30,187 bytes../ljg-card/assets/comic_template.htmlasset2,296 bytes../ljg-card/assets/full_template.htmlasset6,315 bytes../ljg-card/assets/logo.pngasset326,462 bytes../ljg-card/assets/long_template.htmlasset7,940 bytes../ljg-card/assets/prepare-whiteboard-source.test.tsruns1,454 bytes../ljg-card/assets/prepare-whiteboard-source.tsruns2,175 bytes../ljg-card/assets/verify-full-text.test.tsruns3,926 bytes../ljg-card/assets/verify-full-text.tsruns6,505 bytes../ljg-card/assets/whiteboard_template.htmlasset11,759 bytes../ljg-card/bun.lockasset775 bytes../ljg-card/package-lock.jsonasset1,592 bytes../ljg-card/package.jsonruns190 bytes../ljg-card/references/image-generation.mddoc7,239 bytes../ljg-card/references/learning-design.mddoc9,859 bytes../ljg-card/references/mode-comic.mddoc8,918 bytes../ljg-card/references/mode-full.mddoc8,497 bytes../ljg-card/references/mode-long.mddoc9,725 bytes../ljg-card/references/mode-whiteboard.mddoc15,894 bytes../ljg-card/references/taste.mddoc3,304 bytes../ljg-classic/.gitignoreasset14 bytes../ljg-classic/References/AnnotationMethod.mddoc2,247 bytes../ljg-classic/References/InputSchema.mddoc2,735 bytes../ljg-classic/References/LayoutGrammar.mddoc4,079 bytes../ljg-classic/SKILL.mddoc4,678 bytes../ljg-classic/Tools/RenderClassic.help.mddoc900 bytes../ljg-classic/Tools/RenderClassic.test.tsruns21,494 bytes../ljg-classic/Tools/RenderClassic.tsruns30,378 bytes../ljg-classic/Tools/ValidateClassic.help.mddoc540 bytes../ljg-classic/Tools/ValidateClassic.tsruns19,275 bytes../ljg-classic/Workflows/AnnotateAndRender.mddoc8,928 bytes../ljg-classic/bun.lockasset844 bytes../ljg-classic/package.jsonruns282 bytes../ljg-constraint/SKILL.mddoc20,418 bytes../ljg-constraint/references/template.orgasset117 bytes../ljg-explain/SKILL.mddoc8,499 bytes../ljg-explain/agents/openai.yamlasset292 bytes../ljg-invest/SKILL.mddoc6,446 bytes../ljg-is/SKILL.mddoc6,712 bytes../ljg-is/Template.orgasset1,242 bytes../ljg-is/Tools/ValidateNote.help.mddoc1,339 bytes../ljg-is/Tools/ValidateNote.test.tsruns24,099 bytes../ljg-is/Tools/ValidateNote.tsruns27,830 bytes../ljg-is/Workflows/TraceCreation.mddoc7,582 bytes../ljg-is/evals/evals.jsonasset1,075 bytes../ljg-learn/SKILL.mddoc2,776 bytes../ljg-map/Examples.mddoc5,101 bytes../ljg-map/SKILL.mddoc3,768 bytes../ljg-map/Workflows/Map.mddoc7,493 bytes../ljg-map/agents/openai.yamlasset324 bytes../ljg-mechanism/SKILL.mddoc5,206 bytes../ljg-mechanism/Workflows/DiscoverMechanism.mddoc9,507 bytes../ljg-mechanism/agents/openai.yamlasset315 bytes../ljg-paper/ReadingGuide.mddoc18,083 bytes../ljg-paper/SKILL.mddoc7,495 bytes../ljg-paper/evals/evals.jsonasset11,972 bytes../ljg-paper/evals/plain-language-pair.jsonasset23,853 bytes../ljg-paper/references/paper-map.mddoc8,945 bytes../ljg-paper/references/template.orgasset2,925 bytes../ljg-paper/scripts/paper_map_compat.tsruns4,414 bytes../ljg-paper/scripts/validate_note.test.tsruns28,481 bytes../ljg-paper/scripts/validate_note.tsruns25,306 bytes../ljg-present/ChartSpec.mddoc3,366 bytes../ljg-present/CompositionReference.mddoc1,961 bytes../ljg-present/DesignSystem.mddoc4,091 bytes../ljg-present/Fonts/IBMPlexMono-Bold.ttfasset136,008 bytes../ljg-present/Fonts/IBMPlexMono-OFL.txtdoc4,363 bytes../ljg-present/Fonts/IBMPlexMono-Regular.ttfasset133,796 bytes../ljg-present/References/Chapter.pngasset18,639 bytes../ljg-present/References/Compare.pngasset27,671 bytes../ljg-present/References/CompositionDeck.jsonasset7,645 bytes../ljg-present/References/Diagram.pngasset27,650 bytes../ljg-present/References/Evidence.pngasset56,612 bytes../ljg-present/References/RegressionDeck.jsonasset8,243 bytes../ljg-present/References/Statement.pngasset24,319 bytes../ljg-present/RenderingSpec.mddoc5,791 bytes../ljg-present/SKILL.mddoc3,964 bytes../ljg-present/SloganTemplate.htmlasset27,792 bytes../ljg-present/Tools/BuildDeck.help.mddoc1,125 bytes../ljg-present/Tools/BuildDeck.tsruns1,208 bytes../ljg-present/Tools/DeckData.tsruns11,612 bytes../ljg-present/Tools/EmbedAssets.help.mddoc1,056 bytes../ljg-present/Tools/EmbedAssets.tsruns3,384 bytes../ljg-present/Tools/ProbeDeck.help.mddoc1,139 bytes../ljg-present/Tools/ProbeDeck.jsruns6,116 bytes../ljg-present/Tools/ValidateDeck.help.mddoc1,859 bytes../ljg-present/Tools/ValidateDeck.tsruns18,642 bytes../ljg-present/Workflows/Generate.mddoc3,649 bytes../ljg-push/SKILL.mddoc9,945 bytes../ljg-push/Tools/MdizeEmbeddedOrg.test.tsruns2,873 bytes../ljg-push/Tools/MdizeEmbeddedOrg.tsruns3,739 bytes../ljg-push/Tools/Push.shruns32,665 bytes../ljg-push/Tools/Push.test.tsruns15,973 bytes../ljg-push/Workflows/Push.mddoc4,832 bytes../ljg-qa/References/QuestionDesign.mddoc5,826 bytes../ljg-qa/SKILL.mddoc4,187 bytes../ljg-qa/Workflows/Extract.mddoc5,959 bytes../ljg-rank/SKILL.mddoc25,039 bytes../ljg-rank/references/template.orgasset121 bytes../ljg-read/SKILL.mddoc8,946 bytes../ljg-relationship/SKILL.mddoc10,706 bytes../ljg-roundtable/SKILL.mddoc4,567 bytes../ljg-roundtable/references/original-prompt.mddoc7,747 bytes../ljg-structure/SKILL.mddoc8,911 bytes../ljg-structure/Workflows/FindStructure.mddoc10,185 bytes../ljg-teach/SKILL.mddoc8,008 bytes../ljg-think/SKILL.mddoc2,815 bytes../ljg-word/SKILL.mddoc1,301 bytes../ljg-writes/SKILL.mddoc8,224 bytes../ljg-writes/Workflows/WriteEssay.mddoc9,023 bytes
Read SKILL.md
# ljg-analogy：让关系在另一个场景里显形
用户给出一个场景，交付一个让人先看见画面、再认出关系、最后对原场景多懂一点的类比。物件可以相距很远，关系却对得很近。新奇不能抵消失真；熟悉的物件也能承载出人意料的关系。
术语方向固定：**用户想理解的场景是目标域；借来帮助理解的场景是基域。** 搜索从目标域出发寻找基域，知识迁移从基域回到目标域。用户用词相反时按实际意图工作，不为术语打断创作。
## Workflow Routing
| 请求 | 处理 |
|------|------|
| 给一个场景，寻找类比或隐喻 | 按下文的成品标准交付一个主类比 |
| 比较两个对象、产品或机制 | 用共同的关系框架，同时保留共同点与关键差异 |
| 指定受众、领域、文风或只要一句 | 保留结构约束，服从用户的呈现要求 |
| 要多个方案或比较已有候选 | 比较不同关系焦点，点出推荐项与取舍 |ljg-blind
When your agent uses it
盲区扫描——读昨天你与 AI 的全部对话，照出暴露的思维盲区（不是不懂的知识，是让某类真相一直看不见的思维习惯），再从微信读书挑一本书的一章精准补上，落成一篇完整分析笔记。Use when user says '扫盲区', '盲区', '照盲区', '看看我的思维盲区', '我昨天想漏了什么', 'blind spot', 'ljg-blind', '/ljg-blind', or wants yesterday's AI conversations analyzed for cognitive blind spots plus a targeted weread chapter to fill them. 可选参数：传一个日期(YYYY-MM-DD)扫那天而非昨天。NOT FOR 纵向深钻一个观点（用 ljg-think）、一个领域降秩（用 ljg-rank）、陪读一篇文本（用 ljg-read）、找一个领域的约束（用 ljg-constraint）。
What it loads into context
Frontmatter
231 tokensAlways available to the agent
SKILL.md
3,695 tokensWhen the skill is activated
Reference documents
225 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 盲区是什么
- 五种盲区信号
- 选哪一个
- 操作步骤
- 语气规则（写笔记时守住）
- Markdown 严格语法（禁混 Org）
- 自检（写完前过一遍）
- Gotchas
- 和「早信」的分工
Scripts executed separately
Tools/WeReadWebUrl.ts
Files
SKILL.mdcore12,019 bytesSKILL.mdcore12,019 bytesSKILL.mdcore12,019 bytesSKILL.mdcore12,019 bytesSKILL.mdcore12,019 bytesSKILL.mdcore12,019 bytesSKILL.mdcore12,019 bytesTools/WeReadWebUrl.help.mddoc684 bytesTools/WeReadWebUrl.tsruns2,074 bytes
Read SKILL.md
# 盲区扫描
读你昨天跟 AI 的全部对话，照出那个你自己看不见的思维盲区，从微信读书点亮补它的一章。
## 盲区是什么
盲区不是知识缺口。不是"没读过某本书""不知道某个事实"——那种缺口，查一下就补上了。
盲区是一种结构性的思维习惯，它让某一类真相对你**系统性地不可见**。你不是想不到，是这个习惯让你压根没往那个方向看。它藏在你怎么想事情的方式里，不藏在你想的内容里。
所以证据不在"他说错了什么"。在——他没往哪看，他在哪绕了，他默认了什么却从没检。
## 五种盲区信号
ljg-book
When your agent uses it
Explain a whole book to readers without specialist knowledge: what it follows, how its main threads connect, where it ends, and how its evidence or events change understanding. Keep the book's specific content; a general lesson alone is not enough. USE WHEN given a book title, PDF, EPUB, excerpt, or asked 拆书, 分析这本书, 这本书在讲什么, 压缩一本书, or book. Defaults to a saved Org note. NOT FOR chapter summaries, papers, formal reviews, or single-concept deep dives.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
3,006 tokensWhen the skill is activated
Reference documents
4,208 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow Routing
- 先看清整本书，再决定怎样讲
- 让一个念头有机会走完
- 用问题的缺口拉动阅读
- Gotchas
- 只读成品，找出理解在哪里中断
- 末节：读完后应发生的变化
- Completion
Scripts executed separately
scripts/validate_note.test.tsscripts/validate_note.ts
Files
ReadingGuide.mddoc10,882 bytesSKILL.mdcore11,754 bytesSKILL.mdcore11,754 bytesevals/20000101T000001--reading-a__book.orgasset25,428 bytesevals/20000101T000002--reading-b__book.orgasset25,366 bytesevals/evals.jsonasset4,760 bytesevals/reading-pair.jsonasset1,539 bytesreferences/coverage-map.mddoc5,360 bytesreferences/template.orgasset1,366 bytesscripts/validate_note.test.tsruns61,013 bytesscripts/validate_note.tsruns41,689 bytes
Read SKILL.md
# ljg-book：让没读过的人，也能读懂这本书
写给没读过原书的人：让他们知道书里具体发生或论证了什么，看清各部分为什么写在一起，并经历原来的理解怎样被事实、事件和后果逐渐改变。
写作围绕一个问题、人物、关系或模型的持续展开来组织。让它遇到困难、增加条件、改变判断，再走向下一步。同一条线索可以承担不同阶段的工作；需要多条独立主线的书，保留它们的完整发展与联系。不要把全书改写成依次介绍知识点、为每个知识点另配例子的文章。
## Workflow Routing
| 输入 | 必读 | 输出 |
|---|---|---|
| 书名 | 找到可靠材料后读 `ReadingGuide.md` | 保存 Org 笔记 |
| PDF、EPUB、正文、样章、旧笔记 | 先读原文，再读 `ReadingGuide.md` | 保存 Org 笔记 |
| 用户明确只要口头解释 | `ReadingGuide.md` | 按同样要求讲清，不写文件 |
ljg-business-model
When your agent uses it
基于《商业模式新生代》的 Business Model Canvas，把用户提供的项目介绍、访谈、产品资料或商业计划整理成九模块商业模式画布卡片，交付 PNG 与可修改的 HTML。USE WHEN 用户调用 ljg-business-model、要求画商业模式画布、九宫格商业模式或把商业信息做成画布卡片。NOT FOR 普通商业分析、投资估值、Lean Canvas 或只解释商业模式概念。
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
1,428 tokensWhen the skill is activated
Reference documents
1,680 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow Routing
- 内容合同
- 生成与验收
- Gotchas
- Examples
Scripts executed separately
Tools/Render.test.tsTools/Render.ts
Files
CanvasGuide.mddoc3,878 bytesExample.htmlasset13,491 bytesExample.jsonasset3,355 bytesExample.pngasset392,743 bytesSKILL.mdcore5,395 bytesSKILL.mdcore5,395 bytesTools/Render.help.mddoc2,752 bytesTools/Render.test.tsruns3,055 bytesTools/Render.tsruns16,107 bytesagents/openai.yamlasset275 bytes
Read SKILL.md
# ljg-business-model
把用户的信息变成一张能看清「为谁创造什么价值、如何交付、如何收支」的商业模式画布。主产物为中文横版 PNG；同时保留 HTML 和结构化 JSON，便于修改、追溯与重绘。
## Workflow Routing
| 输入 | 处理与交付 |
|---|---|
| 项目介绍、访谈、文档、零散描述 | 依据下方合同整理，运行 `Tools/Render.ts`，验证后交付画布 |
| 现有画布与补充材料 | 以新材料更新指定模型；保留未受影响的信息，重新生成 |
| 多个独立业务／商业模式 | 每个模式一张画布；同一平台的多边客户留在同张图中并用 C1、C2 关联 |
## 内容合同
ljg-card
When your agent uses it
Content caster (铸). Transforms text into PNG through precise HTML typography and, when the mold needs it, generated raster imagery. Four molds: -l (default) long reading card, -f source-faithful full text, -c comic, -w whiteboard. USE WHEN user says '铸', 'cast', '做成图', '做成卡片', '做成海报', '原文排版', '全文卡片', '漫画', or '白板'.
What it loads into context
Frontmatter
129 tokensAlways available to the agent
SKILL.md
4,706 tokensWhen the skill is activated
Reference documents
17,793 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 参数
- 必读顺序
- `-f` 字体优先级
- `-f` 长文阅读面
- 全局临时目录约束
- 共同生产线
- 输入与命名
- 截图工具
- Footer
- mode 路由
- Gotchas
- Examples
- 交付合同
- 维护自检
Scripts executed separately
assets/audit.tsassets/build-fixtures.tsassets/capture.test.tsassets/capture.tsassets/prepare-whiteboard-source.test.tsassets/prepare-whiteboard-source.tsassets/verify-full-text.test.tsassets/verify-full-text.tspackage.json
Files
SKILL.mdcore16,210 bytesSKILL.mdcore16,210 bytesSKILL.mdcore16,210 bytesSKILL.mdcore16,210 bytesSKILL.mdcore16,210 bytesassets/audit.tsruns16,934 bytesassets/build-fixtures.tsruns44,916 bytesassets/capture.test.tsruns9,393 bytesassets/capture.tsruns30,187 bytesassets/comic_template.htmlasset2,296 bytesassets/full_template.htmlasset6,315 bytesassets/logo.pngasset326,462 bytesassets/long_template.htmlasset7,940 bytesassets/prepare-whiteboard-source.test.tsruns1,454 bytesassets/prepare-whiteboard-source.tsruns2,175 bytesassets/verify-full-text.test.tsruns3,926 bytesassets/verify-full-text.tsruns6,505 bytesassets/whiteboard_template.htmlasset11,759 bytesbun.lockasset775 bytespackage-lock.jsonasset1,592 bytespackage.jsonruns190 bytesreferences/image-generation.mddoc7,239 bytesreferences/learning-design.mddoc9,859 bytesreferences/mode-comic.mddoc8,918 bytesreferences/mode-full.mddoc8,497 bytesreferences/mode-long.mddoc9,725 bytesreferences/mode-whiteboard.mddoc15,894 bytesreferences/taste.mddoc3,304 bytes
Read SKILL.md
# ljg-card：铸
内容进去，PNG 出来。生成图负责把思想变成可见动作，HTML 负责把话说准确；`-f` 只设计原文的呈现，不改动原文，也不生成新图。
`-l`、`-w` 承担知识讲解时，还要接通「具体情形 → 判别依据 → 有条件的关系 → 具体结果」。读者应能从正文里的动作或状态看出对象凭什么属于某个概念，再用关系推出眼前的结果；只把例子放在术语旁边，连接仍然缺失。先确定目标读者要完成什么判断，再决定材料和画面；下上结构不规定版面上下，也不要求每张卡从故事开头。文学、叙事与审美表达按自身目的组织，不强加习题。
成品在内容自身的结论、问题或余韵处结束，之后只留署名与来源。不要追加「阅读边界」、免责声明、制作说明或验收说明，也不要换个标题保留这类尾注。会改变理解的原文条件、分歧与限制，就近融入相应论证；提炼范围、材料缺口和验证状态放在交付回复中。`-f` 原稿已有的段落仍按全文保真合同保留。
## 参数
| 参数 | 模具 | 尺寸 | 图像角色 |
|---|---|---|---|
| `-l`（默认） | 长图 · 静线叙事 | 1080 × auto | 0–3 幅；有理解增益时用 1 个安静主场景，必要时追加连续视觉拍点 |
| `-f` | 全文 · 原文排版 | 1080 × auto | 生成图固定为 0；只保真呈现原稿自带图片 |ljg-classic
When your agent uses it
古文逐字注解、组合排版、章节意旨图与全章解读生成器。把原文、字词注、句义注、无字顶部配图和章节解读排成一张可读的长 PNG。USE WHEN 用户调用 ljg-classic OR 要求给文言文、古诗文、经史子集做逐字注解、彩色夹注、章节解读、古文讲义图、章节配图。NOT FOR 只翻译一句古文、只写现代文章或通用内容卡片。
What it loads into context
Frontmatter
150 tokensAlways available to the agent
SKILL.md
1,352 tokensWhen the skill is activated
Reference documents
5,776 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow Notification
- Workflow Routing
- 快速合同
- Gotchas
- Examples
Scripts executed separately
Tools/RenderClassic.test.tsTools/RenderClassic.tsTools/ValidateClassic.tspackage.json
Files
.gitignoreasset14 bytesReferences/AnnotationMethod.mddoc2,247 bytesReferences/InputSchema.mddoc2,735 bytesReferences/LayoutGrammar.mddoc4,079 bytesSKILL.mdcore4,678 bytesTools/RenderClassic.help.mddoc900 bytesTools/RenderClassic.test.tsruns21,494 bytesTools/RenderClassic.tsruns30,378 bytesTools/ValidateClassic.help.mddoc540 bytesTools/ValidateClassic.tsruns19,275 bytesWorkflows/AnnotateAndRender.mddoc8,928 bytesbun.lockasset844 bytespackage.jsonruns282 bytes
Read SKILL.md
# ljg-classic：古文笺
原文是主干，注解贴着字词生长，章节解读把整章重新接成一个能运行的判断。最终交付一张标明书名与章节的 PNG 长图到 `$HOME/Downloads/`；生成与复验过程留在独占 `/tmp` 工作区。
## Workflow Notification
执行工作流时，只输出文字通知：
```text
Running the **AnnotateAndRender** workflow in the **ljg-classic** skill to annotate and render the chapter...
```
不发送开始、阶段或进度语音；完成语音由系统统一处理。
ljg-constraint
When your agent uses it
给一个领域、专业、角色、产品或争论找出真正框住它的几条约束，判明它们属于世界/规则/解释（硬/软/自设），看这组约束如何定义身份、补全问题、框出解空间并解释实际行为；尤其用于区分目标相同但约束不同导致的方案分歧，识别被误当硬事实的旧解释。USE WHEN 用户说 '约束', '找约束', '这个领域的约束是什么', '本质约束', '什么框住了它', '硬约束还是自设约束', '边界在哪', '这行为什么这么做', 'constraint', '/ljg-constraint', or gives any domain/profession/role/product/debate and wants its defining constraints and solution space mapped. NOT FOR 往下挖生成器（用 ljg-rank，找的是生成力不是边界）、纵向深钻一个观点到底（用 ljg-think）、拆一本书（用 ljg-book）、一个概念解剖（用 ljg-learn）。
What it loads into context
Frontmatter
254 tokensAlways available to the agent
SKILL.md
5,821 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow Routing
- Gotchas
- Examples
- 约束是什么
- 三层硬度：这条约束是哪一层的
- 怎么找：工序
- 从约束到解空间到行为
- 心内判据
- 松动哪条（第二位，不参与诊断）
- 中文母语化 · 反坍缩闸
- 怎么写
- 文末配一张 ASCII 结构图——形式跟着骨架走
- 输出
Files
SKILL.mdcore20,418 bytesreferences/template.orgasset117 bytes
Read SKILL.md
# 约束引擎
输入一个领域、一门专业、一个角色，找出框住它的那几条约束，看清这组约束框出的解空间——以及这个解空间怎么解释它的种种行为。
## Workflow Routing
| Trigger | Workflow |
|---|---|
| 给领域、专业、角色、产品找本质约束 | 执行本文工序，写成一篇中文散文分析，保存为 Markdown 文件 |
| 分析一场方案争论为什么说不清 | 先找各方默认约束，再说明他们其实是不是同一道题 |
| 判断某条边界是真硬约束还是旧解释 | 走三层硬度和真伪定性，不急着给突破方案 |
## Gotchas
ljg-explain
When your agent uses it
把概念、公式、机制与原理讲到能辨认、能推导、能迁移：用通俗中文接通具体情境、判别依据、运作过程和成立条件。USE WHEN 用户调用 ljg-explain、说「通俗易懂地讲解」「讲透这个概念或公式」「费曼讲解」「ELI5」，或希望从零理解一个知识点并能用于新情境。NOT FOR 单纯润色或翻译、整篇伴读、整本书或论文解读、只要求形式证明或操作步骤。
What it loads into context
Frontmatter
150 tokensAlways available to the agent
SKILL.md
2,211 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 读者与交付
- 理解标准
- 公式与原理
- 中文表达
- 证据与版式
- Gotchas
- Examples
Files
SKILL.mdcore8,499 bytesagents/openai.yamlasset292 bytes
Read SKILL.md
# ljg-explain：讲到能用
让读者听得懂，也能独立认出新例子、解释结果怎样产生、知道条件变化后该怎样改判断。把这几件事作为完成标准，组织方式由内容决定，不把它们机械排成五个栏目。
用「目的、结构、案例、论证」接通知识：目的说明要回答什么问题，结构说明要素怎样关联，案例让关键关系可见，论证交代为何成立、有效及其限度。四问用于组织和检查讲解，不规定输出顺序或栏目；读者能否使用知识，仍以下面的理解标准为准。
## 读者与交付
- 先使用本次请求与已有上下文中的知识背景、用途和卡点。未说明时，按有日常经验、缺少专业知识的成年人讲解；缺少必要前置知识，就补上够用的那一小段。
- 能合理确定含义就直接讲；只有不同解释会改变讲解对象时才澄清，不能为了填写背景表而中断。
- 默认一次完整输出到对话，在讲解自然收束处结束，不在结尾追加自测题或参考答案；用户明确希望互动时，再按需分轮讲解。
- 默认不写笔记或其他文件。用户要求保存时，遵守指定格式与位置；普通聊天用 Markdown，Org 产物才使用 Org 语法。
## 理解标准ljg-invest
When your agent uses it
投资分析。给一个项目（公司名、BP、创始人对话记录），写一份深度投资分析报告。不走传统投资分析的路——核心判断只有一个：这个项目是不是一台「秩序创造机器」。Use when user says '投资报告', '投资分析', '分析这个项目', '写投资报告', 'investment report', 'invest analysis', or provides entrepreneur conversation records wanting investment evaluation. Also trigger when user pastes or references meeting notes, pitch decks, or founder interviews and asks for analysis.
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
1,692 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 地基
- 输入
- 报告结构
- 输出
- 生成规则
Files
SKILL.mdcore6,446 bytes
Read SKILL.md
# ljg-invest: 投资报告
给一个项目，写一份投资分析。整份报告只回答一个问题：这个东西在创造新秩序，还是在搬运旧秩序。
## 地基
一个定义撑着整份报告：财富不是钱，是被欲望照亮的秩序，钱只是秩序的计量单位。投资，是拿手里的秩序，去换一台更好的秩序生成器。
从这个定义出发，报告的问法和市场惯例不一样：
| 惯常问法 | 这份报告问 |
|----------|------------|
| 这个公司值多少钱 | 这台机器转不转得起来 |
| 市场有多大 | 市场在用什么过时的标签看它 |ljg-is
When your agent uses it
把一个名词或概念写成可使用的理解：先用普通话讲清它是什么、与相邻概念差在哪里，再说明它怎样运作、会改写什么判断，最后给出面对它时的行动抓手。USE WHEN 用户问 X 是什么、怎么理解、意味着什么、为什么重要、以后怎样判断或使用；尤其适合技术概念、制度、产品、角色、方法、规范与实践。NOT FOR 单纯查事实、公式证明、逐步操作教程、纵向因果深挖（用 ljg-think）或母题结构（用 ljg-structure）。
What it loads into context
Frontmatter
159 tokensAlways available to the agent
SKILL.md
1,709 tokensWhen the skill is activated
Reference documents
2,324 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow Routing
- 成品标准
- 判断边界
- Gotchas
- Examples
Scripts executed separately
Tools/ValidateNote.test.tsTools/ValidateNote.ts
Files
SKILL.mdcore6,712 bytesTemplate.orgasset1,242 bytesTools/ValidateNote.help.mddoc1,339 bytesTools/ValidateNote.test.tsruns24,099 bytesTools/ValidateNote.tsruns27,830 bytesWorkflows/TraceCreation.mddoc7,582 bytesevals/evals.jsonasset1,075 bytes
Read SKILL.md
# 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。
```text
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。ljg-learn
When your agent uses it
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or idea. Triggers on '解剖概念', '概念解剖', 'explain concept', 'learn concept', '/ljg-learn'. Produces markdown output.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
880 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Instructions
Files
SKILL.mdcore2,776 bytes
Read SKILL.md
## Usage
<example>
User: /ljg-learn 熵
Assistant: [对"熵"进行八维解剖，生成 markdown 报告]
</example>
## Instructions
你是概念解剖师。拿到一个概念，从八个方向切开它，最后把所有切面压成一句顿悟。
### 1. 定锚
1. 这个概念最通行的定义是什么？常见误解在哪？ljg-map
When your agent uses it
以《学习观》的知识观洞察用户文稿，提炼概念、判别依据与有条件的联结，按文稿自身的关系绘制通俗的形式化知识地图；每个节点都有白话定义、短公式和具体语义，图形不预设层级。USE WHEN 用户调用 /ljg-map，或要求把文章、笔记、讲稿画成形式化地图、思考地形图、概念判别与关系图。NOT FOR 普通摘要、逐段改写、地理地图或单独的公式证明。
What it loads into context
Frontmatter
148 tokensAlways available to the agent
SKILL.md
1,015 tokensWhen the skill is activated
Reference documents
3,489 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow Routing
- Gotchas
- 成品约定
- Examples
Files
Examples.mddoc5,101 bytesSKILL.mdcore3,768 bytesWorkflows/Map.mddoc7,493 bytesagents/openai.yamlasset324 bytes
Read SKILL.md
# ljg-map · 形式化思考地图
用《学习观》关于概念、判别模型和联结模型的理解，看到文稿背后的知识结构：哪些词有明确的所指，现实对象凭什么归入它们，概念之间的关系在什么条件下成立。把看到的结构画出来，形式化负责减少歧义，白话和实例负责让关系可理解、可使用。
## Workflow Routing
| 请求 | 执行 |
|---|---|
| 从文稿生成地图，或修订已有地图 | 阅读 [Workflows/Map.md](Workflows/Map.md) |
| 需要校准公式密度、节点解释和来源边界 | 按需阅读 [Examples.md](Examples.md)；学习表达方式，不套用题材和节点 |
## Gotchas
- **知识观是洞察视角，图形由材料决定。** 具象、概念与应用的对应帮助检查知识是否接通，不构成固定的三个图层、三个栏目或必经步骤。分类交叉就画交叉关系，反馈就画循环；材料确有层级时才画层级。ljg-mechanism
When your agent uses it
针对用户提供的现象，用「看反常—追过程—分解释—带条件迁移」生成机制猜想，并联网核对现象、检验关键因果与竞争解释，交付证据最能支撑的机制及其边界。USE WHEN 用户调用 ljg-mechanism、说「找机制」「机制研究」「用四步框架走一遍」「联网验证这个解释」，或希望研究一个现象怎样发生。NOT FOR 纯概念定义、普通摘要、已有唯一解的操作题或只画地图。
What it loads into context
Frontmatter
145 tokensAlways available to the agent
SKILL.md
1,321 tokensWhen the skill is activated
Reference documents
2,363 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow Routing
- 研究约定
- 成品
- Gotchas
- Examples
Files
SKILL.mdcore5,206 bytesWorkflows/DiscoverMechanism.mddoc9,507 bytesagents/openai.yamlasset315 bytes
Read SKILL.md
# ljg-mechanism · 机制研究
从眼前的现象中找出真正起作用的关系。生成解释后，让它与竞争解释一起接受现实检验；根据证据修正对象、关系或成立条件，给出当前最扎实的机制判断。
「solid」指关键关系有可检查的依据、能够区分竞争解释、能推出新观察，并留下修改自己的入口。完整、流畅或引用很多，均不足以达到这个标准；公开证据不足时，交付领先猜想和具体缺口。
## Workflow Routing
| 请求 | 执行 |
|---|---|
| 提供现象，希望解释其生成过程并验证 | 阅读 [Workflows/DiscoverMechanism.md](Workflows/DiscoverMechanism.md) |
| 希望示范、学习或「走一遍」 | 使用同一研究框架，在成品中展开四个环节与判断变化 |
| 补充新事实、反例或改变范围 | 回到受影响的观察或因果关系，更新判断，不从头重复无关部分 |
ljg-paper
When your agent uses it
Explain research papers to readers without a specialist background: what the paper studies, what the authors contribute, how the findings follow, and what the evidence does not establish. USE WHEN the user shares an arXiv link, paper URL, PDF, local paper, or paper title, or asks to read, explain, analyze, or understand a paper. Defaults to a saved Markdown note. NOT FOR reproduction, formal peer review, benchmark tables, or literature surveys.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
1,831 tokensWhen the skill is activated
Reference documents
6,808 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow Routing
- 解读要达到的三个目标
- 容易出错的地方
- 示例
- 保存与检查
Scripts executed separately
scripts/paper_map_compat.tsscripts/validate_note.test.tsscripts/validate_note.ts
Files
ReadingGuide.mddoc18,083 bytesSKILL.mdcore7,495 bytesSKILL.mdcore7,495 bytesevals/evals.jsonasset11,972 bytesevals/plain-language-pair.jsonasset23,853 bytesreferences/paper-map.mddoc8,945 bytesreferences/template.orgasset2,925 bytesscripts/paper_map_compat.tsruns4,414 bytesscripts/validate_note.test.tsruns28,481 bytesscripts/validate_note.tsruns25,306 bytes
Read SKILL.md
# ljg-paper：讲清论文，让读者理解结论是怎样得来的
默认读者有一般生活经验和理解能力，但不熟悉论文所属行业，也不知道该行业常用的对象、工具和工作方式。用户指定了读者背景时，以其指定为准。
从读者能够直接理解的事情出发，讲清谁在什么条件下做了什么、为什么遇到困难、作者改变了哪个环节，以及结果怎样变化。专业名称在有助于识别论文贡献时引入；读者在记住名称之前，应已理解它指向的事情。
读者最终既能用普通话解释论文的思想，也能说清作者实际研究了什么、做出了什么贡献。生活案例承担解释时，应明确对应论文中的角色与关系，并区分假想示例和真实实验。
全文围绕论文能够支持的具体问题，让读者看见问题为何需要解决、原有判断有何依据，以及证据怎样支持新的判断。具体对象和动作应持续承担解释；随着解释深入，可以更换案例或场景，但要交代它补充了什么。现场感来自与理解有关的细节，不靠虚构心理或夸大结论。
完整的解释应给读者留下亲自解释或迁移的空间。文章写出了判断重构的过程，仍不能证明读者实际经历了这一过程。依据论文组织解释，允许补充、确认、区分和保留未知，不强求反转、统一机制或固定四段结构；默认完整交付，互动按用户意愿进行。
当关键关系需要读者在脑中自行拼装时，优先考虑 ASCII 图来呈现信息流向、前后状态或不同维度，再沿具体例子读图。是否用图、用几幅，由它能否减少理解负担决定，不固定故事或图数。
ljg-present
When your agent uses it
Unix 气质的演讲设计与保真排版。把 Org/Markdown 提纲或经授权提炼的讲稿制成单文件离线 HTML；以语义角色选择巨句、对照、Unicode 关系图、证据与章节版式。默认深色，支持讲稿层、原生图表与翻页笔。USE WHEN present、做演讲、slides、按 outline 美化、把讲述精髓放上屏幕。NOT FOR 未经授权改写作者内容或生成企业 PPT。
What it loads into context
Frontmatter
142 tokensAlways available to the agent
SKILL.md
1,094 tokensWhen the skill is activated
Reference documents
6,422 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow Routing
- Gotchas
- 两种内容契约
- 设计与实现
- 主题
- 交付
- Examples
Scripts executed separately
Tools/BuildDeck.tsTools/DeckData.tsTools/EmbedAssets.tsTools/ProbeDeck.jsTools/ValidateDeck.ts
Files
ChartSpec.mddoc3,366 bytesCompositionReference.mddoc1,961 bytesDesignSystem.mddoc4,091 bytesFonts/IBMPlexMono-Bold.ttfasset136,008 bytesFonts/IBMPlexMono-OFL.txtdoc4,363 bytesFonts/IBMPlexMono-Regular.ttfasset133,796 bytesReferences/Chapter.pngasset18,639 bytesReferences/Compare.pngasset27,671 bytesReferences/CompositionDeck.jsonasset7,645 bytesReferences/Diagram.pngasset27,650 bytesReferences/Evidence.pngasset56,612 bytesReferences/RegressionDeck.jsonasset8,243 bytesReferences/Statement.pngasset24,319 bytesRenderingSpec.mddoc5,791 bytesSKILL.mdcore3,964 bytesSloganTemplate.htmlasset27,792 bytesTools/BuildDeck.help.mddoc1,125 bytesTools/BuildDeck.tsruns1,208 bytesTools/DeckData.tsruns11,612 bytesTools/EmbedAssets.help.mddoc1,056 bytesTools/EmbedAssets.tsruns3,384 bytesTools/ProbeDeck.help.mddoc1,139 bytesTools/ProbeDeck.jsruns6,116 bytesTools/ValidateDeck.help.mddoc1,859 bytesTools/ValidateDeck.tsruns18,642 bytesWorkflows/Generate.mddoc3,649 bytes
Read SKILL.md
# ljg-present：演讲铸造器
让观众一眼找到这一页的主角，让讲者有足够的提示继续展开。Unix 气质来自精确的关系、自然的文字、清楚的主次和有意保留的空白。
## Workflow Routing
| 工作 | 入口 |
|---|---|
| 生成、重排或改进演示 | [Workflows/Generate.md](Workflows/Generate.md) |
## Gotchas
- share、talk 等用途标签不决定颜色。未指定视觉主题时使用 hacker-dark。
- 两行可以是一个判断。role 由讲述功能决定；行数只参与字号与分页。ljg-push
When your agent uses it
把 ~/.agents/skills/ljg-* 里所有更新过的 skills 同步到 github repo (ljg-skills)，先推 master 分支（org-mode 输出风格），再切 md 分支（markdown 输出风格）做基础 markdown 化后推。Use when user says '/ljg-push', 'push skills', '推送 skills', '同步 skills', 'sync ljg', or whenever ljg-* skills get updated and need shipping. NOT FOR pushing non-ljg skills or arbitrary git repos.
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
2,926 tokensWhen the skill is activated
Reference documents
1,439 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 仓库路径（硬编码）
- 两条分支的差异
- 工作流
- README 一致性（硬 gate）
- 自动转换的范围
- Voice Notification
- Examples
- Gotchas
Scripts executed separately
Tools/MdizeEmbeddedOrg.test.tsTools/MdizeEmbeddedOrg.tsTools/Push.shTools/Push.test.ts
Files
SKILL.mdcore9,945 bytesSKILL.mdcore9,945 bytesSKILL.mdcore9,945 bytesTools/MdizeEmbeddedOrg.test.tsruns2,873 bytesTools/MdizeEmbeddedOrg.tsruns3,739 bytesTools/Push.shruns32,665 bytesTools/Push.test.tsruns15,973 bytesWorkflows/Push.mddoc4,832 bytes
Read SKILL.md
# ljg-push: 推送 ljg-* skills
把本地 `~/.agents/skills/ljg-*` 里改过的 skills，一键同步到 github repo，覆盖 master 和 md 两个分支。
## 仓库路径（硬编码）
```
SKILLS_REPO="$HOME/code/ljg-skills" # 本地工作 repo
SKILLS_LOCAL="$HOME/.agents/skills" # 本地 skill 源
REPO_URL="git@github.com:lijigang/ljg-skills.git"
```
如果 `$SKILLS_REPO` 不存在，脚本会自动 clone。如果它存在但不是 ljg-skills 的 git repo，脚本会报错退出（不破坏现有目录）。
ljg-qa
When your agent uses it
信息提问机。给一篇文章/论文/书，把核心观点抽成 Q-A 对——Question 切要害，不教科书；Answer 简洁清晰，有形式化收口，逻辑链完整。读者顺 Q 链走过，每个 A 砸下一枚钉子，复现作者整套推理。Use when user says '问答', 'Q&A', 'QA', '提问', '抽取问题', '/ljg-qa', or shares an article/paper/book and asks for Q-A extraction. Triggers when the user wants ideas extracted not as a summary but as a sequence of incisive questions with answered. NOT FOR FAQ generation, glossary creation, or comprehension quizzes — this is intellectual scaffolding, not study aids.
What it loads into context
Frontmatter
179 tokensAlways available to the agent
SKILL.md
1,245 tokensWhen the skill is activated
Reference documents
3,742 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你不是
- 你是
- 三条铁律
- 工作流
- 设计参考
- Voice Notification
- 输出
- Examples
- Gotchas
Files
References/QuestionDesign.mddoc5,826 bytesSKILL.mdcore4,187 bytesSKILL.mdcore4,187 bytesWorkflows/Extract.mddoc5,959 bytes
Read SKILL.md
# ljg-qa: 问答提取
读一份东西，把它的思想拆成「为什么—怎么—边界」的问答链。
读者顺着 Q 走过去，每个 A 砸下来一枚钉子。
## 你不是
- 不是 FAQ 生成器（"什么是 X"——读者一看就跳过）
- 不是摘要换皮（把段落拆成"问/答"两半还是摘要）
- 不是知识点列表（孤立的事实碰撞不出洞察）
- 不是阅读理解题（提问不是为了考读者，是为了切中作者）
## 你是ljg-rank
When your agent uses it
给一个领域，找出背后真正撑着它的几根独立的力。十几个现象砍到不可再少的生成器——砍完能把现象一个个生回来，才算数。Use when user says '降秩', '找秩', '秩是什么', '这个领域靠什么撑着', '背后是什么', or wants to decompose any domain to its irreducible generators.
What it loads into context
Frontmatter
110 tokensAlways available to the agent
SKILL.md
7,609 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 秩是什么
- 怎么找:先抬头,再往下挖
- 五条心内判据
- 两层判断:先找 root rank,再看能不能叠坐标系
- 中文母语化 · 反坍缩闸
- 怎么写
- 文末配一张 ASCII 结构图——形式跟着骨架走
- 输出
Files
SKILL.mdcore25,039 bytesreferences/template.orgasset121 bytes
Read SKILL.md
# 降秩引擎
输入一个领域，输出它的秩。
## 秩是什么
秩不是"关键要素",不是"核心原则",不是"总结要点"。
秩是这么个东西:这个领域里真正独立的生成器,究竟有几根?拿这几根,能不能把全部现象一个个倒回来?能,才算找到。
但能倒回来只是底线。**Deutsch 在《无穷的开始》里立的尺**——好解释要过两关:
- **解释力**(reach)——不光能推出清单里的现象,还能推出清单外的,而且现实里真验得上。
- **难以变更**(hard to vary)——每根生成器、每个细节,都是被现象逼出来的。动一处,预测就崩。ljg-read
When your agent uses it
用《学习观》的「下上结构」讲透用户提供的文本：从具体情境接通概念、判别依据与有条件的关系，让读者理解原意并能迁移判断；默认直接在对话中展示。USE WHEN 用户说「伴读」「陪我读」「读这篇」「讲透这段」「read with me」或提供文本希望深入浅出地讲解。NOT FOR 单纯翻译、整本书拆解或只画概念地图。
What it loads into context
Frontmatter
129 tokensAlways available to the agent
SKILL.md
2,376 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow Routing
- 《学习观》的下上结构
- 讲解约定
- 可选交互
- Gotchas
- Examples
- 交付检查
Files
SKILL.mdcore8,946 bytes
Read SKILL.md
# 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
ljg-relationship
When your agent uses it
Relationship analyst combining structural diagnostics (5-layer framework) with psychoanalytic depth (transference, unconscious patterns, resistance). Guides users through dialogue to "see" the real structure of their relationship issues. Use when user says "关系分析", "分析关系", "relationship", "人际关系", or describes a specific relationship problem they want to understand.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
2,739 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Instructions
- 对话流程
- 判断路径速查
Files
SKILL.mdcore10,706 bytes
Read SKILL.md
## Usage
<example>
User: /ljg-relationship 我和老板的关系最近很紧张
Assistant: [启动关系分析对话，从表层行为逐步引导到深层结构]
</example>
<example>
User: 关系分析 我跟合伙人总是在同一个问题上吵架
Assistant: [识别"反复出现的模式"信号，启动结构+精神分析双轨诊断]
</example>
## Instructions
ljg-roundtable
When your agent uses it
一个议题，一场圆桌：主持人请来 3-5 位真实人物，定义开场，逐轮交锋， 每轮收一张 ASCII 结构图，用户用指令控节奏（可/止/深入此节/引入新人物）， 散场后全文存入 Markdown 笔记。Use when user says "圆桌讨论", "圆桌", "roundtable", "辩论", or wants to explore a topic through multi-perspective structured debate.
What it loads into context
Frontmatter
126 tokensAlways available to the agent
SKILL.md
1,376 tokensWhen the skill is activated
Reference documents
1,816 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Instructions
Files
SKILL.mdcore4,567 bytesreferences/original-prompt.mddoc7,747 bytes
Read SKILL.md
## Usage
<example>
User: 圆桌讨论 人工智能是否拥有真正的创造力？
Assistant: [主持人开场，请出人物，从定义谈起]
</example>
<example>
User: 圆桌 自由意志是否存在？
Assistant: [就自由意志展开圆桌]
</example>
## Instructions
ljg-structure
When your agent uses it
找出一段信息中母题级别的结构，把抽象关系展开回具体可见的现象，再用风洞检验关键因果与边界。USE WHEN user says '找结构', '母题是什么', '结构风洞', '背后的结构', '不要只做AB测试', or wants the generative mechanism beneath a problem. 仅当用户明确要求时展开跨域来源或多母题组合。NOT FOR 普通摘要、单个类比、事实查询或已有明确唯一解的执行题。
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
2,393 tokensWhen the skill is activated
Reference documents
2,703 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 四个概念，不能混
- 理解契约
- 适用边界
- Workflow Routing
- Gotchas
- 输出要求
- Examples
Files
SKILL.mdcore8,911 bytesWorkflows/FindStructure.mddoc10,185 bytes
Read SKILL.md
# 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ljg-teach
When your agent uses it
用体验而不是定义来教授概念、原理或检验观点：先给与学习者认知水平相称的局面，让其选择，再用公平的意外显化认知缺口，结构化后才命名，并以迁移局面循环复测。USE WHEN 用户调用 '/ljg-teach'、说 '用情境教我'、'别先讲答案'、'通过案例让我学会'，或希望通过选择与反馈理解一个概念或观点。NOT FOR 直接定义查询（用 ljg-is/ljg-word）、八维概念解剖（用 ljg-learn）、伴读文本（用 ljg-read）。
What it loads into context
Frontmatter
174 tokensAlways available to the agent
SKILL.md
2,143 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow Routing
- 理想状态
- 体验循环
- 交互节奏
- Gotchas
- Examples
Files
SKILL.mdcore8,008 bytes
Read SKILL.md
# 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。
```text
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 |
|---|---|ljg-think
When your agent uses it
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.
What it loads into context
Frontmatter
126 tokensAlways available to the agent
SKILL.md
823 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你是什么
- 钻的逻辑
- 怎么钻
- 什么算到底
- 怎么写
- 输出
Files
SKILL.mdcore2,815 bytes
Read SKILL.md
# 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，ljg-word
When your agent uses it
Deep-dive English word mastery tool. Deconstructs a single English word into core semantics and epiphany. Use when user asks to explain/master a specific English word.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
372 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Instructions
Files
SKILL.mdcore1,301 bytes
Read SKILL.md
## Usage
<example>
User: Deeply explain the word "Serendipity".
Assistant: [Calls ljg-explain-words with "Serendipity"]
</example>
## Instructions
目标不是翻译，而是让用户掌握这个词的深层含义和用法。
针对输入的 `word`（转换为小写，首字母大写），进行以下分析，直接在对话中用 Markdown 输出：
### 输出结构ljg-writes
When your agent uses it
写作引擎。把一个观点写成可理解、可迁移、经得住反例的 1000-1500 字中文文章。USE WHEN 写文章 OR 优化思想内容 OR 展开观点 OR 改写成逻辑递进的中文。NOT FOR 普通摘要、事实查询或结构风洞（用 ljg-structure）。
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
2,156 tokensWhen the skill is activated
Reference documents
2,307 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow Routing
- 成文契约
- 怎样解释一个观点
- 姿态与语言
- 最后检查
- Gotchas
- Examples
- 输出约束
Files
SKILL.mdcore8,224 bytesWorkflows/WriteEssay.mddoc9,023 bytes
Read SKILL.md
# 写作引擎
把一个观点讲清楚，让一个具体的人读懂它为什么成立、能用在哪里。用容易理解的案例说明关键关系；需要引入抽象概念时，先交代它能解释什么。
## Workflow Routing
| Workflow | Trigger | File |
|---|---|---|
| *WriteEssay* | 写文章、优化思想内容、展开或重写观点 | `Workflows/WriteEssay.md` |
执行时完整读取工作流。分析和检查在内部完成，正文按内容需要展开，不逐项展示写作步骤。
## 成文契约
Skills included
- ljg-analogy
- ljg-blind
- ljg-book
- ljg-business-model
- ljg-card
- ljg-classic
- ljg-constraint
- ljg-explain
- ljg-invest
- ljg-is
- ljg-learn
- ljg-map
- ljg-mechanism
- ljg-paper
- ljg-present
- ljg-push
- ljg-qa
- ljg-rank
- ljg-read
- ljg-relationship
- ljg-roundtable
- ljg-structure
- ljg-teach
- ljg-think
- ljg-word
- ljg-writes
Repository facts
- License
- MIT
- Created
- Mar 8, 2026
- Last pushed
- Nov 2, 2026
- Forks
- 855
- Open issues
- 2
- Project activity
- Active
Rank over the last 12 weeks
Now #191 · best #154 · down 18 in 30 days
- #188 on Oct 30
- #189 on Oct 31
- #188 from Nov 1 to Nov 2
- #189 on Nov 3
- #190 on Nov 4
- #191 since Nov 5
60 earlier periods
- #154 on Aug 2
- #154 from Aug 7 to Aug 9
- #157 on Aug 10
- #158 on Aug 11
- #156 on Aug 12
- #158 from Aug 13 to Aug 14
- #157 from Aug 15 to Aug 16
- #156 on Aug 17
- #157 from Aug 18 to Aug 19
- #156 from Aug 20 to Aug 21
- #154 on Aug 22
- #158 from Aug 23 to Aug 24
- #157 from Aug 25 to Aug 26
- #158 on Aug 27
- #157 on Aug 28
- #158 on Aug 29
- #156 from Aug 30 to Aug 31
- #158 on Sep 1
- #155 on Sep 2
- #160 on Sep 3
- #159 on Sep 4
- #161 on Sep 5
- #159 on Sep 6
- #161 from Sep 7 to Sep 8
- #162 on Sep 9
- #163 on Sep 10
- #160 on Sep 11
- #164 from Sep 12 to Sep 14
- #165 on Sep 15
- #164 from Sep 16 to Sep 17
- #165 on Sep 18
- #163 on Sep 19
- #166 on Sep 20
- #167 from Sep 21 to Sep 22
- #168 from Sep 23 to Sep 26
- #169 on Sep 27
- #170 from Sep 28 to Sep 29
- #167 on Sep 30
- #171 on Oct 1
- #172 on Oct 2
- #169 on Oct 3
- #168 on Oct 4
- #171 from Oct 5 to Oct 6
- #173 on Oct 7
- #171 on Oct 8
- #174 on Oct 9
- #172 on Oct 10
- #175 on Oct 11
- #176 on Oct 12
- #179 from Oct 13 to Oct 14
- #180 on Oct 15
- #179 on Oct 16
- #181 on Oct 17
- #182 on Oct 18
- #181 on Oct 19
- #180 on Oct 20
- #182 from Oct 21 to Oct 23
- #183 on Oct 24
- #185 on Oct 25
- #186 from Oct 28 to Oct 29
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 54 notes
skills/ljg-business-model/Example.html:4Analysis incomplete: physical or joined line exceeds character limitskills/ljg-business-model/Example.html:2Analysis incomplete: physical or joined line exceeds character limitskills/ljg-business-model/Example.html:3Analysis incomplete: physical or joined line exceeds character limitskills/ljg-business-model/Tools/Render.ts:101Analysis incomplete: physical or joined line exceeds character limitskills/ljg-business-model/Tools/Render.ts:99Analysis incomplete: physical or joined line exceeds character limitskills/ljg-business-model/Tools/Render.ts:100Analysis incomplete: physical or joined line exceeds character limitskills/ljg-paper/evals/plain-language-pair.json:14Analysis incomplete: physical or joined line exceeds character limitskills/ljg-paper/evals/plain-language-pair.json:12Analysis incomplete: physical or joined line exceeds character limitskills/ljg-paper/evals/plain-language-pair.json:13Analysis incomplete: physical or joined line exceeds character limitskills/ljg-push/Tools/Push.sh:283Analysis incomplete: physical or joined line exceeds character limitskills/ljg-blind/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ljg-blind/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ljg-blind/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ljg-blind/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ljg-blind/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ljg-blind/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ljg-book/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ljg-business-model/Example.html:4Analysis incomplete: physical or joined line exceeds character limitskills/ljg-business-model/Example.html:2Analysis incomplete: physical or joined line exceeds character limitskills/ljg-business-model/Example.html:3Analysis incomplete: physical or joined line exceeds character limit
- No broad tool permissions
- 10 dangerous shell commandsin 4 files: skills/ljg-present/Tools/ValidateDeck.ts:97 skills/ljg-card/assets/verify-full-text.test.ts:2 skills/ljg-classic/Tools/RenderClassic.test.ts:2 and 1 more
- 197 network referencesin 25 files: skills/ljg-paper/scripts/validate_note.test.ts:10 skills/ljg-blind/SKILL.md:107 skills/ljg-card/package-lock.json:11 and 22 more
- 4 obfuscation signalsin 2 files: skills/ljg-business-model/Tools/Render.ts:101 skills/ljg-present/Tools/ValidateDeck.ts:13
- No instruction overrides
- 64 executable scriptsin 32 files: skills/ljg-blind/Tools/WeReadWebUrl.ts:1 skills/ljg-book/scripts/validate_note.test.ts:1 skills/ljg-book/scripts/validate_note.ts:1 and 29 more
- 10 references to secretsin 1 file: skills/ljg-blind/SKILL.md:102
- No requests to vote in Hot
Show all 285 signals by file
.claude-plugin/marketplace.json
- Network accessline 6
"owner": { "name": "lijigang", "url": "https://github.com/lijigang" - Network accessline 7
"name": "lijigang", "url": "https://github.com/lijigang" }, - Network accessline 8
"url": "https://github.com/lijigang" - Network accessline 9
}, "repository": "https://github.com/lijigang/ljg-skills", "license": "MIT", - Network accessline 10
"repository": "https://github.com/lijigang/ljg-skills",
.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "lijigang", "url": "https://github.com/lijigang" - Network accessline 6
"name": "lijigang", "url": "https://github.com/lijigang" }, - Network accessline 7
"url": "https://github.com/lijigang" - Network accessline 8
}, "repository": "https://github.com/lijigang/ljg-skills", "keywords": ["skills", "paper-reading", "content-casting", "writing"], - Network accessline 9
"repository": "https://github.com/lijigang/ljg-skills",
skills/ljg-analogy/Theory.md
- Network accessline 3
来源：Dedre Gentner (1983), *Structure-Mapping: A Theoretical Framework for Analogy*, Cognitive Science, 7(2), 155–170。[作者机构提供的论文](https://groups.psych.northwestern.edu/gentner/papers/Gentner83.2b.pdf)。以下页码是期刊页码。
skills/ljg-blind/SKILL.md
- Access to secretsline 102
[Credential-related source omitted] - Access to secretsline 102
[Credential-related source omitted] - Network accessline 107
[Credential-related source omitted] - Network accessline 107
[Credential-related source omitted] - Access to secretsline 107
[Credential-related source omitted] - Access to secretsline 107
[Credential-related source omitted] - Access to secretsline 108
[Credential-related source omitted] - Access to secretsline 108
[Credential-related source omitted] - Network accessline 118
[Credential-related source omitted] - Network accessline 118
[Credential-related source omitted] - Access to secretsline 118
[Credential-related source omitted] - Access to secretsline 118
[Credential-related source omitted] - Access to secretsline 119
[Credential-related source omitted] - Access to secretsline 119
[Credential-related source omitted] - Network accessline 137
https://weread.qq.com/web/reader/{encodedBookId}k{encodedChapterUid} - Network accessline 137
https://weread.qq.com/web/reader/{encodedBookId}k{encodedChapterUid} - Network accessline 172
- 章节：<章节标题> - 时长：约 N 分钟 - 链接：[在微信读书网页版阅读本章](https://weread.qq.com/web/reader/ENCODED_BOOKkENCODED_CHAPTER) - Network accessline 172
- 章节：<章节标题> - 时长：约 N 分钟 - 链接：[在微信读书网页版阅读本章](https://weread.qq.com/web/reader/ENCODED_BOOKkENCODED_CHAPTER) - Network accessline 173
- 时长：约 N 分钟 - 链接：[在微信读书网页版阅读本章](https://weread.qq.com/web/reader/ENCODED_BOOKkENCODED_CHAPTER) - 为什么是它：<3-4 句。把盲区和这一章对上——这章具体讲什么、怎么补这个盲区。不要泛泛说"开阔视野"，要说清这一章的哪个东西正对这个盲区的哪个缺口。> - Network accessline 173
- 时长：约 N 分钟 - 链接：[在微信读书网页版阅读本章](https://weread.qq.com/web/reader/ENCODED_BOOKkENCODED_CHAPTER) - 为什么是它：<3-4 句。把盲区和这一章对上——这章具体讲什么、怎么补这个盲区。不要泛泛说"开阔视野"，要说清这一章的哪个东西正对这个盲区的哪个缺口。> - Network accessline 174
- 链接：[在微信读书网页版阅读本章](https://weread.qq.com/web/reader/ENCODED_BOOKkENCODED_CHAPTER) - Network accessline 174
- 链接：[在微信读书网页版阅读本章](https://weread.qq.com/web/reader/ENCODED_BOOKkENCODED_CHAPTER) - Network accessline 200
- 盲区有具体证据吗？每一处都能指到昨天哪几句话？没有就退回第三步。 - 只选了 1 个盲区、说透了吗？还是贪多点了三四个？ - 章节链接以 `https://weread.qq.com/web/reader/` 开头，并由工具用非空 bookId、chapterUid 生成？ - Network accessline 200
- 盲区有具体证据吗？每一处都能指到昨天哪几句话？没有就退回第三步。 - 只选了 1 个盲区、说透了吗？还是贪多点了三四个？ - 章节链接以 `https://weread.qq.com/web/reader/` 开头，并由工具用非空 bookId、chapterUid 生成？ - Network accessline 201
- 只选了 1 个盲区、说透了吗？还是贪多点了三四个？ - 章节链接以 `https://weread.qq.com/web/reader/` 开头，并由工具用非空 bookId、chapterUid 生成？ - 全文没有残留只能唤起移动 App 的专用协议链接？ - Network accessline 201
- 只选了 1 个盲区、说透了吗？还是贪多点了三四个？ - 章节链接以 `https://weread.qq.com/web/reader/` 开头，并由工具用非空 bookId、chapterUid 生成？ - 全文没有残留只能唤起移动 App 的专用协议链接？ - Network accessline 202
- 章节链接以 `https://weread.qq.com/web/reader/` 开头，并由工具用非空 bookId、chapterUid 生成？ - Network accessline 202
- 章节链接以 `https://weread.qq.com/web/reader/` 开头，并由工具用非空 bookId、chapterUid 生成？ - Network accessline 210
- **网页版 reader 路径使用编码 ID。** `https://weread.qq.com/web/reader/573976?chapterUid=13` 会返回 404；必须用 `Tools/WeReadWebUrl.ts` 分别编码 bookId 与 chapterUid，再用 `k` 连接。 - Network accessline 210
- **网页版 reader 路径使用编码 ID。** `https://weread.qq.com/web/reader/573976?chapterUid=13` 会返回 404；必须用 `Tools/WeReadWebUrl.ts` 分别编码 bookId 与 chapterUid，再用 `k` 连接。
skills/ljg-blind/Tools/WeReadWebUrl.help.md
skills/ljg-blind/Tools/WeReadWebUrl.ts
skills/ljg-book/scripts/validate_note.test.ts
skills/ljg-book/scripts/validate_note.ts
skills/ljg-business-model/CanvasGuide.md
- Network accessline 37
- [官方说明](https://www.strategyzer.com/library/the-business-model-canvas)：九模块、单一业务模型的范围与左右结构。 - Network accessline 37
- [官方说明](https://www.strategyzer.com/library/the-business-model-canvas)：九模块、单一业务模型的范围与左右结构。 - Network accessline 38
- [官方画布 PDF](https://assets.strategyzer.com/assets/resources/the-business-model-canvas.pdf)：模块布局、署名与 CC BY-SA 3.0。 - Network accessline 38
- [官方画布 PDF](https://assets.strategyzer.com/assets/resources/the-business-model-canvas.pdf)：模块布局、署名与 CC BY-SA 3.0。 - Network accessline 39
- [工具使用说明](https://www.strategyzer.com/legal/usage-of-our-tools)：改编版本应保留清晰的 Strategyzer.com 归属。 - Network accessline 39
- [工具使用说明](https://www.strategyzer.com/legal/usage-of-our-tools)：改编版本应保留清晰的 Strategyzer.com 归属。 - Network accessline 41
查阅日期：2026-10-08。中文翻译可能随版本采用不同名称；默认用上表标题，可在条目解释同义词。画布模板改编按 [CC BY-SA 3.0](https://creativecommons.org/licenses/by-sa/3.0/) 标示；不把此许可扩张到用户提供的商业信息。 - Network accessline 41
查阅日期：2026-10-08。中文翻译可能随版本采用不同名称；默认用上表标题，可在条目解释同义词。画布模板改编按 [CC BY-SA 3.0](https://creativecommons.org/licenses/by-sa/3.0/) 标示；不把此许可扩张到用户提供的商业信息。
skills/ljg-business-model/Example.html
- Network accessline 64
<div class="bottom"><span>基于当前材料整理 · 材料提供 ≠ 外部验证 · 画布不代表商业模式已获验证</span><span class="signal">1 项推测 · 1 项待补充</span></div> <div class="sources">材料：S1 虚构项目说明，仅用于演示</div> <footer class="credit"><span>基于《商业模式新生代》 · Alexander Osterwalder & Yve - Network accessline 64
<div class="bottom"><span>基于当前材料整理 · 材料提供 ≠ 外部验证 · 画布不代表商业模式已获验证</span><span class="signal">1 项推测 · 1 项待补充</span></div> <div class="sources">材料：S1 虚构项目说明，仅用于演示</div> <footer class="credit"><span>基于《商业模式新生代》 · Alexander Osterwalder & Yve - Network accessline 65
<div class="sources">材料：S1 虚构项目说明，仅用于演示</div> <footer class="credit"><span>基于《商业模式新生代》 · Alexander Osterwalder & Yves Pigneur<br>中文翻译与视觉排版改编 · 业务材料权利归原权利人</span><span><strong>Business Model Canvas · <a href="https://www.strategyzer.com/ - Network accessline 65
<div class="sources">材料：S1 虚构项目说明，仅用于演示</div> <footer class="credit"><span>基于《商业模式新生代》 · Alexander Osterwalder & Yves Pigneur<br>中文翻译与视觉排版改编 · 业务材料权利归原权利人</span><span><strong>Business Model Canvas · <a href="https://www.strategyzer.com/ - Network accessline 66
<footer class="credit"><span>基于《商业模式新生代》 · Alexander Osterwalder & Yves Pigneur<br>中文翻译与视觉排版改编 · 业务材料权利归原权利人</span><span><strong>Business Model Canvas · <a href="https://www.strategyzer.com/">Strategyzer.com</a></strong><br>画布模板：<a href - Network accessline 66
<footer class="credit"><span>基于《商业模式新生代》 · Alexander Osterwalder & Yves Pigneur<br>中文翻译与视觉排版改编 · 业务材料权利归原权利人</span><span><strong>Business Model Canvas · <a href="https://www.strategyzer.com/">Strategyzer.com</a></strong><br>画布模板：<a href
skills/ljg-business-model/Tools/Render.test.ts
skills/ljg-business-model/Tools/Render.ts
- Executable scriptline 1
#!/usr/bin/env bun - Executable scriptline 1
#!/usr/bin/env bun - Possible obfuscationline 101
*{box-sizing:border-box}html,body{margin:0;padding:0;background:#e9e8e1;color:#222b32}body{font-family:"PingFang SC","Noto Sans CJK SC","Microsoft YaHei",sans-serif}#canvas{width:${width}px;padding:42px 42px 28px;background:#f6f5ef;--rule:# - Possible obfuscationline 101
*{box-sizing:border-box}html,body{margin:0;padding:0;background:#e9e8e1;color:#222b32}body{font-family:"PingFang SC","Noto Sans CJK SC","Microsoft YaHei",sans-serif}#canvas{width:${width}px;padding:42px 42px 28px;background:#f6f5ef;--rule:# - Network accessline 107
<div class="bottom"><span>基于当前材料整理 · 材料提供 ≠ 外部验证 · 画布不代表商业模式已获验证</span><span class="signal">${inferred} 项推测 · ${unknown} 项待补充</span></div> <div class="sources">材料：${model.sources.length ? model.sources.map(s => `${esc(s.id)} ${esc(s.label)} - Network accessline 107
<div class="bottom"><span>基于当前材料整理 · 材料提供 ≠ 外部验证 · 画布不代表商业模式已获验证</span><span class="signal">${inferred} 项推测 · ${unknown} 项待补充</span></div> <div class="sources">材料：${model.sources.length ? model.sources.map(s => `${esc(s.id)} ${esc(s.label)} - Network accessline 108
<div class="sources">材料：${model.sources.length ? model.sources.map(s => `${esc(s.id)} ${esc(s.label)}`).join(" ／ ") : "尚未提供"}</div> <footer class="credit"><span>基于《商业模式新生代》 · Alexander Osterwalder & Yves Pigneur<br>中文翻译与视觉排版改编 · 业务材料权利归 - Network accessline 108
<div class="sources">材料：${model.sources.length ? model.sources.map(s => `${esc(s.id)} ${esc(s.label)}`).join(" ／ ") : "尚未提供"}</div> <footer class="credit"><span>基于《商业模式新生代》 · Alexander Osterwalder & Yves Pigneur<br>中文翻译与视觉排版改编 · 业务材料权利归 - Network accessline 109
<footer class="credit"><span>基于《商业模式新生代》 · Alexander Osterwalder & Yves Pigneur<br>中文翻译与视觉排版改编 · 业务材料权利归原权利人</span><span><strong>Business Model Canvas · <a href="https://www.strategyzer.com/">Strategyzer.com</a></strong><br>画布模板：<a href - Network accessline 109
<footer class="credit"><span>基于《商业模式新生代》 · Alexander Osterwalder & Yves Pigneur<br>中文翻译与视觉排版改编 · 业务材料权利归原权利人</span><span><strong>Business Model Canvas · <a href="https://www.strategyzer.com/">Strategyzer.com</a></strong><br>画布模板：<a href
skills/ljg-card/assets/audit.ts
skills/ljg-card/assets/build-fixtures.ts
skills/ljg-card/assets/capture.test.ts
skills/ljg-card/assets/capture.ts
skills/ljg-card/assets/comic_template.html
- Network accessline 4
<meta charset="UTF-8"> <style> @import url('https://fonts.googleapis.com/css2?family=Noto+Serif+SC:wght@400;700;900&family=DM+Sans:wght@400;500;700&display=swap'); - Network accessline 4
<meta charset="UTF-8"> <style> @import url('https://fonts.googleapis.com/css2?family=Noto+Serif+SC:wght@400;700;900&family=DM+Sans:wght@400;500;700&display=swap'); - Network accessline 6
@import url('https://fonts.googleapis.com/css2?family=Noto+Serif+SC:wght@400;700;900&family=DM+Sans:wght@400;500;700&display=swap'); - Network accessline 6
@import url('https://fonts.googleapis.com/css2?family=Noto+Serif+SC:wght@400;700;900&family=DM+Sans:wght@400;500;700&display=swap');
skills/ljg-card/assets/prepare-whiteboard-source.test.ts
skills/ljg-card/assets/prepare-whiteboard-source.ts
skills/ljg-card/assets/verify-full-text.test.ts
skills/ljg-card/assets/verify-full-text.ts
skills/ljg-card/package-lock.json
- Network accessline 11
"node_modules/fsevents": { "version": "2.3.2", "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz", - Network accessline 11
"node_modules/fsevents": { "version": "2.3.2", "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz", - Network accessline 12
"version": "2.3.2", "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz", "integrity": "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==", - Network accessline 12
"version": "2.3.2", "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz", "integrity": "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==", - Network accessline 13
"resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz", - Network accessline 13
"resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz", - Network accessline 25
"node_modules/playwright": { "version": "1.58.2", "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.58.2.tgz", - Network accessline 25
"node_modules/playwright": { "version": "1.58.2", "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.58.2.tgz", - Network accessline 26
"version": "1.58.2", "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.58.2.tgz", "integrity": "sha512-vA30H8Nvkq/cPBnNw4Q8TWz1EJyqgpuinBcHET0YVJVFldr8JDNiU9LaWAE1KqSkRYazuaBhTpB5ZzShOezQ6A==", - Network accessline 26
"version": "1.58.2", "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.58.2.tgz", "integrity": "sha512-vA30H8Nvkq/cPBnNw4Q8TWz1EJyqgpuinBcHET0YVJVFldr8JDNiU9LaWAE1KqSkRYazuaBhTpB5ZzShOezQ6A==", - Network accessline 27
"resolved": "https://registry.npmjs.org/playwright/-/playwright-1.58.2.tgz", - Network accessline 27
"resolved": "https://registry.npmjs.org/playwright/-/playwright-1.58.2.tgz", - Network accessline 43
"node_modules/playwright-core": { "version": "1.58.2", "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.58.2.tgz", - Network accessline 43
"node_modules/playwright-core": { "version": "1.58.2", "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.58.2.tgz", - Network accessline 44
"version": "1.58.2", "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.58.2.tgz", "integrity": "sha512-yZkEtftgwS8CsfYo7nm0KE8jsvm6i/PTgVtB8DL726wNf6H2IMsDuxCpJj59KDaxCtSnrWan2AeDqM7JBaultg==", - Network accessline 44
"version": "1.58.2", "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.58.2.tgz", "integrity": "sha512-yZkEtftgwS8CsfYo7nm0KE8jsvm6i/PTgVtB8DL726wNf6H2IMsDuxCpJj59KDaxCtSnrWan2AeDqM7JBaultg==", - Network accessline 45
"resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.58.2.tgz", - Network accessline 45
"resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.58.2.tgz",
skills/ljg-card/package.json
skills/ljg-classic/Tools/RenderClassic.test.ts
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Dangerous shell operationline 2
import { mkdir, mkdtemp, rm } from "node:fs/promises"; - Dangerous shell operationline 2
import { mkdir, mkdtemp, rm } from "node:fs/promises"; - Network accessline 77
test("rejects remote and data hero sources", () => { for (const heroImage of ["https://example.com/hero.png", "data:image/png;base64,AAAA"]) { - Network accessline 77
test("rejects remote and data hero sources", () => { for (const heroImage of ["https://example.com/hero.png", "data:image/png;base64,AAAA"]) { - Network accessline 78
for (const heroImage of ["https://example.com/hero.png", "data:image/png;base64,AAAA"]) { - Network accessline 78
for (const heroImage of ["https://example.com/hero.png", "data:image/png;base64,AAAA"]) { - Network accessline 206
const spec = validateSpec({ ...validSpec, source: "維基文庫固定修订 https://zh.wikisource.org/w/index.php?title=%E9%81%93%E5%BE%B7%E7%B6%93&oldid=2354026", - Network accessline 206
const spec = validateSpec({ ...validSpec, source: "維基文庫固定修订 https://zh.wikisource.org/w/index.php?title=%E9%81%93%E5%BE%B7%E7%B6%93&oldid=2354026", - Network accessline 207
...validSpec, source: "維基文庫固定修订 https://zh.wikisource.org/w/index.php?title=%E9%81%93%E5%BE%B7%E7%B6%93&oldid=2354026", passages: [{ - Network accessline 207
...validSpec, source: "維基文庫固定修订 https://zh.wikisource.org/w/index.php?title=%E9%81%93%E5%BE%B7%E7%B6%93&oldid=2354026", passages: [{ - Network accessline 208
source: "維基文庫固定修订 https://zh.wikisource.org/w/index.php?title=%E9%81%93%E5%BE%B7%E7%B6%93&oldid=2354026", - Network accessline 208
source: "維基文庫固定修订 https://zh.wikisource.org/w/index.php?title=%E9%81%93%E5%BE%B7%E7%B6%93&oldid=2354026",
skills/ljg-classic/Tools/RenderClassic.ts
skills/ljg-classic/Tools/ValidateClassic.ts
skills/ljg-classic/package.json
skills/ljg-is/Tools/ValidateNote.test.ts
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Network accessline 359
const old = goodV4Org().replace("改变不只在于", "The One 是 X -> Y。改变不只在于"); const placeholder = goodV4Org().replace("网约车", "{目标}"); const markdown = goodV4Org().replace("网约车", "[网约车](https://example.com)"); - Network accessline 359
const old = goodV4Org().replace("改变不只在于", "The One 是 X -> Y。改变不只在于"); const placeholder = goodV4Org().replace("网约车", "{目标}"); const markdown = goodV4Org().replace("网约车", "[网约车](https://example.com)"); - Network accessline 360
const placeholder = goodV4Org().replace("网约车", "{目标}"); const markdown = goodV4Org().replace("网约车", "[网约车](https://example.com)"); expect(errorsFor(old).some((error) => error.includes("旧合同"))).toBe(true); - Network accessline 360
const placeholder = goodV4Org().replace("网约车", "{目标}"); const markdown = goodV4Org().replace("网约车", "[网约车](https://example.com)"); expect(errorsFor(old).some((error) => error.includes("旧合同"))).toBe(true); - Network accessline 361
const markdown = goodV4Org().replace("网约车", "[网约车](https://example.com)"); - Network accessline 361
const markdown = goodV4Org().replace("网约车", "[网约车](https://example.com)");
skills/ljg-is/Tools/ValidateNote.ts
skills/ljg-paper/evals/evals.json
- Network accessline 154
{ "id": 11, "prompt": "请用 ljg-paper 直接解释原论文 https://arxiv.org/abs/2307.03172v3，不保存用户笔记。评估执行时提供完整PDF或同源全文；正文临时保存供独立试读。", - Network accessline 154
{ "id": 11, "prompt": "请用 ljg-paper 直接解释原论文 https://arxiv.org/abs/2307.03172v3，不保存用户笔记。评估执行时提供完整PDF或同源全文；正文临时保存供独立试读。", - Network accessline 155
"id": 11, "prompt": "请用 ljg-paper 直接解释原论文 https://arxiv.org/abs/2307.03172v3，不保存用户笔记。评估执行时提供完整PDF或同源全文；正文临时保存供独立试读。", "files": [], - Network accessline 155
"id": 11, "prompt": "请用 ljg-paper 直接解释原论文 https://arxiv.org/abs/2307.03172v3，不保存用户笔记。评估执行时提供完整PDF或同源全文；正文临时保存供独立试读。", "files": [], - Network accessline 156
"prompt": "请用 ljg-paper 直接解释原论文 https://arxiv.org/abs/2307.03172v3，不保存用户笔记。评估执行时提供完整PDF或同源全文；正文临时保存供独立试读。", - Network accessline 156
"prompt": "请用 ljg-paper 直接解释原论文 https://arxiv.org/abs/2307.03172v3，不保存用户笔记。评估执行时提供完整PDF或同源全文；正文临时保存供独立试读。", - Network accessline 157
"files": [], "source_url": "https://arxiv.org/abs/2307.03172v3", "source_pdf_sha256": "653b29619eae2ae4b361d7bdcdc06db4bedcb1b0eabe31814036beca8c1af0b1", - Network accessline 157
"files": [], "source_url": "https://arxiv.org/abs/2307.03172v3", "source_pdf_sha256": "653b29619eae2ae4b361d7bdcdc06db4bedcb1b0eabe31814036beca8c1af0b1", - Network accessline 158
"source_url": "https://arxiv.org/abs/2307.03172v3", - Network accessline 158
"source_url": "https://arxiv.org/abs/2307.03172v3",
skills/ljg-paper/evals/plain-language-pair.json
- Network accessline 1
{ "version": 1, "source": "https://arxiv.org/abs/2609.02750v1", - Network accessline 1
{ "version": 1, "source": "https://arxiv.org/abs/2609.02750v1", - Network accessline 2
"version": 1, "source": "https://arxiv.org/abs/2609.02750v1", "source_pdf_sha256": "c97fb9d82e26045354ee03fece7ab5bb67b3766a7562363ed497f00d6ebf55d0", - Network accessline 2
"version": 1, "source": "https://arxiv.org/abs/2609.02750v1", "source_pdf_sha256": "c97fb9d82e26045354ee03fece7ab5bb67b3766a7562363ed497f00d6ebf55d0", - Network accessline 3
"source": "https://arxiv.org/abs/2609.02750v1", - Network accessline 3
"source": "https://arxiv.org/abs/2609.02750v1",
skills/ljg-paper/scripts/paper_map_compat.ts
skills/ljg-paper/scripts/validate_note.test.ts
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Network accessline 10
#+filetags: :paper: #+identifier: 20260820T091641 #+source: https://arxiv.org/abs/2608.14036 - Network accessline 10
#+filetags: :paper: #+identifier: 20260820T091641 #+source: https://arxiv.org/abs/2608.14036 - Network accessline 11
#+identifier: 20260820T091641 #+source: https://arxiv.org/abs/2608.14036 #+authors: A. Author, B. Author - Network accessline 11
#+identifier: 20260820T091641 #+source: https://arxiv.org/abs/2608.14036 #+authors: A. Author, B. Author - Network accessline 12
#+source: https://arxiv.org/abs/2608.14036 - Network accessline 12
#+source: https://arxiv.org/abs/2608.14036 - Network accessline 34
- 格式版本：2 - 原文位置：https://arxiv.org/abs/2608.14036 - Network accessline 34
- 格式版本：2 - 原文位置：https://arxiv.org/abs/2608.14036 - Network accessline 35
- 原文位置：https://arxiv.org/abs/2608.14036 - Network accessline 35
- 原文位置：https://arxiv.org/abs/2608.14036 - Network accessline 339
test("accepts one bare absolute local source path", () => { const local = validNote.replace("#+source: https://arxiv.org/abs/2608.14036", "#+source: /tmp/papers/source paper.pdf"); - Network accessline 339
test("accepts one bare absolute local source path", () => { const local = validNote.replace("#+source: https://arxiv.org/abs/2608.14036", "#+source: /tmp/papers/source paper.pdf"); - Network accessline 340
const local = validNote.replace("#+source: https://arxiv.org/abs/2608.14036", "#+source: /tmp/papers/source paper.pdf"); - Network accessline 340
const local = validNote.replace("#+source: https://arxiv.org/abs/2608.14036", "#+source: /tmp/papers/source paper.pdf"); - Network accessline 432
}); test("rejects mismatched source records", () => { const map = currentMap.replace("- 原文位置：https://arxiv.org/abs/2608.14036", "- 原文位置：https://example.org/unrelated-paper"); - Network accessline 432
}); test("rejects mismatched source records", () => { const map = currentMap.replace("- 原文位置：https://arxiv.org/abs/2608.14036", "- 原文位置：https://example.org/unrelated-paper"); - Network accessline 433
test("rejects mismatched source records", () => { const map = currentMap.replace("- 原文位置：https://arxiv.org/abs/2608.14036", "- 原文位置：https://example.org/unrelated-paper"); expect(validate(validNote, filename, map).errors.join("\n")). - Network accessline 433
test("rejects mismatched source records", () => { const map = currentMap.replace("- 原文位置：https://arxiv.org/abs/2608.14036", "- 原文位置：https://example.org/unrelated-paper"); expect(validate(validNote, filename, map).errors.join("\n")). - Network accessline 434
const map = currentMap.replace("- 原文位置：https://arxiv.org/abs/2608.14036", "- 原文位置：https://example.org/unrelated-paper"); - Network accessline 434
const map = currentMap.replace("- 原文位置：https://arxiv.org/abs/2608.14036", "- 原文位置：https://example.org/unrelated-paper"); - Network accessline 435
expect(validate(validNote, filename, map).errors.join("\n")).toContain("原文位置不一致"); const localNote = validNote.replace("https://arxiv.org/abs/2608.14036", "/tmp/source paper.pdf"); const localMap = currentMap.replace("- 原文位置：https:/ - Network accessline 435
expect(validate(validNote, filename, map).errors.join("\n")).toContain("原文位置不一致"); const localNote = validNote.replace("https://arxiv.org/abs/2608.14036", "/tmp/source paper.pdf"); const localMap = currentMap.replace("- 原文位置：https:/ - Network accessline 436
const localNote = validNote.replace("https://arxiv.org/abs/2608.14036", "/tmp/source paper.pdf"); - Network accessline 436
const localNote = validNote.replace("https://arxiv.org/abs/2608.14036", "/tmp/source paper.pdf"); - Network accessline 437
const localMap = currentMap.replace("- 原文位置：https://arxiv.org/abs/2608.14036", "- 原文位置：/tmp/source paper.pdf"); - Network accessline 437
const localMap = currentMap.replace("- 原文位置：https://arxiv.org/abs/2608.14036", "- 原文位置：/tmp/source paper.pdf");
skills/ljg-paper/scripts/validate_note.ts
skills/ljg-present/Fonts/IBMPlexMono-OFL.txt
- Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 3
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: https://openfontlicense.org - Network accessline 5
https://openfontlicense.org - Network accessline 5
https://openfontlicense.org
skills/ljg-present/References/RegressionDeck.json
- Network accessline 192
"id": "SRC-11", "content": { "pre": "<script> & <svg>\nhttps://example.com\nfetch(\"literal text\")" - Network accessline 192
"id": "SRC-11", "content": { "pre": "<script> & <svg>\nhttps://example.com\nfetch(\"literal text\")" - Network accessline 193
"content": { "pre": "<script> & <svg>\nhttps://example.com\nfetch(\"literal text\")" } - Network accessline 193
"content": { "pre": "<script> & <svg>\nhttps://example.com\nfetch(\"literal text\")" } - Network accessline 194
"pre": "<script> & <svg>\nhttps://example.com\nfetch(\"literal text\")" - Network accessline 194
"pre": "<script> & <svg>\nhttps://example.com\nfetch(\"literal text\")" - Network accessline 410
{ "role": "evidence", "pre": "<script> & <svg>\nhttps://example.com\nfetch(\"literal text\")", - Network accessline 410
{ "role": "evidence", "pre": "<script> & <svg>\nhttps://example.com\nfetch(\"literal text\")", - Network accessline 411
"role": "evidence", "pre": "<script> & <svg>\nhttps://example.com\nfetch(\"literal text\")", "sourceIds": [ - Network accessline 411
"role": "evidence", "pre": "<script> & <svg>\nhttps://example.com\nfetch(\"literal text\")", "sourceIds": [ - Network accessline 412
"pre": "<script> & <svg>\nhttps://example.com\nfetch(\"literal text\")", - Network accessline 412
"pre": "<script> & <svg>\nhttps://example.com\nfetch(\"literal text\")",
skills/ljg-present/SloganTemplate.html
- Network accessline 147
const chartSignal = palette.getPropertyValue("--hl").trim(); const svgNode = (tag, attrs = {}, text) => { const node = document.createElementNS("http://www.w3.org/2000/svg", tag); - Network accessline 147
const chartSignal = palette.getPropertyValue("--hl").trim(); const svgNode = (tag, attrs = {}, text) => { const node = document.createElementNS("http://www.w3.org/2000/svg", tag); - Network accessline 148
const svgNode = (tag, attrs = {}, text) => { const node = document.createElementNS("http://www.w3.org/2000/svg", tag); Object.entries(attrs).forEach(([name, value]) => node.setAttribute(name, String(value))); - Network accessline 148
const svgNode = (tag, attrs = {}, text) => { const node = document.createElementNS("http://www.w3.org/2000/svg", tag); Object.entries(attrs).forEach(([name, value]) => node.setAttribute(name, String(value))); - Network accessline 149
const node = document.createElementNS("http://www.w3.org/2000/svg", tag); - Network accessline 149
const node = document.createElementNS("http://www.w3.org/2000/svg", tag);
skills/ljg-present/Tools/BuildDeck.ts
skills/ljg-present/Tools/DeckData.ts
skills/ljg-present/Tools/EmbedAssets.ts
skills/ljg-present/Tools/ProbeDeck.js
skills/ljg-present/Tools/ValidateDeck.ts
- Executable scriptline 1
#!/usr/bin/env bun - Executable scriptline 1
#!/usr/bin/env bun - Possible obfuscationline 13
return (mime === "font/ttf" && (start === "\x00\x01\x00\x00" || start === "true")) - Possible obfuscationline 13
return (mime === "font/ttf" && (start === "\x00\x01\x00\x00" || start === "true")) - Dangerous shell operationline 97
const render = (chart: unknown): ChartFixtureNode => runInNewContext(`${source}\nrenderChart(input);`, { document, body, getComputedStyle, input: chart }, { timeout: 1000 }); - Dangerous shell operationline 97
const render = (chart: unknown): ChartFixtureNode => runInNewContext(`${source}\nrenderChart(input);`, { document, body, getComputedStyle, input: chart }, { timeout: 1000 }); - Network accessline 108
const mobile = byClass(line, "chart-data")[0]; const unsafeTitle = '<img src="missing.png"> & <script>'; const literalText = render({ kind: "compare", title: unsafeTitle, items: [{ label: "<svg>", text: "fetch('x')" }, { label: "B", - Network accessline 108
const mobile = byClass(line, "chart-data")[0]; const unsafeTitle = '<img src="missing.png"> & <script>'; const literalText = render({ kind: "compare", title: unsafeTitle, items: [{ label: "<svg>", text: "fetch('x')" }, { label: "B", - Network accessline 109
const unsafeTitle = '<img src="missing.png"> & <script>'; const literalText = render({ kind: "compare", title: unsafeTitle, items: [{ label: "<svg>", text: "fetch('x')" }, { label: "B", text: "https://example.com" }] }); const compa - Network accessline 109
const unsafeTitle = '<img src="missing.png"> & <script>'; const literalText = render({ kind: "compare", title: unsafeTitle, items: [{ label: "<svg>", text: "fetch('x')" }, { label: "B", text: "https://example.com" }] }); const compa - Network accessline 110
const literalText = render({ kind: "compare", title: unsafeTitle, items: [{ label: "<svg>", text: "fetch('x')" }, { label: "B", text: "https://example.com" }] }); - Network accessline 110
const literalText = render({ kind: "compare", title: unsafeTitle, items: [{ label: "<svg>", text: "fetch('x')" }, { label: "B", text: "https://example.com" }] }); - Network accessline 122
mobileDataKeepsCoordinates: mobile?.children.length === 3 && byClass(mobile, "chart-label").map((node) => node.textContent).join("|") === "A · 1|B · 2|C · 5", literalChartText: byClass(literalText, "chart-title")[0]?.textContent === u - Network accessline 122
mobileDataKeepsCoordinates: mobile?.children.length === 3 && byClass(mobile, "chart-label").map((node) => node.textContent).join("|") === "A · 1|B · 2|C · 5", literalChartText: byClass(literalText, "chart-title")[0]?.textContent === u - Network accessline 123
literalChartText: byClass(literalText, "chart-title")[0]?.textContent === unsafeTitle && all(literalText).every((node) => !["img", "script", "svg"].includes(node.tagName)), comparisonPreservesOrder: compare.length === 2 && text(compar - Network accessline 123
literalChartText: byClass(literalText, "chart-title")[0]?.textContent === unsafeTitle && all(literalText).every((node) => !["img", "script", "svg"].includes(node.tagName)), comparisonPreservesOrder: compare.length === 2 && text(compar - Network accessline 124
comparisonPreservesOrder: compare.length === 2 && text(compare[0]) === "<svg>fetch('x')" && text(compare[1]) === "Bhttps://example.com" - Network accessline 124
comparisonPreservesOrder: compare.length === 2 && text(compare[0]) === "<svg>fetch('x')" && text(compare[1]) === "Bhttps://example.com" - Network accessline 154
const template=await Bun.file(resolve(import.meta.dir,'../SloganTemplate.html')).text();const fixture=await Bun.file(resolve(import.meta.dir,'../References/CompositionDeck.json')).json(); const prepared=prepareDeck(fixture),html=materializ - Network accessline 154
const template=await Bun.file(resolve(import.meta.dir,'../SloganTemplate.html')).text();const fixture=await Bun.file(resolve(import.meta.dir,'../References/CompositionDeck.json')).json(); const prepared=prepareDeck(fixture),html=materializ - Network accessline 155
const prepared=prepareDeck(fixture),html=materialize(template,prepared);const checks=await validateHtml(html);const result:Record<string,boolean>={templatePass:checks.every(c=>c.pass)}; const mutations={bypass:html.replace('SLIDES.forEach( - Network accessline 155
const prepared=prepareDeck(fixture),html=materialize(template,prepared);const checks=await validateHtml(html);const result:Record<string,boolean>={templatePass:checks.every(c=>c.pass)}; const mutations={bypass:html.replace('SLIDES.forEach( - Network accessline 156
const mutations={bypass:html.replace('SLIDES.forEach((s,i)=>{','SLIDES.forEach((s,i)=>{ return;'),cssOverride:html.replace('</style>','.claim{font-size:8px}</style>'),extraScript:html.replace('</body>','<script>console.log(1)</script></body - Network accessline 156
const mutations={bypass:html.replace('SLIDES.forEach((s,i)=>{','SLIDES.forEach((s,i)=>{ return;'),cssOverride:html.replace('</style>','.claim{font-size:8px}</style>'),extraScript:html.replace('</body>','<script>console.log(1)</script></body - Dangerous shell operationline 167
const mathCode=template.slice(template.indexOf(' function escapeHtml('),template.indexOf('// BEGIN CHART RENDERER'));const renderMath=(text:string)=>runInNewContext(mathCode+'\nrenderMathAware(input)',{input:text},{timeout:1000}); - Dangerous shell operationline 167
const mathCode=template.slice(template.indexOf(' function escapeHtml('),template.indexOf('// BEGIN CHART RENDERER'));const renderMath=(text:string)=>runInNewContext(mathCode+'\nrenderMathAware(input)',{input:text},{timeout:1000});
skills/ljg-push/SKILL.md
skills/ljg-push/Tools/MdizeEmbeddedOrg.test.ts
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Network accessline 11
"", "* 昨天你在想什么", "- 链接：[[https://example.com][阅读]]", - Network accessline 11
"", "* 昨天你在想什么", "- 链接：[[https://example.com][阅读]]", - Network accessline 12
"* 昨天你在想什么", "- 链接：[[https://example.com][阅读]]", "```", - Network accessline 12
"* 昨天你在想什么", "- 链接：[[https://example.com][阅读]]", "```", - Network accessline 13
"- 链接：[[https://example.com][阅读]]", - Network accessline 13
"- 链接：[[https://example.com][阅读]]", - Network accessline 19
expect(converted).toContain("```markdown\n---\ntitle: 盲区扫描"); expect(converted).toContain("tags: blind weread\n---\n# 昨天你在想什么"); expect(converted).toContain("- 链接：[阅读](https://example.com)"); - Network accessline 19
expect(converted).toContain("```markdown\n---\ntitle: 盲区扫描"); expect(converted).toContain("tags: blind weread\n---\n# 昨天你在想什么"); expect(converted).toContain("- 链接：[阅读](https://example.com)"); - Network accessline 20
expect(converted).toContain("tags: blind weread\n---\n# 昨天你在想什么"); expect(converted).toContain("- 链接：[阅读](https://example.com)"); expect(converted).not.toContain("#+"); - Network accessline 20
expect(converted).toContain("tags: blind weread\n---\n# 昨天你在想什么"); expect(converted).toContain("- 链接：[阅读](https://example.com)"); expect(converted).not.toContain("#+"); - Network accessline 21
expect(converted).toContain("- 链接：[阅读](https://example.com)"); - Network accessline 21
expect(converted).toContain("- 链接：[阅读](https://example.com)");
skills/ljg-push/Tools/MdizeEmbeddedOrg.ts
skills/ljg-push/Tools/Push.sh
skills/ljg-push/Tools/Push.test.ts
skills/ljg-push/Workflows/Push.md
skills/ljg-qa/SKILL.md
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 1 fact
- Contacts creativecommons.org, which SKILL.md, the README and the plugin manifest do not mentionljg-business-model/Tools/Render.ts:109High confidence
Signal confidence: 213 facts
- Network access in prose of documentationljg-analogy/Theory.md:3Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valueskills/ljg-blind/SKILL.md:102Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valueljg-blind/SKILL.md:102Low confidence
- Network access in code of the SKILL.mdskills/ljg-blind/SKILL.md:107High confidence
- Network access in code of the SKILL.mdljg-blind/SKILL.md:107High confidence
- Access to secrets in code of the SKILL.mdskills/ljg-blind/SKILL.md:107High confidence
- Access to secrets in code of the SKILL.mdljg-blind/SKILL.md:107High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueskills/ljg-blind/SKILL.md:108Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueljg-blind/SKILL.md:108Low confidence
- Network access in code of the SKILL.mdskills/ljg-blind/SKILL.md:118High confidence
- Network access in code of the SKILL.mdljg-blind/SKILL.md:118High confidence
- Access to secrets in code of the SKILL.mdskills/ljg-blind/SKILL.md:118High confidence
- Access to secrets in code of the SKILL.mdljg-blind/SKILL.md:118High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueskills/ljg-blind/SKILL.md:119Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueljg-blind/SKILL.md:119Low confidence
- Network access in code of the SKILL.mdskills/ljg-blind/SKILL.md:137High confidence
- Network access in code of the SKILL.mdljg-blind/SKILL.md:137High confidence
- Network access in code of the SKILL.mdskills/ljg-blind/SKILL.md:172High confidence
- Network access in code of the SKILL.mdljg-blind/SKILL.md:172High confidence
- Network access in code of the SKILL.mdskills/ljg-blind/SKILL.md:173High confidence
- Network access in code of the SKILL.mdljg-blind/SKILL.md:173High confidence
- Network access in code of the SKILL.mdskills/ljg-blind/SKILL.md:174High confidence
- Network access in code of the SKILL.mdljg-blind/SKILL.md:174High confidence
- Network access in prose of the SKILL.mdskills/ljg-blind/SKILL.md:200Low confidence
- Network access in prose of the SKILL.mdljg-blind/SKILL.md:200Low confidence
- Network access in prose of the SKILL.mdskills/ljg-blind/SKILL.md:201Low confidence
- Network access in prose of the SKILL.mdljg-blind/SKILL.md:201Low confidence
- Network access in prose of the SKILL.mdskills/ljg-blind/SKILL.md:202Low confidence
- Network access in prose of the SKILL.mdljg-blind/SKILL.md:202Low confidence
- Network access in prose of the SKILL.mdskills/ljg-blind/SKILL.md:210Low confidence
- Network access in prose of the SKILL.mdljg-blind/SKILL.md:210Low confidence
- Network access in code of documentationskills/ljg-blind/Tools/WeReadWebUrl.help.md:25Low confidence
- Network access in code of documentationljg-blind/Tools/WeReadWebUrl.help.md:25Low confidence
- Executable script in code of a file that runsskills/ljg-blind/Tools/WeReadWebUrl.ts:1High confidence
- Executable script in code of a file that runsljg-blind/Tools/WeReadWebUrl.ts:1High confidence
- Network access in code of a file that runsskills/ljg-blind/Tools/WeReadWebUrl.ts:51High confidence
- Network access in code of a file that runsljg-blind/Tools/WeReadWebUrl.ts:51High confidence
- Executable script in code of a testskills/ljg-book/scripts/validate_note.test.ts:1Low confidence
- Executable script in code of a testljg-book/scripts/validate_note.test.ts:1Low confidence
- Executable script in code of a file that runsskills/ljg-book/scripts/validate_note.ts:1High confidence
- Executable script in code of a file that runsljg-book/scripts/validate_note.ts:1High confidence
- Network access in prose of documentationskills/ljg-business-model/CanvasGuide.md:37Low confidence
- Network access in prose of documentationljg-business-model/CanvasGuide.md:37Low confidence
- Network access in prose of documentationskills/ljg-business-model/CanvasGuide.md:38Low confidence
- Network access in prose of documentationljg-business-model/CanvasGuide.md:38Low confidence
- Network access in prose of documentationskills/ljg-business-model/CanvasGuide.md:39Low confidence
- Network access in prose of documentationljg-business-model/CanvasGuide.md:39Low confidence
- Network access in prose of documentationskills/ljg-business-model/CanvasGuide.md:41Low confidence
- Network access in prose of documentationljg-business-model/CanvasGuide.md:41Low confidence
- Executable script in code of a testskills/ljg-business-model/Tools/Render.test.ts:1Low confidence
and 163 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/ljg-analogy/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/ljg-analogy/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/ljg-analogy/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/ljg-analogy/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/ljg-analogy/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/lijigang-ljg-skills/)