Nlm Skill
iusztinpaul/ai-research-os-workshop
Expert guide for the NotebookLM CLI (nlm) and MCP server - interfaces for Google NotebookLM.
Turns a named classical Chinese chapter, such as one from the Tao Te Ching or the Analects, into a single annotated PNG image with notes and commentary.
SKILL.md written in Chinese; this summary is our English description.
Install Classical Chinese Text Annotator
$ npx skills add lijigang/ljg-skills --skill ljg-classic -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lijigang/ljg-skills ljg-classic --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/lijigang/ljg-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ljg-classic .claude/skills/ljg-classic && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ljg-classic" agent skill from https://github.com/lijigang/ljg-skills/tree/master/skills/ljg-classic into .claude/skills/ljg-classic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ljg-classic", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/lijigang/ljg-skills/tree/master/skills/ljg-classicType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add lijigang/ljg-skills --skill ljg-classic -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lijigang/ljg-skills ljg-classic --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lijigang/ljg-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ljg-classic .agents/skills/ljg-classic && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ljg-classic" agent skill from https://github.com/lijigang/ljg-skills/tree/master/skills/ljg-classic into .agents/skills/ljg-classic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ljg-classic", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lijigang/ljg-skills --skill ljg-classic -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lijigang/ljg-skills ljg-classic --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lijigang/ljg-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ljg-classic .cursor/skills/ljg-classic && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ljg-classic" agent skill from https://github.com/lijigang/ljg-skills/tree/master/skills/ljg-classic into .cursor/skills/ljg-classic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ljg-classic", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/lijigang/ljg-skills.git --path skills/ljg-classic--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add lijigang/ljg-skills --skill ljg-classic -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lijigang/ljg-skills ljg-classic --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lijigang/ljg-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ljg-classic .gemini/skills/ljg-classic && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ljg-classic" agent skill from https://github.com/lijigang/ljg-skills/tree/master/skills/ljg-classic into .gemini/skills/ljg-classic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ljg-classic", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install lijigang/ljg-skills ljg-classicInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add lijigang/ljg-skills --skill ljg-classic -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lijigang/ljg-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ljg-classic .github/skills/ljg-classic && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ljg-classic" agent skill from https://github.com/lijigang/ljg-skills/tree/master/skills/ljg-classic into .github/skills/ljg-classic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ljg-classic", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lijigang/ljg-skills --skill ljg-classic -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lijigang/ljg-skills ljg-classic --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lijigang/ljg-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ljg-classic .opencode/skills/ljg-classic && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ljg-classic" agent skill from https://github.com/lijigang/ljg-skills/tree/master/skills/ljg-classic into .opencode/skills/ljg-classic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ljg-classic", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ljg-classic- GitHub stars
- 7.5k
- Token cost
- ~551 tokens
- SKILL.md length
- 74 words
- Files
- 13 (incl. references)
- Skills in repo
- 26
- Repo updated
- First seen
- Licence
- MIT
At a glance
Turns a named classical Chinese chapter, such as one from the Tao Te Ching or the Analects, into a single annotated PNG image with notes and commentary.
- Creating a word-by-word annotated image for a classical Chinese chapter
- SKILL.md covers Workflow Notification, Workflow Routing, 快速合同 and Gotchas, plus 1 more section
- Runs TypeScript scripts from its folder
- Producing a study handout that mixes original text with sentence glosses
What it does
This skill takes a classical Chinese work and chapter, settles which edition to follow when the text has variants, and produces one long PNG that pairs the original passage with inline annotations rather than a plain translation. Word and phrase notes cover grammar and meaning, sentence notes explain what each clause is doing, and a closing chapter-level commentary works through one main relationship in plain Chinese, including where it does or does not carry over to other situations.
Work happens in an isolated temporary folder before anything is copied to the user's Downloads folder as a finished image, and the process checks file size, title and chapter labels, annotation coverage, and a cropped slice of the long image before calling a candidate done. An unlabeled illustration between the chapter title and the text is generated by default to summarize the chapter's theme without adding text or symbols, and the skill falls back to a text-only version when image generation is unavailable.
It is meant for annotating and laying out a full chapter, not for translating a single sentence, and it never rewrites the source text - textual variants get flagged rather than silently replaced.
When your agent uses it
- Creating a word-by-word annotated image for a classical Chinese chapter
- Producing a study handout that mixes original text with sentence glosses
- Generating a chapter commentary alongside the source passage
Example prompts
- “Annotate chapter 16 of the Tao Te Ching word by word with full commentary.”
- “Make a word-by-word glossed image from this Analects passage I'm pasting in.”
- “Turn this classical Chinese excerpt into a study card with sentence notes.”
Requirements
- Bun (for the TypeScript render and validate scripts)
What it can do on your machine
Read from SKILL.md and the folder at commit 9e75497. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (TypeScript), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Classical Chinese Text Annotator loads about 551 tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 44 tokens; SKILL.md has 74 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from lijigang/ljg-skills at commit 9e75497, republished under its MIT licence (© lijigang). 74 words, ~551 tokens.
Download SKILL.mdSave it as
.claude/skills/ljg-classic/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.- name
- ljg-classic
- description
- 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。
- user_invocable
- true
- version
- 1.1.2
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：
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。
Workflow Routing
| Workflow | Trigger | File |
|---|---|---|
| AnnotateAndRender | 逐字注解、彩色夹注、章节解读、生成古文 PNG | Workflows/AnnotateAndRender.md |
快速合同
- 输入必须能确定原文、书名、章节；版本不明时保留异文边界。
- 所有非标点原文片段都有对应注解，不能只挑“重点词”。
- 青色解释字词与语法，朱色解释整句动作，赭色只标异文与不确定处；章节解读使用暖纸深墨，不用蓝色长正文。
- 解读借用
ljg-explain的直白中文与理解标准和ljg-writes的「条件—机制—结果、迁移、边界」，产物仍遵守本工作流，不额外附加自测或写作脚手架。 - 默认调用内置
image_gen生成一幅无字、低干扰的章节意旨图，放在章节标题与原文之间；图像不可用时继续生成无图版本并说明。 - 每次运行先建立独占
/tmp/ljg-classic-*工作区；JSON、HTML、manifest、意旨图、候选 PNG 与重叠 QA 切片都只放在该工作区。 - 候选 PNG 完成硬验收后，才复制到
$HOME/Downloads/作为最终卡片；用户显式指定另一最终路径时以本次指令为准。未经明确要求不覆盖同名文件。
Gotchas
- “逐字”指原文覆盖率 100%，不等于把固定词拆成失去意义的单字；成词、虚词功能和通假关系按最小有意义单位注。
- 注解不能改写原文。底本疑似错字、通假或版本差异用
variant标出，不能静默替换。 - 字词注与句义注若都写成长句，原文会被淹没。字词注只解决局部读法，句义注只补当前动作或因果。
- 章节解读不是逐句译文的重复，也不是金句合集。它只运行一个主关系，并说明一个可迁移场景或失效边界。
- 边界要自然写进文章，不另起「解读边界」「应用边界」「迁移测试」之类的方法标题；这些词会让读者从内容中跳回写作后台。
- 顶部配图负责压缩母题，不负责复述情节。禁止图中文字、书法、印章、水印与高饱和宗教奇观；画面细节太满会抢走原文的第一阅读权。
- PNG 文件存在不算完成。必须核对真实尺寸、标题章节、注解覆盖、页面底部、整图与长图切片。
- 不直接渲染到 Downloads。先在
/tmp验收候选 PNG，再复制最终卡片，并读回候选与交付文件的 SHA-256 一致性。 - 图像宽度固定不代表字号固定。文字量增加时先增高页面和调整断行，不能把正文字号压到难读。
- 标点不能作为可独立换行的单元。句末标点与闭引号跟住前一原文 token；段首引号跟住后一 token，避免孤行。
Examples
Example 1：整章古文排版
User: 「/ljg-classic 《道德经》第十六章，逐字注解并讲透」
→ 锁定书名、章节与底本
→ 逐段生成字词注、句义注和全章解读
→ 在独占 `/tmp` 工作区完成验收，只把带书名章节的 1080px 长 PNG 交付到 `$HOME/Downloads/`Example 2：用户提供原文
User: 「把这段《论语·学而》做成文言文夹注图，最后写完整解读」
→ 原文逐片段覆盖，通假与语法另行标色
→ 解读用直白中文跑通条件、机制和结果
→ JSON、HTML、manifest、配图和 QA 切片保留在 `/tmp`；最终 PNG 交付到 `$HOME/Downloads/`Example 3：只翻译一句
User: 「这句古文是什么意思？」
→ 不触发 ljg-classic
→ 直接做简短翻译；需要讲透章内概念或原理时使用 ljg-explain© lijigang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 12 other files (references) in skills/ljg-classic of lijigang/ljg-skills.
- SKILL.md
- .gitignore
- References/AnnotationMethod.md
- References/InputSchema.md
- References/LayoutGrammar.md
- Tools/RenderClassic.help.md
- Tools/RenderClassic.test.ts
- Tools/RenderClassic.ts
- Tools/ValidateClassic.help.md
- Tools/ValidateClassic.ts
- Workflows/AnnotateAndRender.md
- bun.lock
- package.json
Open the folder on GitHubat commit 9e75497
Compare with similar skills
Classical Chinese Text Annotator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Classical Chinese Text Annotator this skilllijigang/ljg-skills | 7.5k | — | ~551 | Automated safety check: Pass | MIT | |
| Nlm Skilliusztinpaul/ai-research-os-workshop | 179 | 1 repos | ~6.9k | Automated safety check: Pass | MIT | |
| LearnHughYau/AcademicForge | 2.6k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | |
| Content RepurposerOneWave-AI/claude-skills | 336 | 1 repos | ~395 | Automated safety check: Pass | MIT | |
| Notebooklmalirezarezvani/claude-skills | 28k | — | ~4k | Automated safety check: Pass | MIT | |
| Notebooklm CLIItamarZand88/CLI-Anything-WEB | 231 | — | ~997 | Automated safety check: Pass | MIT |
Similar skills
Learn
HughYau/AcademicForge
A skill your agent uses when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's judgment.
Content Repurposer
OneWave-AI/claude-skills
Master skill that transforms ANY content into 8+ formats: slides, infographic, video script, podcast, social posts, email series, flashcards, quiz, one-pager, interactive game.
Notebooklm
alirezarezvani/claude-skills
Browser automation skill for controlling Google's NotebookLM.
Notebooklm CLI
ItamarZand88/CLI-Anything-WEB
Drives Google NotebookLM via the cli-web-notebooklm command-line tool — create and manage notebooks, add URL/text sources, ask questions grounded in the sources, and generate/download artifacts…
Cet Skill
mingchen666/Reviva
CET-4 and CET-6 exam preparation coach for original CET-style practice, diagnostic feedback, writing and translation correction, reading/listening drills, and study planning.
More from lijigang/ljg-skills
All 26 skills in this repoWhole-Book Explainer Notes
lijigang/ljg-skills
Explains a whole book to someone who has not read it, keeping its specific content and showing how its threads connect, and saves the result as an Org note.
Ljg Paper
lijigang/ljg-skills
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.
Text to PNG Card Caster
lijigang/ljg-skills
Turns text, URLs or local files into tall PNG cards through HTML typography, with four modes: long reading card, full-text layout, comic and whiteboard.
Constraint Engine
lijigang/ljg-skills
Finds the handful of constraints that truly define a domain, role, product or debate, grades each by hardness, and explains the behavior those constraints produce.
Offline HTML Talk Decks
lijigang/ljg-skills
Builds single-file offline HTML talk decks from Org or Markdown outlines, with faithful layout or editorial condensing and keyboard navigation.
ljg-qa Question Chain Extractor
lijigang/ljg-skills
Turns an article, paper or book into a directed chain of sharp questions and four-part answers that retraces the author's reasoning, saved as an org-mode note.
Related
Categories
Questions about Classical Chinese Text Annotator
What does Classical Chinese Text Annotator do?
Turns a named classical Chinese chapter, such as one from the Tao Te Ching or the Analects, into a single annotated PNG image with notes and commentary. This skill takes a classical Chinese work and chapter, settles which edition to follow when the text has variants, and produces one long PNG that pairs the original passage with inline annotations rather than a plain translation. Word and phrase notes cover grammar and meaning, sentence notes explain what each clause is doing, and a closing chapter-level commentary works through one main relationship in plain Chinese, including where it does or does not carry over to other situations.
When should I use Classical Chinese Text Annotator?
Classical Chinese Text Annotator fits situations like: creating a word-by-word annotated image for a classical Chinese chapter; producing a study handout that mixes original text with sentence glosses; generating a chapter commentary alongside the source passage.
How do I install Classical Chinese Text Annotator in Claude Code?
Run `npx skills add lijigang/ljg-skills --skill ljg-classic -a claude-code`. Or copy the skill folder (skills/ljg-classic in lijigang/ljg-skills) into .claude/skills/ljg-classic in your project. Claude Code loads it when a task matches its description.
How do I install Classical Chinese Text Annotator in Codex?
Run `npx skills add lijigang/ljg-skills --skill ljg-classic -a codex`. Or copy the skill folder (skills/ljg-classic in lijigang/ljg-skills) into .agents/skills/ljg-classic in your project. Codex loads it when a task matches its description.
Can I use Classical Chinese Text Annotator in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lijigang/ljg-skills --skill ljg-classic -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ljg-classic, .gemini/skills/ljg-classic, .github/skills/ljg-classic and .opencode/skills/ljg-classic in your project.
What does Classical Chinese Text Annotator need to run?
Going by SKILL.md and its folder, Classical Chinese Text Annotator needs TypeScript for the scripts in its folder. Our summary lists: Bun (for the TypeScript render and validate scripts).
Does Classical Chinese Text Annotator access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Classical Chinese Text Annotator safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Classical Chinese Text Annotator use?
Classical Chinese Text Annotator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Classical Chinese Text Annotator use?
About 551 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.3k tokens, read only when the agent opens those files.
What are the alternatives to Classical Chinese Text Annotator?
Skills that share tags, products or a category with Classical Chinese Text Annotator: Nlm Skill (iusztinpaul/ai-research-os-workshop, 179 stars), Learn (HughYau/AcademicForge, 2.6k stars), Content Repurposer (OneWave-AI/claude-skills, 336 stars) and Notebooklm (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Classical Chinese Text Annotator?
lijigang (a GitHub user) maintains it in lijigang/ljg-skills, which has 7,481 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 8, 2026.
Source: lijigang/ljg-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.