laohan-notebooklm skillB
laohan-notebooklm is agent-read markdown (skill) from hanzhcn/laohan-skills: 口播稿一键生成幻灯片图片，通过 NotebookLM 生成中文幻灯片，PDF 转图片输出供剪映使用。Use when 用户说"生成PPT""生成幻灯片""做PPT图片""幻灯片""PPT"或提到口播稿背景图/视觉素材。.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# 口播稿幻灯片生成 > **定位（2026-09-20治理P2-20）**：研究辅助工具，非生产链路；生产视频的画面资产走本地素材库/网络素材合同（⑩）或动画实现（⑪），不走本工具。 把口播稿一键生成幻灯片图片，输出到 script.md 同级目录的 slides/ 子目录，剪映直接用。 ## 核心理念 不加提示词、不加布局要求——NotebookLM 自由发挥效果最好。输出是半成品图片，布局和排版在剪映里调整，不在这里浪费时间。 ## 不适用场景 - 想要精确控制每页内容和排版 → NotebookLM 不支持，用 python-pptx 手动生成 PPT - 生成英文幻灯片 → 改 `--language en-US`，但本 skill 默认中文场景 - 没有 nlm CLI 或网络无法访问 NotebookLM → 先装依赖、解决网络问题 ## 使用 ``` /laohan-notebooklm <script.md路径> ``` ## 流程 每步可能 SSL 超时，加重试（最多3次，间隔3秒）。 ### 0. 准备 - 从 script.md 路径确定输出目录：script.md 所在目录下的 `slides/` 子目录 - `SCRIPT_DIR=$(dirname "$SCRIPT")`，`OUTPUT="$SCRIPT_DIR/slides"` - `mkdir -p "$OUTPUT"` - `cp "$SCRIPT" "$OUTPUT/script.md"` - 确认网络可访问 NotebookLM（REGION_NOT_SUPPORTED 时需切换网络环境） ### 1. 创建笔记本 ```bash nlm notebook create "<标题>PPT" ``` 记录返回的 NOTEBOOK_ID。 ### 2. 上传素材 ```bash nlm source add NOTEBOOK_ID --file "$OUTPUT/script.md" ``` 只上传口播稿原文，不加任何提示词或引导注释。 ### 3. 触发生成 ```bash echo "y" | nlm slides create NOTEBOOK_ID --language zh-CN --length default ``` `--language zh-CN` 是关键，漏了生成英文版。 ### 4. 轮询+下载+转图片（后台脚本） 必须用一个后台脚本一次性完成轮询、下载、转图片。用 `Bash` 工具的 `run_in_background: true` 执行： ```bash NB="NOTEBOOK_ID" TITLE="<标题>" OUTPUT="<script.md所在目录>/slides" …
Read the whole file at its exact version.
How to install
mdr add hanzhcn/laohan-skills/laohan-notebooklm@v1.2.0mdr add hanzhcn/laohan-skills/laohan-notebooklm@sha256:6475bcede4d37ba9Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_i7a2bxn66boc4jct)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.2.0 latest | 2026-09-20 | 18d6cbd | 3,266 B | B | view · diff |
| v1.2.0 | 2026-05-28 | 4b2e974 | 3,065 B | B | view · diff |
| git:20260523.02ac604 | 2026-05-23 | 02ac604 | 3,048 B | B | view · diff |
| v1 | 2026-05-22 | fa0389f | 2,997 B | B | view · diff |
| git:20260522.ee29bcc | 2026-05-22 | ee29bcc | 2,984 B | B | view |
Audit of the latest version
- fail: No script tag (matched: <script)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3266 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
Source
hanzhcn/laohan-skills · 11 stars · license MIT · pushed 2026-09-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_i7a2bxn66boc4jct GET https://markdownregistry.com/api/v1/resolve?ref=hanzhcn/laohan-skills/laohan-notebooklm GET https://markdownregistry.com/api/v1/blob/6475bcede4d37ba984f024415a841955de257ef124ed66f958b8dd043a627183
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.