Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hanzhcn/laohan-skills --skill laohan-notebooklmgit clone --depth 1 https://github.com/hanzhcn/laohan-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-notebooklm)<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-notebooklm"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-notebooklm/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-notebooklm"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-notebooklm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low MCP Rug Pull · line 109 pip install without ==version installs the latest release, which could include malicious changes.Fix: Pin the version: pip install package==1.2.3
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.00974 |
| Opus 5.5 | $0.00029 | $0.00390 |
| Sonnet 5.5 | $0.00015 | $0.00195 |
| Haiku 4.5 | $0.00007 | $0.00097 |
Grade A, and why
laohan-notebooklm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
口播稿幻灯片生成
定位(2026-09-20治理P2-20):研究辅助工具,非生产链路;生产视频的画面资产走本地素材库/网络素材合同(⑩)或动画实现(⑪),不走本工具。
把口播稿一键生成幻灯片图片,输出到 script.md 同级目录的 slides/ 子目录,剪映直接用。
核心理念
不加提示词、不加布局要求——NotebookLM 自由发挥效果最好。输出是半成品图片,布局和排版在剪映里调整,不在这里浪费时间。
不适用场景
- 想要精确控制每页内容和排版 → NotebookLM 不支持,用 python-pptx 手动生成 PPT
- 生成英文幻灯片 → 改
--language en-US,但本 skill 默认中文场景 - 没有 nlm CLI 或网络无法访问 NotebookLM → 先装依赖、解决网络问题
使用
/laohan-notebooklm <script.md路径>
流程
每步可能 SSL 超时,加重试(最多3次,间隔3秒)。
0. 准备
- 从 script.md 路径确定输出目录:script.md 所在目录下的
slides/子目录 SCRIPT_DIR=$(dirname "$SCRIPT"),OUTPUT="$SCRIPT_DIR/slides"mkdir -p "$OUTPUT"cp "$SCRIPT" "$OUTPUT/script.md"- 确认网络可访问 NotebookLM(REGION_NOT_SUPPORTED 时需切换网络环境)
1. 创建笔记本
nlm notebook create "<标题>PPT"
记录返回的 NOTEBOOK_ID。
2. 上传素材
nlm source add NOTEBOOK_ID --file "$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
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:
NB="NOTEBOOK_ID"
TITLE="<标题>"
OUTPUT="<script.md所在目录>/slides"
for i in $(seq 1 20); do
st=$(nlm studio status "$NB" 2>&1 | grep -o '"status": "[^"]*"' | head -1)
echo "[$i] $st"
echo "$st" | grep -q "completed" && break
sleep 30
done
for i in 1 2 3; do
nlm download slide-deck "$NB" -o "${OUTPUT}/${TITLE}.pdf" 2>&1 && break
sleep 5
done
pdftoppm -png -r 200 "${OUTPUT}/${TITLE}.pdf" "${OUTPUT}/slide"
echo "Done: $(ls "${OUTPUT}"/slide-*.png | wc -l | tr -d ' ') slides"
后台完成后读取输出确认图片数量,告知用户。
输出
<script.md所在目录>/slides/
├── script.md
├── <标题>.pdf
├── slide-01.png
├── slide-02.png
└── ...
关键原则
- 不加提示词:只上传口播稿原文,NotebookLM 自由发挥效果最好
- 不加布局要求:布局在剪映里调整
- 输出到 script.md 同级的 slides/ 目录,与其他素材统一管理
前置依赖
- nlm CLI v0.5.25(
pip install notebooklm-mcp-cli) - poppler(
brew install poppler)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +2 lines 6475bcede4d3
- 1mo ago First seen · 111 lines · 73 tokens per session scan A 1e00ea8f22f2
laohan-notebooklm is a skill published in the GitHub repository hanzhcn/laohan-skills (15 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 974 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
consulting-pdf-from-youtube
Generate polished Chinese consulting-style PDF reports from YouTube videos. Uses a transcription priority chain -- YouTube auto-subs first, Whisper fallback second (with quality gates and proper noun verification). Includes bot-detection bypass escalation when yt-dlp is blocked. Use when a user shares a YouTube link…
chinese-pdf-report
Create professional Chinese PDF reports with reliable font rendering on macOS, especially when previous HTML-to-PDF output produced garbled Chinese text, missing glyphs, or ugly default typography. Use when asked to generate or re-export Chinese-heavy PDFs, fix Chinese font issues, improve typography for formal…
youtube-bilingual-transcript-report
Download a YouTube video, build English and Chinese timestamped transcripts, create a structured summary with independent insights, and export a professional Chinese PDF report. Includes fallback when Chinese subtitle download hits HTTP 429 and when full-resolution video download is unnecessarily heavy.
chinese-video-transcribe-pdf
A workflow that turns Chinese-language videos, with or without subtitles, into structured text and a Chinese PDF report. It can use videos from sources such as YouTube or local MP4 files.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
academic-paper-to-chinese-insight-pdf
Turn an academic paper PDF into a high-quality Chinese insight report and export it as a polished Chinese PDF. Use when asked to read a paper, translate or summarize a paper into Chinese, extract the paper's core ideas, produce original insights/opinions, explain the paper in simpler language, or deliver a Chinese PDF…