Borrowing it
Nothing to install: this file belongs to Shashank2577/hesoyam-for-claude-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Shashank2577/hesoyam-for-claude-code/main/.claude/skills/notebooklm-sme/SKILL.mdgit clone --depth 1 https://github.com/Shashank2577/hesoyam-for-claude-codeWrote 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/shashank2577/hesoyam-for-claude-code/notebooklm-sme)<a href="https://agentmods.dev/skills/shashank2577/hesoyam-for-claude-code/notebooklm-sme"><img src="https://agentmods.dev/badge/skills/shashank2577/hesoyam-for-claude-code/notebooklm-sme/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/shashank2577/hesoyam-for-claude-code/notebooklm-sme"><img src="https://agentmods.dev/badge/skills/shashank2577/hesoyam-for-claude-code/notebooklm-sme.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00023 | $0.00751 |
| Opus 5 | $0.00012 | $0.00376 |
| Sonnet 5 | $0.00005 | $0.00150 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade B, and why
notebooklm-sme scanned grade B with 1 finding 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 11d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
3. Settings in `~/.claude/settings.json` — look for an MCP server with "notebooklm" in the name or command How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$VAULT_PATH defaults to ~/Documents/obsidian-vault. Override by setting VAULT_PATH in your environment or passing --vault-path during install.
You are a bridge between the user and their NotebookLM knowledge base. Follow this process exactly.
Step 0: Check availability
Before doing anything, silently check in order:
command -v notebooklm— notebooklm-py CLIpython -c "import notebooklm" 2>/dev/null— notebooklm-py Python package- Settings in
~/.claude/settings.json— look for an MCP server with "notebooklm" in the name or command
If none found, tell the user:
NotebookLM is not configured. To set it up:
- Install notebooklm-py:
pip install 'notebooklm-py[browser]'thennotebooklm login- Or configure a NotebookLM MCP server in your Claude Code settings
See: guides/notebooklm-workflows.md for full setup instructions.
Then stop. Do not proceed.
Step 1: Understand the question
Parse the invocation for a question (e.g., /ask-sme "What did we decide about auth?"). If no question was passed inline, ask:
- What do you want to know?
- Which notebook? (if multiple — default to most recently modified)
- Output format: answer only / sourced answer / artifact (mind-map, slides, audio)
Step 2: Query the notebook
For direct Q&A:
notebooklm ask "<question>"
Show the answer with source citations. If sources reference vault notes at $VAULT_PATH, show the file paths.
For deep-dive questions, run three focused queries:
notebooklm ask "<question> — focus on the decision or recommendation"
notebooklm ask "<question> — what are the tradeoffs or risks"
notebooklm ask "<question> — what alternatives were considered"
Synthesize into a structured answer with headings.
For artifact generation:
notebooklm generate <type> # mind-map | data-table | slide-deck | audio
notebooklm download <type> ./<filename>
Report the downloaded file path to the user.
Step 3: Optionally save to vault
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.
- 11d ago First seen · 81 lines · 23 tokens per session scan B e924f9c842b7
notebooklm-sme is a skill published in the GitHub repository Shashank2577/hesoyam-for-claude-code (11 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 751 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.