tim-hub/notebook-lm
personal/skills/notebook-lm/SKILL.md
Creates NotebookLM YAML and structured slide content from project docs. Use when converting documentation into NotebookLM or slide format.
$ install --global
skillsauthnpx skillsauth add tim-hub/powerball notebook-lmInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 19, 2026, 6:08 AM171.3s3 files scanned
SKILL.md
- name:
- notebook-lm
- description:
- Creates NotebookLM YAML and structured slide content from project docs. Use when converting documentation into NotebookLM or slide format.
- when_to_use:
- NotebookLM, create YAML, structured slides, convert docs, notebook format
- allowed-tools:
- ["Read", "Write", "Edit"]
- argument-hint:
- [yaml|slides]
NotebookLM Skill
Generates NotebookLM YAML and structured slide content from project documents.
Quick Reference
| User Input | Subcommand | Behavior |
|------------|------------|----------|
| notebook-lm yaml or "Convert docs to NotebookLM" | yaml | Generates NotebookLM YAML (see references/notebooklm-yaml.md) |
| notebook-lm slides or "Create slide content" | slides | Generates structured slide YAML (see references/notebooklm-slides.md) |
Feature Details
| Feature | Details | |---------|--------| | NotebookLM YAML | See references/notebooklm-yaml.md | | Slide YAML | See references/notebooklm-slides.md |
Execution Steps
- Classify the user's request
- Read the appropriate reference file from "Feature Details" above
- Generate according to its contents
PDF Page Range Reading (Claude Code 2.1.49+)
A feature for efficiently handling large PDFs.
Reading with Page Range Specification
// Read with page range specification
Read({ file_path: "docs/spec.pdf", pages: "1-10" })
// Check table of contents only
Read({ file_path: "docs/manual.pdf", pages: "1-3" })
// Specific sections only
Read({ file_path: "docs/api-reference.pdf", pages: "25-45" })
Recommended Approaches by Use Case
| Case | Recommended Reading Method | Reason | |------|---------------------------|--------| | PDFs over 100 pages | Table of contents (1-3) → relevant chapters only | Minimize token consumption | | Specification review | Range specification per section | Read only the necessary parts in detail | | API documentation | Start from endpoint list (table of contents) | Understand overall structure before diving into details | | Academic papers | Abstract + conclusion → body | Grasp key points first | | Technical manuals | Table of contents + troubleshooting chapter | Prioritize practical sections |
Usage Example for NotebookLM YAML Generation
When generating YAML from a large PDF (300-page technical specification):
1. **Read the table of contents** (pages 1-5)
Read({ file_path: "spec.pdf", pages: "1-5" })
→ Understand the chapter structure
2. **Read the beginning of each chapter** (first 2 pages of each chapter)
Read({ file_path: "spec.pdf", pages: "10-11" }) // Chapter 1
Read({ file_path: "spec.pdf", pages: "45-46" }) // Chapter 2
→ Understand each chapter's overview
3. **Read important sections in detail**
Read({ file_path: "spec.pdf", pages: "78-95" }) // API Reference
→ Extract detailed content
This approach allows efficient YAML generation without reading all 300 pages.
Best Practices
| Principle | Description | |-----------|-------------| | Progressive loading | Read in order: table of contents → overview → details | | Relevant pages only | Specify only the pages needed for the task | | Token conservation | Reading all pages is a last resort | | Structure understanding first | Understand the big picture from the table of contents before diving into details |
Comparison with Conventional Methods
| Method | Token Consumption | Processing Time | Accuracy | |--------|------------------|-----------------|----------| | Full page loading (300 pages) | ~150,000 | Long | High | | Page range specification (30 needed pages) | ~15,000 | Short | High |
→ 90% token reduction and processing time improvement possible
Related Skills
tim-hub/choosing-k8s-release-strategy
testing
VerifiedTrustedCommunity
Picks the right Kubernetes Deployment update strategy (RollingUpdate / Recreate / Blue-Green / Canary) for the situation. Use when configuring a new Deployment, changing rollout config, or deciding how to ship a risky change.
2SKILL.mdUpdated May 25, 2026
tim-hub/translate-markdown
tools
VerifiedTrustedCommunity
Translates a markdown file to a target language, preserving structure. Use when the user needs a markdown file translated.
2SKILL.mdUpdated May 21, 2026
tim-hub/language-translate
development
VerifiedTrustedCommunity
Translates text between any two languages while preserving source format. Use when the user needs to translate plain text, code, or markdown content.
2SKILL.mdUpdated May 21, 2026
tim-hub/creative-writing
testing
VerifiedTrustedCommunity
Generates written content — blog posts, social posts, emails, and marketing copy — matched to the project's existing voice. Use when the user needs written material.
2SKILL.mdUpdated May 21, 2026