agentsclimarketplace

Cm notebooklm

Skill tody-agent/codymaster/skills/cm-notebooklm

Sync high-value dev knowledge (skills, decisions, lessons) into Google NotebookLM for cloud recall, podcasts, and flashcards. Pairs with Dockit/deep-search. Use for NotebookLM, nlm, knowledge base, skill sync, or cross-machine AI memory.From its SKILL.md

Install
npx -y skills add tody-agent/codymaster --skill cm-notebooklm

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

SKILL.md

5.0 KB, ~1.3k tokens by cl100k_base, as published. Nobody here has run it

Goal

Cloud brain / soul cho AI — lưu trữ kiến thức giá trị nhất, đồng bộ qua nhiều máy tính. brain.md = compiled source of truth, upload 1 lần thay vì 50.

How It Works

Skills + Lessons + Experiences
        ↓ compile
  ~/.codymaster/brain.md  (local file = backup)
        ↓ upload (1 API call)
  NotebookLM (cloud = cross-machine sync)

All automation via scripts/brain-sync.sh — AI chỉ cần gọi script.

Instructions

The Dual-Brain Architecture

CodyMaster uses a Dual-Brain approach to scale memory across multiple projects without context collapse:

  1. Master Brain (codymaster): Global brain storing Meta-Learnings, proven Architecture Decisions, and universal patterns. Evolved via the "Rule of 3" (knowledge graduation).
  2. Project Brain (Isolated): Optional local brain created per project to hold internal PRDs, APIs, and local code context from ./docs.
LevelGoalQuery Command
MasterTìm pattern chungnlm notebook query codymaster "..."
ProjectTìm context domainnlm notebook query $(cat .cm/notebook_id) "..."

🤖 AI Rule: Tự đưa quyết định khi hỏi: Hỏi codymaster cho các giải pháp mang tính hệ thống chung. Hỏi qua .cm/notebook_id cho các business logic đặc thù dự án đang làm.

Master Brain Setup (Global)

# 1. Install CLI
uv tool install notebooklm-mcp-cli

# 2. Setup Master Brain
bash ~/.gemini/antigravity/skills/cm-notebooklm/scripts/brain-sync.sh init

Project Brain Setup (Local - Optional)

Nếu dự án đủ lớn và nhiều doc:

# Tạo Project Brain riêng cho thư mục hiện tại
bash ~/.gemini/antigravity/skills/cm-notebooklm/scripts/brain-sync.sh init-project

Daily Usage

SCRIPT=~/.gemini/antigravity/skills/cm-notebooklm/scripts/brain-sync.sh

# Add a lesson learned
bash $SCRIPT lesson "Tên bài học"
# → Edit ~/.codymaster/lessons.md → fill in details

# Add coding experience
bash $SCRIPT experience "Tên pattern"
# → Edit ~/.codymaster/experiences.md → fill in details

# Sync to Master Brain (Thêm rule of 3)
bash $SCRIPT sync

# Sync to Project Brain (Up tài liệu local docs/)
bash $SCRIPT sync-project

# Check status
bash $SCRIPT status

# Query
nlm notebook query codymaster "your question"

Auto-Sync Triggers

AI detect và hỏi user (không tự động):

TriggerPrompt
Skill mới tạo"Sync skill mới vào brain?" → bash $SCRIPT sync
Bug fixed / post-mortem"Lưu bài học?" → bash $SCRIPT lesson "..."
Architecture changed"Update brain?" → bash $SCRIPT sync
User nói "sync/update"bash $SCRIPT sync

Cross-Machine (Máy Mới)

uv tool install notebooklm-mcp-cli
nlm login
nlm notebook list          # CodyMaster Brain already there
nlm alias set codymaster <id>
# Done! Query ngay: nlm notebook query codymaster "..."

Content Generation

nlm audio create codymaster --format deep_dive --confirm   # Podcast
nlm report create codymaster --format "Study Guide" --confirm
nlm flashcards create codymaster --difficulty medium --confirm
nlm studio status codymaster

What Gets Indexed

✅ HIGH-VALUE (auto-compiled into brain.md):
├── Skill Index (names + descriptions — NOT full SKILL.md)
├── Lessons Learned (~/.codymaster/lessons.md)
├── Coding Experiences (~/.codymaster/experiences.md)
└── AGENTS.md (project identity)

❌ NOT INDEXED (use qmd/cm-deep-search instead):
├── Full SKILL.md files (too many, hard to maintain)
├── Source code, tests, configs
└── Duplicated content

Memory Architecture

Session  → variables        → temporary
Working  → CONTINUITY.md    → ~500 words/turn
Local    → qmd              → BM25+vector, offline, stable
Cloud    → NotebookLM       → AI brain, cross-machine, podcast

Integration

SkillRole
cm-deep-searchLocal search complement (code)
cm-dockitGenerate docs → select high-value → feed to brain
cm-continuitySession memory, brain = long-term
skill-creator-ultraTRIGGER: new skill → prompt sync
cm-debuggingTRIGGER: bug fixed → prompt lesson

Constraints

  • 🔌 nlm CLI = third-party (jacob-bd). May break. Fallback: cm-deep-search.
  • 🧠 Selective only — quality > quantity. Don't dump everything.
  • 🔐 NO secrets in NotebookLM — cloud service.
  • ❌ NO delete without user confirmation.
  • 🤖 NO nlm chat start — use nlm notebook query only.
  • 🔄 Auto-sync = ask first, never silent upload.
<!-- Generated by Skill Creator Ultra v1.0 -->

What ships with it: 5 files

22.6 KB alongside SKILL.md, 2 of them executable

references/

resources/

scripts/

Gives 0 of the 12 instructions most memory context skills give in ~1.3k tokens

Counted across 754 of the 1,056 authors here whose files we hold, read 2026-09-06

  • Preserve existing content structurein 15 of 754, across 9 files
  • Front-load the leading wordin 14 of 754, across 10 files
  • Update existing entries instead of duplicatingin 14 of 754, across 7 files
  • Keep CLAUDE.md under one hundred linesin 14 of 754, across 12 files
  • Read CLAUDE.md at the project rootin 14 of 754
  • Keep each meaning in a single source of truthin 12 of 754, across 8 files
  • Redact sensitive information before committingin 11 of 754, across 4 files
  • Scan for all CLAUDE.md filesin 11 of 754, across 7 files
  • Use frontmatter for metadata on filesin 10 of 754, across 3 files
  • Repeat user interactions 10 timesin 10 of 754, across 4 files
  • Write the CLAUDE.md file into the target folderin 10 of 754, across 8 files
  • Use memlab to process snapshotsin 9 of 754, across 3 files

Said here and by no other author read

  • Ask user before syncing to brain
  • Query master brain for systemic solutions
  • Query project brain for domain context
  • Keep high-value knowledge selective
  • Use notebook query instead of chat start

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.