Agent skill

Nlm

Manages Google NotebookLM notebooks via the nlm CLI. An agent skill from tmc/nlm.

MITAuto-check: notesKnowledge Management

Install Nlm

skills CLI

$ npx skills add tmc/nlm --skill nlm -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install tmc/nlm nlm --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/tmc/nlm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/nlm .claude/skills/nlm && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "nlm" agent skill from https://github.com/tmc/nlm/tree/main/skills/nlm into .claude/skills/nlm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nlm", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/tmc/nlm/tree/main/skills/nlm

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add tmc/nlm --skill nlm -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install tmc/nlm nlm --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/tmc/nlm.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/nlm .agents/skills/nlm && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "nlm" agent skill from https://github.com/tmc/nlm/tree/main/skills/nlm into .agents/skills/nlm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nlm", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add tmc/nlm --skill nlm -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install tmc/nlm nlm --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/tmc/nlm.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/nlm .cursor/skills/nlm && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "nlm" agent skill from https://github.com/tmc/nlm/tree/main/skills/nlm into .cursor/skills/nlm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nlm", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/tmc/nlm.git --path skills/nlm

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add tmc/nlm --skill nlm -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install tmc/nlm nlm --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/tmc/nlm.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/nlm .gemini/skills/nlm && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "nlm" agent skill from https://github.com/tmc/nlm/tree/main/skills/nlm into .gemini/skills/nlm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nlm", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install tmc/nlm nlm

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add tmc/nlm --skill nlm -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/tmc/nlm.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/nlm .github/skills/nlm && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "nlm" agent skill from https://github.com/tmc/nlm/tree/main/skills/nlm into .github/skills/nlm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nlm", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add tmc/nlm --skill nlm -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install tmc/nlm nlm --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/tmc/nlm.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/nlm .opencode/skills/nlm && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "nlm" agent skill from https://github.com/tmc/nlm/tree/main/skills/nlm into .opencode/skills/nlm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nlm", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: nlm
GitHub stars: 391
Token cost: ~2.2k tokens
SKILL.md length: 700 words
Files: 2
Skills in repo: 1
Repo updated: Sep 23, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Manages Google NotebookLM notebooks via the nlm CLI. An agent skill from tmc/nlm.

Creating notebooks
SKILL.md covers Command Discovery, Interpreting $ARGUMENTS, Critical Practices and Common Workflows, plus 2 more sections
Calls pdftotext
Listing and syncing sources

What it does

Nlm is an agent skill from tmc/nlm. Manages Google NotebookLM notebooks via the nlm CLI. Use for creating notebooks, listing and syncing sources, uploading files/URLs/text, chatting with sources, generating reports/audio/video/slides, running research, managing labels, editing notebook metadata (title/emoji/description/cover), and managing notebook content.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `reference/commands.md`).

It sits in Knowledge Management, covering Source-grounded notebooks and Slides and decks. It works with NotebookLM. The repository describes itself as: a command line interface to NotebookLM. The licence is MIT.

When your agent uses it

Creating notebooks
Listing and syncing sources
Uploading files/URLs/text
Chatting with sources

Example prompts

“Use the nlm skill to manage Google NotebookLM notebooks via the nlm CLI. An agent skill from tmc/nlm”
“/nlm”

Requirements

Pre-approved tools (allowed-tools): Bash(*), Read, Glob, Grep, Write

What it can do on your machine

Read from SKILL.md and the folder at commit 7a173b4. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
- Bash(*)
- Read
- Glob
- Grep
- Write
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- pdftotext
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nlm loads about 2.2k tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 700 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~82
When it runs · the whole SKILL.md, loaded when a task matches: ~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
```
allowed-tools: Bash(*), Read, Glob, Grep, Write
```

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from tmc/nlm at commit 7a173b4, republished under its MIT licence (© tmc). 700 words, ~2,173 tokens.

Download SKILL.mdSave it as .claude/skills/nlm/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: nlm
description: Manages Google NotebookLM notebooks via the nlm CLI. Use for creating notebooks, listing and syncing sources, uploading files/URLs/text, chatting with sources, generating reports/audio/video/slides, running research, managing labels, editing notebook metadata (title/emoji/description/cover), and managing notebook content.
allowed-tools: Bash(*), Read, Glob, Grep, Write
when_to_use: User mentions NotebookLM, nlm, notebook IDs, source upload/sync, chat with sources, report/audio/video/slides generation, research, labels/autolabel clusters…
argument-hint: [action] [args...]

nlm — NotebookLM CLI

Command Discovery

Run nlm --help for the canonical command tree. Run nlm <command> --help for command-local flags. The stable surface is noun-first: notebook, source, note, artifact, and chat groups.

For a compact command map, read reference/commands.md only when needed. Always prefer live help output when it disagrees with the reference.

Interpreting $ARGUMENTS

Argument	Action
(empty)	Run `nlm notebook list`, then ask what to do
`create` or `new`	Create a notebook with `nlm notebook create`
`upload` or `add`	Add one-off sources with `nlm source add`
`sync`	Sync a directory as a managed source with `nlm source sync`
`chat`	Start, resume, or run one-shot chat
`research`	Run `nlm research` and choose fast/deep mode if needed
`audio` / `video` / `slides` / `report`	Use the corresponding create or generation command
`status`	Show notebook, sources, artifacts, and recent chats
a notebook ID	Show details for that notebook
a file path or glob	Upload that file/pattern to a notebook

Critical Practices

Surface full UUIDs for notebooks, sources, conversations, notes, and artifacts in responses. Follow-up commands need them.
Use -y for destructive operations in non-interactive contexts, for example nlm -y notebook delete <id>.
Use nlm auth --authuser N or NLM_AUTHUSER=N for non-default Google accounts.
Use --direct-rpc for audio download; if the direct fetch is unavailable, it prints the NotebookLM browser URL. video download enables the required direct-RPC path itself and uses the same browser fallback.
Prefer canonical grouped commands in all new guidance.

Common Workflows

List notebooks

bash

nlm notebook list
nlm notebook list --limit 25
nlm notebook list --all

Add one-off sources — use source add for files, URLs, and direct text. Pass - to read newline-delimited source references from stdin.

bash

nlm source add <notebook-id> https://example.com/article
nlm source add <notebook-id> ./paper.pdf
nlm source add --name "API notes" <notebook-id> ./notes.txt
printf '%s\n' ./a.pdf https://example.com/b | nlm source add <notebook-id> -

Sync a directory as one source — source sync packs files into txtar, quotes nested txtar markers, chunks large payloads, and skips unchanged chunks using a content-hash cache. Use it whenever the same tree will be re-uploaded. Use source add for one-shot single-file/URL uploads.

bash

nlm source sync <notebook-id> src/
nlm source sync --name "project: src/" <notebook-id> src/
nlm source sync --dry-run <notebook-id> .
nlm source sync --force <notebook-id> ./docs ./notes
nlm source sync --json <notebook-id> .

Preview what sync will upload — source pack writes the exact txtar bytes sync would upload, no network. Pipe through txtar --list or txtar -x to inspect:

bash

nlm source pack src/ | txtar --list
nlm source pack src/ > preview.txtar
nlm source pack --chunk 2 src/ > pt2.txtar

Focus on specific sources — --source-ids and --source-match scope chat, generate-chat, generate-report, source-guide, and content transforms. --source-match is a Go regex matched against titles and UUIDs.

bash

nlm chat --source-match 'internal/sync' <notebook-id> "What changed?"
nlm generate-chat --source-ids a,b,c <notebook-id> "Summarize these"
nlm summarize --source-match '^spec/' <notebook-id>
nlm source list <notebook-id> | grep Q3 | nlm chat --source-ids - <notebook-id> "Risks?"

Chat and continuation

bash

nlm chat <notebook-id>
nlm chat <notebook-id> "What are the main conclusions?"
nlm generate-chat --conversation <conversation-id> <notebook-id> "Follow up"
nlm chat show --citations tail <notebook-id> <conversation-id>

Research

bash

nlm research <notebook-id> "What changed in the source set?"
nlm research --mode fast <notebook-id> "Which docs should I read first?"
nlm research --md <notebook-id> "Write a concise brief" > report.md
nlm research --import <notebook-id> "Find source material"

Content creation — creation may take time. Poll with artifact list, audio list, or video list.

bash

nlm create-audio <notebook-id> "Conversational, focus on key decisions"
nlm create-video <notebook-id> "Whiteboard walkthrough"
nlm create-slides <notebook-id> "Presentation summary"
nlm generate-report --sections 3 <notebook-id>
nlm artifact list <notebook-id>
nlm --direct-rpc audio download <notebook-id> output.wav
nlm --direct-rpc video download <notebook-id> output.mp4

Rename after stdin upload — stdin text defaults to "Pasted Text"; use --name during upload or rename after:

bash

nlm source rename <source-id> "descriptive name"

Notebook metadata — title, emoji, description, and cover are separate commands. cover takes a built-in preset ID; cover-image uploads a custom image. unrecent only hides from the recents list, it does not delete.

Show full SKILL.md (277 more words)Show less

bash

nlm notebook rename <notebook-id> "New Title"
nlm notebook emoji <notebook-id> "📓"
nlm notebook description <notebook-id> "One-line summary"
echo "long description" | nlm notebook description <notebook-id>
nlm notebook cover <notebook-id> 4
nlm notebook cover-image <notebook-id> ./cover.png
nlm notebook unrecent <notebook-id>

Labels (autolabel clusters) — labels are server-side clusters over sources. generate and relabel-all are heavy server jobs (relabel-all can exceed the 60s deadline on large notebooks); unlabeled only touches sources without a label. attach takes one source per call.

bash

nlm label list <notebook-id>
nlm label generate <notebook-id>
nlm label create <notebook-id> "Important" "⭐"
nlm label rename <notebook-id> <label-id> "New Name"
nlm label emoji <notebook-id> <label-id> "🐛"
nlm label delete <notebook-id> <label-id> [<label-id>...]
nlm label unlabeled <notebook-id>
nlm label relabel-all <notebook-id>
nlm label attach <notebook-id> <label-id|name> <source-id|name>

Discover sources vs chat — discover-sources calls a server-driven source-discovery RPC (Es3dTe) that returns ranked source IDs for a query. If the server rejects it (error or transient code-13), the CLI falls back to a regular chat call asking the model to list relevant sources. Use it to pick --source-ids for a follow-up; use nlm chat when you want a narrative answer rather than just IDs.

bash

nlm discover-sources <notebook-id> "Q3 revenue assumptions"

Source Freshness Strategy

Pick the lightest tool that does the job:

nlm source check <source-id> [notebook-id] — Drive-only. Asks Google whether the indexed copy is still current. No re-index, no upload. Use to decide whether anything else is needed.
nlm source refresh <notebook-id> <source-id> — Drive-only. Re-indexes the existing source in place. Use when check reports stale and the source is still a Google Drive document.
Re-upload — for non-Drive sources (files, URLs, pasted text) check and refresh do not apply. Use nlm source delete then nlm source add, or for a synced tree run nlm source sync (it auto-detects changed chunks; --force to re-upload unchanged content).

Binary upload workarounds — if a binary upload fails, convert to text:

bash

pdftotext paper.pdf - | nlm source add --name "paper text" <notebook-id> -
plutil -convert xml1 -o - file.plist | nlm source add --name "plist text" <notebook-id> -

Error Recovery

Error	Fix
"Authentication required"	Run `nlm auth`
"Service unavailable" on upload	Retry after a few seconds (rate limit)
"source limit reached" or "Failed precondition" on add	Remove unused sources or use a smaller target notebook
"upload init failed (status 500)"	Try text extraction workaround
`--source-match matched no sources`	Re-run `nlm source list <notebook-id>` and adjust the regex

Files

SKILL.md and 1 other file in skills/nlm of tmc/nlm.

SKILL.md
reference/commands.md

Open the folder on GitHubat commit 7a173b4

Compare with similar skills

Nlm next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Nlm compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Nlm this skilltmc/nlm	391	—	~2.2k	Automated safety check: Notes	MIT	14 days ago
Notebooklmrobonuggets/notebooklm-skill	139	—	~2.5k	Automated safety check: Pass	None	6 mo ago
Notebooklm Slide StylesYamilAyma/notebooklm-prompt-styles	104	—	~744	Automated safety check: Pass	None	5 mo ago
Notebooklm CLIItamarZand88/CLI-Anything-WEB	231	—	~1.4k	Automated safety check: Pass	MIT	6 days ago
Nlm Skilliusztinpaul/ai-research-os-workshop	179	1 repos	~6.9k	Automated safety check: Pass	MIT	3 mo ago
Notebooklmalirezarezvani/claude-skills	28k	—	~4k	Automated safety check: Pass	MIT	1 mo ago

Similar skills

Notebooklm
robonuggets/notebooklm-skill
Query, manage, and automate Google NotebookLM from your AI agent.
139 GitHub stars~2.5k tokensUpdated 6 mo ago
Knowledge ManagementAuto-check passed
Notebooklm Slide Styles
YamilAyma/notebooklm-prompt-styles
Translates visual identity and design documents into standardized YAML for NotebookLM slide generation.
104 GitHub stars~744 tokensUpdated 5 mo ago
Knowledge ManagementAuto-check passed
Notebooklm CLI
ItamarZand88/CLI-Anything-WEB
Use cli-web-notebooklm to interact with Google NotebookLM — create notebooks, add sources, ask questions, generate artifacts (audio, video, slides, mindmap, study guide, quiz, briefing, infographic…
231 GitHub stars~1.4k tokensUpdated 6 days ago
Knowledge ManagementAuto-check passed
Nlm Skill
iusztinpaul/ai-research-os-workshop
Expert guide for the NotebookLM CLI (nlm) and MCP server - interfaces for Google NotebookLM.
179 GitHub starsUsed in 1 repo~6.9k tokens
Knowledge ManagementAuto-check passed
Notebooklm
alirezarezvani/claude-skills
Browser automation skill for controlling Google's NotebookLM.
28k GitHub stars~4k tokensUpdated 1 mo ago
Knowledge ManagementAuto-check passed
Notebooklm CLI
ItamarZand88/CLI-Anything-WEB
Drives Google NotebookLM via the cli-web-notebooklm command-line tool — create and manage notebooks, add URL/text sources, ask questions grounded in the sources, and generate/download artifacts…
231 GitHub stars~997 tokensUpdated 6 days ago
Knowledge ManagementAuto-check passed

Works with

NotebookLM

Questions about Nlm

What does Nlm do?

Manages Google NotebookLM notebooks via the nlm CLI. An agent skill from tmc/nlm. Nlm is an agent skill from tmc/nlm. Manages Google NotebookLM notebooks via the nlm CLI.

When should I use Nlm?

Nlm fits situations like: creating notebooks; listing and syncing sources; uploading files/URLs/text; chatting with sources.

How do I install Nlm in Claude Code?

Run `npx skills add tmc/nlm --skill nlm -a claude-code`. Or copy the skill folder (skills/nlm in tmc/nlm) into .claude/skills/nlm in your project. Claude Code loads it when a task matches its description.

How do I install Nlm in Codex?

Run `npx skills add tmc/nlm --skill nlm -a codex`. Or copy the skill folder (skills/nlm in tmc/nlm) into .agents/skills/nlm in your project. Codex loads it when a task matches its description.

Can I use Nlm in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tmc/nlm --skill nlm -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nlm, .gemini/skills/nlm, .github/skills/nlm and .opencode/skills/nlm in your project.

What does Nlm need to run?

Going by SKILL.md and its folder, Nlm needs the command-line tools its instructions call (pdftotext). Its frontmatter pre-approves these tools: Bash(*), Read, Glob, Grep, Write.

Does Nlm access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Nlm safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Nlm use?

Nlm is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Nlm use?

About 2.2k tokens (SKILL.md is roughly 8.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Nlm?

Skills that share tags, products or a category with Nlm: Notebooklm (robonuggets/notebooklm-skill, 139 stars), Notebooklm Slide Styles (YamilAyma/notebooklm-prompt-styles, 104 stars), Notebooklm CLI (ItamarZand88/CLI-Anything-WEB, 231 stars) and Nlm Skill (iusztinpaul/ai-research-os-workshop, 179 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nlm?

tmc (a GitHub user) maintains it in tmc/nlm, which has 391 GitHub stars. The repository was last updated on September 23, 2026.

Source: tmc/nlm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Nlm

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

nlm — NotebookLM CLI

Command Discovery

Interpreting $ARGUMENTS

Critical Practices

Common Workflows

Source Freshness Strategy

Error Recovery

Files

Compare with similar skills

Similar skills

Notebooklm

Notebooklm Slide Styles

Notebooklm CLI

Nlm Skill

Notebooklm

Notebooklm CLI

Related

Questions about Nlm