Motherduck Cli logo

Motherduck Cli

Organization
motherduckdb
motherduck-cli

Use the MotherDuck CLI for terminal queries, authentication, and file-based Dive or Flight workflows.

Overview

Publishermotherduckdb
Repositoryagent-skills
Skill namemotherduck-cli
Stars
62
Forks
6
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by motherduckdb on GitHub. Read the source before you install it.

Installation

Install the Motherduck Cli AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/motherduckdb/agent-skills/tree/main/plugins/motherduck-skills-claude/skills/motherduck-cli
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/motherduckdb/agent-skills.git /tmp/agent-skills
mkdir -p .claude/skills
cp -r /tmp/agent-skills/plugins/motherduck-skills-claude/skills/motherduck-cli .claude/skills/motherduck-cli
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Motherduck Cli in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Motherduck Cli on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Motherduck Cli is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Use the MotherDuck CLI

Source Of Truth

  • Prefer the current MotherDuck CLI documentation and command reference. Read command help before relying on remembered flags because the command surface can evolve.
  • Before authoring or editing a Dive or Flight, run motherduck dive guide or motherduck flight guide. Those built-in guides are the current runtime contract.
  • Use motherduck <command> --help after a parsing or option error instead of guessing at syntax.

Default Posture

  • Reuse an authenticated CLI when available; check with motherduck status before starting a login flow.
  • For automation, pass MOTHERDUCK_TOKEN through the environment and set an absolute, task-specific MOTHERDUCK_HOME so parallel agents do not share credentials or assets.
  • Request --output json for machine-readable resource operations and check both the exit code and returned success field. motherduck query --output json returns a bare JSON array instead.
  • Redirect large query results to a file rather than pulling every row into model context.
  • Never run motherduck new merely because authentication is missing. Account creation requires an explicit signup request.
  • Keep Guides as files with motherduck guide init|pull|push; push creates or updates and only adds a version when content changes. Record a Git SHA with --external-id and the reason with --version-description. pull overwrites local files, so push or save local edits first.
  • Treat dive push, flight push, guide push, scheduling, secret changes, and account creation as external mutations. Perform them only when the user's build/change request includes that outcome.

Workflow

  1. Inspect the host project and existing CLI/authentication state.
  2. Install or upgrade only when needed, following the current platform-specific docs.
  3. Choose CLI or MCP based on the task shape:
    • files, local edits, CI, large results, or repeated iterations: CLI
    • chat-only exploration, inline answers, or no filesystem: MCP
    • mixed workflow: explore through MCP, then build from local files through the CLI
  4. For queries, use motherduck query with the smallest suitable output format.
  5. For a Dive or Flight, read its built-in guide, pull or initialize the local project, edit files, validate or preview, then push only when publication is requested.
  6. Capture the resource ID, URL, or run number from JSON output and verify the remote state after mutation.

For answer, review, or planning requests, recommend commands without logging in, creating an account, or changing remote resources. For explicit build/change requests, complete the in-scope CLI workflow and validate its result; ask before destructive deletes or materially broader external changes.

References

Read only the reference sections needed for the current task.

  • Read references/CLI_PLAYBOOK.md for installation, authentication, JSON contracts, query patterns, agent isolation, and complete Dive/Flight file workflows.

Related Skills

Load related skills only for missing capabilities; reuse established context.

  • motherduck-connect for choosing the underlying application connection path
  • motherduck-explore and motherduck-query for catalog discovery and SQL behavior
  • motherduck-create-dive and motherduck-create-flight for the product-specific authoring workflow

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Motherduck Cli AI skill do?

Use the MotherDuck CLI for terminal queries, authentication, and file-based Dive or Flight workflows.

Why use Motherduck Cli on TypingMind?

Because you install it once and use it with any model. Motherduck Cli is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Motherduck Cli in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/motherduckdb/agent-skills/tree/main/plugins/motherduck-skills-claude/skills/motherduck-cli. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Motherduck Cli?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Motherduck Cli?

As many as you like. As long as a model supports skills, you can use Motherduck Cli with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Motherduck Cli AI skill free?

Yes. It is published on GitHub by motherduckdb under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇