Cds Docs logo

Cds Docs

Organization
coinbase
cds-docs

Retrieve Coinbase Design System (CDS) documentation: setup, installation, theming, tokens, and per-component APIs/examples. Use this skill whenever the task involves CDS components, design-system rules, theming, or choosing between web and mobile CDS packages, even if the user only says "use CDS" or names a component. Always start from the docs route index, then fetch only the pages you need to reason and implement correctly. Prefer the CDS MCP server (`list-cds-routes`, `get-cds-doc`); if MCP is unavailable, use curl against https://cds.coinbase.com/llms/....

Overview

Publishercoinbase
Repositorycds
Skill namecds-docs
Stars
505
Forks
107
Bundled files
1
LicenseApache-2.0
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Cds Docs 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.
  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/coinbase/cds.git /tmp/cds
mkdir -p .claude/skills
cp -r /tmp/cds/skills/cds-docs .claude/skills/cds-docs
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cds Docs 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 Cds Docs 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 Cds Docs 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.

CDS Documentation Skill

Goal: Pull CDS documentation into the session so your next edits, recommendations, and API usage are grounded in current docs—not to produce a documentation handout for the user.

Treat fetched pages as source material you have read: internalize props, patterns, imports, and setup constraints, then act (code, refactors, answers) from that understanding. Quote or summarize for the user only when it helps. Keep the actual doc page contents to yourself and only share their contents directly to the user if they ask.

Whether you use the CDS MCP server or fetch the pages yourself with curl is an implementation detail. The use does not need to know your methodology unless they indicated they are debugging this skill.

Ambiguous product requests (e.g. “turn this into tabs,” “make it a card”) after you’ve read the index: if several CDS components could be relevant (e.g. underline Tabs vs pill SegmentedTabs vs TabNavigation), it is acceptable and often better to ask one short, concrete question (e.g. which visual pattern matches their spec) while briefly naming the options and how they differ per the docs. Do not pick one arbitrarily just to avoid asking.

1. Choose platform

Decide whether the work targets web (React, @coinbase/cds-web) or mobile (React Native, @coinbase/cds-mobile). If unclear, infer from the repo (e.g. package.json dependencies, apps/* layout) or ask a single clarifying question.

Pass web or mobile to list-cds-routes and when building curl URLs.

2. Tool order (try in sequence)

  1. CDS MCP server (packaged mcp-docs in @coinbase/cds-mcp-server / packages/mcp-server):

    • list-cds-routes with platform: "web" | "mobile".
    • get-cds-doc with route: path including the platform, ending in .txt (e.g. web/getting-started/installation.txt). Paths must come from the index.
  2. curl if MCP is not configured, fails, or returns errors:

    • Index: https://cds.coinbase.com/llms/web/routes.txt or https://cds.coinbase.com/llms/mobile/routes.txt
    • Page: https://cds.coinbase.com/llms/<route> where <route> matches the index (e.g. web/getting-started/theming.txt).

    Use curl -fsSL '<url>'. Prefer targeted fetches (the pages you need for this task) over loading everything; the index is for routing, not for echoing back wholesale.

3. Workflow whenever this skill applies

  1. Resolve platform (web or mobile).
  2. Load the index once per platform focus (list-cds-routes or routes.txt) and use it as the canonical map of .txt paths.
  3. Fetch additional pages only as needed for the work ahead; after each fetch, apply what you learned (imports, props, patterns)—do not stop at regurgitating the file.

4. Practical notes

  • Routes are case-sensitive; doc content is .txt from MCP or HTTP.
  • Web and mobile docs differ; confirm the component or topic exists for that platform’s index.
  • Human-readable URLs inside the .txt files are optional to share with the user; your priority is correct implementation, not reproducing the doc site in the reply.

5. What “done” looks like

  • Platform is correct or explicitly chosen.
  • Index informed which pages you pulled.
  • User-facing output is implementation-focused (components, imports, structure); retrieval steps stay implicit unless the user needs them.
  • If multiple components fit, you either ground the choice in doc differences or ask one clarifying question when the product spec is under-specified.
  • Your actions and explanations reflect fetched CDS details (APIs, setup, tokens)—especially where memory would be risky—not a dump of documentation for its own sake.

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 Cds Docs AI skill do?

Retrieve Coinbase Design System (CDS) documentation: setup, installation, theming, tokens, and per-component APIs/examples. Use this skill whenever the task involves CDS components, design-system rules, theming, or choosing between web and mobile CDS packages, even if the user only says "use CDS" or names a component. Always start from the docs route index, then fetch only the pages you need to reason and implement correctly. Prefer the CDS MCP server (`list-cds-routes`, `get-cds-doc`); if MCP is unavailable, use curl against https://cds.coinbase.com/llms/....

Why use Cds Docs on TypingMind?

Because you install it once and use it with any model. Cds Docs 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 Cds Docs in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/coinbase/cds/tree/master/skills/cds-docs. 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 Cds Docs?

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 Cds Docs?

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

Is the Cds Docs AI skill free?

Yes. It is published on GitHub by coinbase under the Apache-2.0 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 👇