Composio logo

Composio

OrganizationPopular
ComposioHQ
composio

Route and complete Composio work across Composio For You and Composio Platform. Use when the user mentions Composio; wants an agent to use apps such as Gmail, Slack, GitHub, Notion, Calendar, or Linear; needs first-time setup, an SDK or MCP integration, CLI operation, migration guidance, current documentation, or help diagnosing a connection or tool call.

Overview

PublisherComposioHQ
Repositorycomposio
Skill namecomposio
Stars
30.4K
Forks
4.8K
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

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

Installation

Install the Composio 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/ComposioHQ/composio/tree/next/skills/composio
  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/ComposioHQ/composio.git /tmp/composio
mkdir -p .claude/skills
cp -r /tmp/composio/skills/composio .claude/skills/composio
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Composio 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 Composio 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 Composio 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.

Composio

Use this skill as a router. Identify the product and the job, load only the relevant guidance, consult canonical documentation for volatile details, and then answer or do the work the user requested.

1. Choose the product

Do not blend the products. They use different credentials and setup paths.

Composio For YouComposio Platform
Use whenSomeone wants their own agent to use their own appsA developer is building a product whose users connect accounts
Primary surfaceMCP or the Composio CLISDK sessions inside an application
Credentialck_... consumer key when the client requires a headerCOMPOSIO_API_KEY project key
Dashboarddashboard.composio.dev → For Youdashboard.composio.dev → Platform

Ask one short question only when context does not establish the product:

Is this for your own agent and accounts, or for a product where your users connect their accounts?

Treat a named personal AI client with no product code as For You. Treat an application codebase, SDK, user or tenant identity, backend, or product agent as Platform.

2. Choose the job

Identify the requested outcome before taking action:

  • Explain or discover: answer a question, compare approaches, or find the current API.
  • Set up: establish credentials, an MCP client, the CLI, or an SDK for the first time.
  • Build or change: integrate Composio into an existing agent or application.
  • Operate: find, connect, and run tools for a real task.
  • Debug or migrate: diagnose a failure, update an older integration, or move from legacy direct execution or Tool Router.

Do not turn an explanation, documentation lookup, or narrow bug fix into onboarding.

3. Load only the relevant guidance

Complete the selected job

  • For a question, fetch current documentation when needed and give the concrete answer. Do not mutate a project or force a tool call.
  • For setup or integration, inspect the existing environment, preserve its architecture and identity model, make the smallest useful change, and verify it with one safe real tool call when credentials and user authorization are available.
  • For an operational request, connect only the apps the task needs and execute the requested workflow.
  • For debugging, get the Composio log or request ID, identify the failing boundary, fix that boundary, and retry when the user authorized execution.

Stable rules

  1. Establish the product before choosing credentials, URLs, SDKs, or commands.
  2. Treat dashboard onboarding as a context, not the skill's identity. When the developer arrives with an existing COMPOSIO_API_KEY from Getting Started, use it and never create, rotate, replace, print, or request it in chat. Do not run composio dev init in that path.
  3. For a general first-time Platform setup with no dashboard credential handoff, follow the current setup path in the Platform guide.
  4. Never invent toolkit or tool slugs. Discover them at runtime or with the CLI.
  5. Do not build a provider OAuth flow. Composio returns a Connect Link when authentication is needed.
  6. Use sessions for new Platform integrations. Preserve the application's existing user identity and agent architecture.
  7. Keep credentials out of source control, URLs, logs, chat, and command output.
  8. Get the log or request ID before diagnosing a failed tool call.
  9. Prefer the smallest configuration that completes the current job. Keep toolkit filters, tag policies, sandbox controls, custom auth, provider-specific hardening, and other advanced options out of the first path unless the request or existing code requires them.
  10. Do not invent repository facts. Never claim that a file, framework, environment loader, identity field, agent path, or dependency exists until it was provided or inspected. If codebase context is unavailable, state the unknown and ask for access or one necessary detail.
  11. In SDK or API examples, use exact identifiers and call shapes from a current public page or schema. Copy the documented shape for the requested language instead of translating names between TypeScript and Python; if a required detail is not documented, explain the behavior without inventing code.

Canonical information

Use bundled references for stable decisions. A user-facing source list contains only public https://docs.composio.dev/... pages actually consulted; bundled reference names, local paths, and file:// URLs are omitted. For versions, provider adapters, client-specific setup, toolkit behavior, or APIs that may have changed, use the current canonical documentation and current CLI or tool schemas as the primary sources before answering or editing code:

When sources disagree, prefer the current API reference and live endpoint behavior over any page marked Legacy, and name the REST API version explicitly.

text
https://docs.composio.dev/llms.txt
https://docs.composio.dev/docs/<page>.md
https://docs.composio.dev/toolkits/<toolkit>.md

If those primary sources do not answer a Composio product or troubleshooting question, query the public unified knowledge search at https://docs.composio.dev/api/knowledge-search?q=<question>.

Results may be canonical docs, KB, toolkit, example, or reference pages. Use the returned evidence to answer the question; public records do not establish the live state of a user's account, project, connection, or tool call.

When knowledge search supplies evidence, cite the result's returned canonicalUrl, not the search API URL. If canonicalUrl is relative, prefix it with https://docs.composio.dev before citing it.

Only treat a result as evidence when its excerpt or page directly addresses the question. If no public source directly documents an exact error or symptom, say so instead of diagnosing from adjacent results; request the log or request ID, or the necessary live evidence.

Use the documentation to complete the task. Do not merely hand the user a link unless they asked for one.

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 Composio AI skill do?

Route and complete Composio work across Composio For You and Composio Platform. Use when the user mentions Composio; wants an agent to use apps such as Gmail, Slack, GitHub, Notion, Calendar, or Linear; needs first-time setup, an SDK or MCP integration, CLI operation, migration guidance, current documentation, or help diagnosing a connection or tool call.

Why use Composio on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ComposioHQ/composio/tree/next/skills/composio. 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 Composio?

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 Composio?

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

Is the Composio AI skill free?

Yes. It is published on GitHub by ComposioHQ 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 👇