agentleFS
poorvith-mppoorvith-mp/skills-agents/skills/composio/SKILL.md

composio

Skill0 starsChanged 2 months agoMITView on GitHub

Wire agents to authenticated third-party SaaS tools through Composio connectors. Use when integrating AI agents with GitHub, Slack, Gmail, or Jira via Composio.

  • Reads credentials
  • Installs packages

32 other projects use a version of this, 8 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use albert-dm, new-client-system and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • yawningwhaleAISkill

    albert-dm

    Reply to DMs and messages the way Albert would. Use when the user asks "how would Albert reply to this", pastes a conversation and wants an Albert-style response, or asks you to draft/write a DM in Albert's voice. Albert sells AI voice agents / automations to local service businesses (Go High Level, lead follow-up, bookings).

    Also in 5 projects that use this

  • yawningwhaleAISkill

    new-client-system

    Scaffold a new client's full stack — Next.js 16 frontend dashboard + Trigger.dev backend worker — from the Shiney automations template. Use when the user says "new client", "onboard a client", "scaffold a client system", "set up <client-name>", or wants to start a fresh frontend+backend project styled and structured like the Shiney automations dashboard. Produces structure only; no automations are scaffolded — those are added later.

    Also in 6 projects that use this

  • huyvpSkill

    cost-reducer

    Reduce cloud, infrastructure, and operational costs while maintaining performance. Use when writing database queries, configuring cloud resources, optimizing bundles, setting up caching, choosing between services, sizing instances, configuring CDN, managing storage, or reviewing code for cost inefficiencies. Covers AWS/GCP/Vercel pricing, database optimization, serverless tuning, image pipelines, observability costs, and FinOps practices.

    Also in 9 projects that use this

  • ffsshhttiikkSkill

    scalability

    Core foundational concepts and principles for Scalability

    Also in 9 projects that use this

  • RoxenRobloxSkill

    youtube-broll-maker

    Generate 10-second B-roll footage of yourself doing an action using the Higgsfield MCP (Seedance 2.0). Upload one photo of yourself, describe the action ("typing on laptop", "walking at night"), pick from 5 cinematography style presets, get an MP4. Use when the user wants B-roll, cutaway footage, "me doing X" video, YouTube B-roll, or any image-to-video of themselves performing an action.

    Also in 3 projects that use this

  • RoxenRobloxSkill

    youtube-popup-graphic

    Generate stunning Adobe-Premiere-Pro-style UI popup motion graphics for YouTube videos using the Higgsfield MCP. The user uploads a style reference image (any UI mockup, dashboard, glass card, design they love), names one skill/feature/item, and the skill produces an MP4 of a single card popping in styled to match the reference. Use when the user wants a "popup graphic", "popup animation", "card popup", "skill popup", "AE/Premiere-style animation", "stunning UI animation for YouTube", or says "make me a popup for <skill/feature/item> styled like <reference>".

    Also in 3 projects that use this

  • +4 more from yawningwhaleAI

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the detailed reference files for comprehensive patterns:

    line 12
  2. Distinctive:

    Check connected account status: before executing tools: ACTIVE, INITIATED, EXPIRED, FAILED, INACTIVE

    line 95
  3. Very specific:

    Use $ARGUMENTS to understand what the user wants to integrate.

    line 122
  4. Distinctive:

    Use clear headings and bullet lists where helpful.

    line 128
  5. Distinctive:

    Call out assumptions and open questions at the end.

    line 129
  6. Distinctive:

    NEVER weaken or skip a failing test to make a change land.

    line 141
  7. Distinctive:

    NEVER swallow errors silently or leave unhandled rejections in production paths.

    line 142
  8. Distinctive:

    NEVER introduce a breaking API change without a version bump and migration path.

    line 143

“Common” is measured: kept by at least 6 in 10 of the 29 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Composio

You are an expert at integrating AI agents with third-party applications using Composio — the developer-first platform that connects agents to 1000+ apps via unified SDKs and MCP. Read the detailed reference files for comprehensive patterns:

  • references/sdk-reference.md — Python and TypeScript SDK patterns, sessions, tools, MCP integration, executing actions
  • references/auth-and-triggers.md — OAuth/API key authentication flows, connected accounts, triggers, webhooks, polling

Setup Checklist

Python

pip install composio composio-claude-agent-sdk

TypeScript

npm install composio @composio/claude-agent-sdk

Environment Variables

COMPOSIO_API_KEY=your_composio_api_key    # from composio.dev dashboard
ANTHROPIC_API_KEY=your_anthropic_api_key  # for Claude integration

Key Concepts

ConceptDescription
ToolkitsBundles of tools by service (github, gmail, slack, notion, etc.)
ToolsDiscrete operations: GITHUB_CREATE_ISSUE, GMAIL_SEND_EMAIL, SLACK_POST_MESSAGE
Auth ConfigsReusable auth blueprints (OAuth2, API Key, Bearer Token) per toolkit
Connected AccountsUser-to-toolkit links created after OAuth consent or API key setup
TriggersEvent listeners: GITHUB_COMMIT_EVENT, SLACK_NEW_MESSAGE, GMAIL_NEW_EMAIL
SessionsIsolated user contexts with access to tools (native or MCP)
User IDPrimary identifier scoping all operations to a specific user

Core Patterns

Initialize Client

Python:

from composio import Composio

composio = Composio(api_key = "<YOUR_API_KEY>")
# Or set COMPOSIO_API_KEY env var and omit api_key

TypeScript:

import { Composio } from "composio";

const composio = new Composio({ apiKey: "your_api_key" });

Create Session and Get Tools (Native)

session = composio.create(user_id="user_123", toolkits=["github", "gmail"])
tools = session.tools()
# Pass tools to your Claude agent

Create Session and Get MCP URL

session = composio.create(user_id="user_123", toolkits=["github", "slack"])
mcp_url = session.mcp.url
# Use mcp_url in MCP-compatible clients (Claude Desktop, Cursor, etc.)

Authenticate a User (OAuth2)

connection_request = composio.connected_accounts.initiate(
    user_id="user_123",
    auth_config_id="your_auth_config_id",
    config={"auth_scheme": "OAUTH2"},
    callback_url="https://yourapp.com/callback"
)
# Redirect user to: connection_request.redirect_url
# After consent, wait for connection:
connected_account = connection_request.wait_for_connection()

Set Up a Trigger

trigger = composio.triggers.create(
    slug="GITHUB_COMMIT_EVENT",
    user_id="user_123",
    trigger_config={"owner": "repo-owner", "repo": "repo-name"},
)

Critical Rules

  1. Always scope operations by user_id — every session, connected account, and trigger belongs to a user
  2. Only ACTIVE connected accounts can execute tools — check status before using
  3. Use MCP mode for dynamic tool discovery — reduces token usage vs passing all tool definitions upfront
  4. Auth configs are reusable — create one per toolkit per environment, reuse across users
  5. Composio auto-refreshes OAuth tokens — no manual token refresh needed
  6. Webhook triggers are real-time — polling triggers check every ~1 minute
  7. Never hardcode API keys — use environment variables (COMPOSIO_API_KEY)
  8. Use type-safe tool names — e.g., GITHUB_CREATE_ISSUE not arbitrary strings
  9. Check connected account status before executing tools: ACTIVE, INITIATED, EXPIRED, FAILED, INACTIVE
  10. Max toolkits per session vary by plan — check Composio dashboard for limits

Common Workflows

Email Triage Agent

session = composio.create(user_id="user_1", toolkits=["gmail", "slack", "notion"])
tools = session.tools()
# Agent reads Gmail, classifies emails, routes to Slack channels, logs in Notion

GitHub PR Monitor

trigger = composio.triggers.create(
    slug="GITHUB_PULL_REQUEST_EVENT",
    user_id="user_1",
    trigger_config={"owner": "myorg", "repo": "myrepo"},
)
# On PR event -> agent reviews code, posts summary to Slack

Multi-App Workflow

session = composio.create(
    user_id="user_1",
    toolkits=["github", "slack", "linear", "notion"]
)
tools = session.tools()
# Agent receives Slack message -> creates Linear issue -> updates Notion -> confirms in Slack

Use $ARGUMENTS to understand what the user wants to integrate. Read the reference files for detailed SDK patterns and authentication flows before writing code.

Output format

  • Lead with the result the user asked for.
  • Use clear headings and bullet lists where helpful.
  • Call out assumptions and open questions at the end.
  • Stay specific to the Composio workflow; avoid generic filler.

Verification & Quality Checklist

  • Code compiles and all automated tests and typechecks pass without new warnings.
  • Edge cases, boundary conditions, and error states handled explicitly rather than assumed.
  • No hardcoded secrets, credentials, or insecure defaults introduced.
  • Changes are covered by a test that fails without them.

Anti-Patterns & Constraints

  • NEVER weaken or skip a failing test to make a change land.
  • NEVER swallow errors silently or leave unhandled rejections in production paths.
  • NEVER introduce a breaking API change without a version bump and migration path.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.