Skip to content
FunCoding

openloomi

OpenLoomi entrypoint for skill-only agent runtimes without a plugin mechanism. Use when the user mentions OpenLoomi or Loomi, wants first-use setup guidance, wants to use local OpenLoomi memory, connectors, Loop, knowledge base, RAG search, or asks how to install OpenLoomi skills in runtimes such as WorkBuddy or other skill-capable agents.

Star
1,039
License
Apache-2.0
Last commit
Sep 24, 2026

skills/openloomi/SKILL.md

View on GitHub

OpenLoomi Skills Entrypoint

Use this skill as the front door for OpenLoomi in agents that can load skills but do not support OpenLoomi plugins.

OpenLoomi remains the runtime owner. The desktop app owns memory storage, connector credentials, Loop execution, model/provider settings, local API routes, and secret handling. Skills only explain how to route work into that local runtime.

First Step

When readiness is unknown, start with openloomi-setup. It guides the user through installing or opening OpenLoomi Desktop, confirming the local API, and finishing the session/token setup. Do not ask the user to paste API keys, OAuth tokens, connector secrets, or OpenLoomi auth tokens into chat.

Route Requests

Use the narrow OpenLoomi skill that matches the task:

User intentUse
First-use setup, install guidance, readiness checksopenloomi-setup
Search memory, knowledge base, documents, insightsopenloomi-memory
Connect platforms, list accounts, check connector status, send repliesopenloomi-connectors
Use third-party OAuth apps such as Slack, Gmail, GitHub, Notion, Linear, or Jiracomposio, paired with openloomi-connectors
Inspect Loop state, run a tick, manage decisions, preferences, channels, or rulesopenloomi-loop
List active Goals or inspect ordered Goal progressopenloomi-goals
Answer backend route, local API, auth, RAG, integrations, or workspace questionsopenloomi-api
Explain OpenLoomi concepts, product capabilities, or user workflowsopenloomi-feature-guide

Common Flows

Use these examples to route common requests without reimplementing OpenLoomi logic in the agent:

  • Search memory: start with openloomi-setup if readiness is unknown, then use openloomi-memory to search memory, knowledge base documents, or insights.
  • Post to Slack: start with openloomi-setup, use openloomi-connectors to check connector/account readiness, then use composio for the OAuth-backed Slack action when the user asks to send or post.
  • Draft an email: start with openloomi-setup, use openloomi-memory for relevant context, then use composio or connector guidance for the mail surface the user has authorized.
  • Summarize a Notion page: start with openloomi-setup, use composio for the authorized Notion access path, then hand useful context to openloomi-memory or openloomi-api when the user wants it saved, searched, or grounded in the local knowledge base.

Boundaries

  • Do not depend on Codex or Claude plugin files.
  • Do not call plugin bridge scripts such as loomi-bridge.mjs.
  • Do not duplicate OpenLoomi business logic inside the agent.
  • Do not invent connector behavior. Use the connector and Composio skills for platform-specific flows.
  • If OpenLoomi Desktop is missing or the local API is unavailable, use openloomi-setup to provide official installation and recovery guidance.

Similar Skills

subagent-driven-development

OBobra/superpowers298k2,631 new stars in the last 7 days

chief-of-staff

MAmattpocock/skills288k10,178 new stars in the last 7 days

setup-matt-pocock-skills

MAmattpocock/skills288k10,178 new stars in the last 7 days

ask-matt

MAmattpocock/skills288k10,178 new stars in the last 7 days

agent-eval

AFaffaan-m/ECC278k4,046 new stars in the last 7 days

autonomous-agent-harness

AFaffaan-m/ECC278k4,046 new stars in the last 7 days