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.
git clone --depth 1 https://github.com/melandlabs/openloomi /tmp/openloomi && cp -r /tmp/openloomi/skills/openloomi ~/.claude/skills/openloomiSKILL.md
# 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 intent | Use | | --- | --- | | First-use setup, install guidance, readiness checks | `openloomi-setup` | | Search memory, knowledge base, documents, insights | `openloomi-memory` | | Connect platforms, list accounts, check connector status, send replies | `openloomi-connectors` | | Use third-party OAuth apps such as Slack, Gmail, GitHub, Notion, Linear, or Jira | `composio`, paired with `openloomi-connectors` | | Inspect Loop state, run a tick, manage decisions, preferences, channels, or rules | `openloomi-loop` | | List active Goals or inspect ordered Goal progress | `openloomi-goals` | | Answer backend route, local API, auth, RAG, integrations, or workspace questions | `openloomi-api` | | Explain OpenLoomi concepts, product capabilities, or user workflows | `openloomi-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.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Use 1000+ external apps via Composio - either directly through the CLI or by building AI agents and apps with the SDK
Walk the user through installing the optional composio skill and turning on screen memory
Persist learning across turns by actively maintaining MENTAL_MODEL.md in the workspace. Use for iterative coding, debugging, benchmarking, or any feedback-driven task; read and update the file with actual filesystem writes before every response, never just hidden/internal memory.
Create an end-to-end Continual Learning Bench task. Use when adding a new src/tasks/<name> benchmark task, including design interview, concrete Jinja prompt templates, JSON action contracts, observation templates, debug schedule, behavioral E2E tests, validation, smoke/debug runs with icl and icl_notepad, and README documentation.
Drive a native macOS app via the cua-driver CLI (default) or MCP server — snapshot its AX tree, click/type/scroll by element_index, verify via re-snapshot. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real macOS application on the host (e.g. "open a file in TextEdit", "navigate to /Applications in Finder", "click the Save button in Numbers").
High-performance data analysis using Polars - load, transform, aggregate, visualize and export tabular data. Use for CSV/JSON/Parquet processing, statistical analysis, time series, and creating charts.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a "report", "memo", "letter", "template", or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.