openloomi-feature-guide
openloomi is a proactive AI workspace that monitors business signals, executes autonomous tasks, and maintains long-term memory across work contexts. Use this skill to answer user questions about openloomi's core features, capabilities like noise filtering and autonomous execution, builtin skills spanning data analysis to web automation, installation instructions, and how to accomplish specific tasks such as creating automations or connecting integrations like Telegram.
git clone --depth 1 https://github.com/melandlabs/openloomi /tmp/openloomi-feature-guide && cp -r /tmp/openloomi-feature-guide/skills/openloomi-feature-guide ~/.claude/skills/openloomi-feature-guideSKILL.md
> **Note:** If you haven't downloaded or installed openloomi yet, please refer to [Getting Started](https://openloomi.ai/docs/getting-started) for installation instructions. # OpenLoomi Product Features Use this skill when users ask about openloomi features, usage, or capabilities. Provide accurate and easy-to-understand feature introductions and operation guides. --- ## What is OpenLoomi openloomi is a **Proactive AI Workspace** that understands your intent, orchestrates execution, and gets things done. It's not just another AI assistant—it's an innovative AI product that **senses business signals**, **orchestrates tasks autonomously**, and **tracks and validates results end-to-end**. ### Core Value Proposition openloomi transforms how individuals and SMB teams work by: - **Proactive Awareness** — Monitors signals across platforms and alerts you before you ask - **Long-Term Memory** — Remembers context across months, never forgets commitments - **Autonomous Execution** — Not just telling you what to do, but doing it - **Builtin Skills** — Rich execution capabilities for every work scenario --- ## Core Capabilities ### 🧠 Long-Term Memory Clear recollection, never forgotten. openloomi builds persistent knowledge graphs that remember all important people, events, decisions, and context across sessions and time. Six months later, it still knows your commitments and preferences. ### 🎯 Noise Filtering Tells you what you should act on. With hundreds of daily messages, openloomi replaces "information overload" with "priority signals." Filters 95% of noise, focusing your attention on the 5% that truly matters. ### ⚡ Powerful Engine Intent understanding, automatic orchestration. When you say "Help me prepare an investor pitch," openloomi automatically understands intent, breaks it into multiple sub-tasks, invokes appropriate Skills, and chains execution. ### 🔐 Security & Privacy Your data, your sovereignty. Local-first architecture—your raw data never leaves your device. End-to-end AES-256 encryption, zero-data-training commitment, SOC 2 compliance audit. ### 🛠️ Builtin Skills Builtin Skills covering every work scenario, continuously expanding: - 📊 Data Analysis - 💻 Code Generation - 📄 Document Creation - 🌐 Web Automation - 🎨 Image Generation - 📧 Email Writing - 🔍 Deep Research - 📊 PPT Creation - more skills... --- ## Use Cases ### 🌍 Global Managers Never miss a critical signal across time zones. Business runs 24/7 globally. openloomi filters time zone and language noise, capturing high-value opportunities while you sleep—wake up to a refined action list. ### 🧑💻 Engineers & Product Teams Team memory that never decays. Transform discussions scattered across Slack, Jira, and documents into structured knowledge. Auto-generate weekly reports, sync missed context, eliminate "context rot." ### 🚀 Founders & Sales One person does the work of many, at scale. openloomi learns your communication style, automatically maintains hundreds of client relationships, follows up on leads, generates personalized proposals—never burns out. --- ## Quick Start ### 1. Sign Up / Sign In - Sign up with email and password - Or sign in directly with your **Google** or **GitHub** account ### 2. Onboarding First-time users will go through an onboarding flow: 1. Select your role and focus areas 2. Tell openloomi what you'd like it to help with 3. Connect platforms to unlock deeper insights 4. Name your AI assistant ### 3. Connect Communication Platforms Click **[Connect platform]** to complete authorization. **Supported platforms:** - **Messaging**: Slack, Telegram, Discord, WhatsApp, Weixin, iMessage, QQ, Feishu, DingTalk - **Email**: Gmail, Outlook - **Social Media**: X (Twitter) — for marketing and content automation - **Other**: RSS - **Coming Soon**: Google Drive, Microsoft Teams, Notion, HubSpot, Google Calendar --- ## Platform Connection Steps ### WhatsApp 1. Click **[Connect WhatsApp]** 2. Complete authorization via **QR code scan** or **phone pair code** 3. Once authorized, openloomi will automatically read your WhatsApp messages to generate long-term events. You can send messages in **"Starred Messages"** and AI will: - Read and understand your message content - Generate smart insights in openloomi - You can converse with AI about these messages in openloomi > 💡 How to use: Open "Starred Messages" in WhatsApp, send a message to yourself, and AI will automatically read and understand it. ### Weixin 1. Click **[Connect Weixin]** 2. Complete authorization via **QR code scan** ### Telegram 1. Click **[Connect Telegram]** to enter the authorization page in the source settings. 2. Choose a login method: - **Phone verification**: Enter phone number → receive verification code → enter 2FA password if enabled - **QR code**: Scan QR code with Telegram → enter 2FA password if enabled - **Quick login**: If you have the official Telegram desktop app installed locally, you can use your existing session to log in without phone number or verification code 3. Once authorized, openloomi will automatically read your Telegram messages to generate long-term events on the Today page. You can send messages in **"Saved Messages"** and AI will: - Read and understand your message content - Generate smart insights in openloomi - You can converse with AI about these messages in openloomi > 💡 How to use: Open "Saved Messages" in Telegram, send a message to your saved messages, and AI will automatically read and understand it. ### Slack 1. Click **[Connect Slack]** in the integration settings 2. Click **[Install openloomi]** on the authorization page to add to your workspace 3. Note: Currently only workspace owners can install ### Discord 1. Click **[Connect Discord]** in the integration settings 2. Select the Discord server to install 3. Grant openloomi bot message permissions 4. Note: Only server admins can install ### Gmail 1. Click **[Connect Gmail]** in the integration
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.
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").
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.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
openloomi API documentation and reference. Use when working with openloomi backend APIs, AI, authentication, characters, messages, files, integrations, billing, or any server-side functionality. Triggers: API endpoints, backend routes, authentication, cloud API, integrations
openloomi Connectors tools - manage platform integrations (OAuth connections, list accounts, check status). Triggers: connect platform, integration status, list accounts, disconnect
openloomi Memory tools - search memory files, knowledge base, and chat insights. Triggers: memory search, knowledge base, documents, insights
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.