openloomi-feature-guide
Use this when users ask about openloomi features, capabilities, or how to use it. Examples: 'openloomi 怎么用', '你能做什么', 'What can you do?', 'How does openloomi work?', 'Tell me about openloomi features', 'What platforms does openloomi support?', 'How do I use scheduled tasks?', 'What is Loop?', 'How does the attention agent work?', 'What is a Decision Card?', 'How do connectors work?', 'How do I extend Loop with custom types?', 'What is a classifier rule?', 'How do I plug openloomi into Claude Code / Codex?'
npx skills add melandlabs/openloomi --skill openloomi-feature-guide --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
OpenLoomi is an open-source AI coworker driven by an attention agent. It connects authorized work tools and screen content, builds context, and surfaces what happened and what to do next. It supports standalone use or integration with agent runtimes like Claude Code, Codex, OpenCode, Hermes, and OpenClaw, with Loomi surfacing decisions as desktop cards for approval.
How it works
The skill defines a single end-to-end pipeline: Connectors pull raw events into Signals, Loop reads memory and signals to produce Decisions, Cards render in the UI and on the Attention Agent, the user approves, an Action Runner executes via a Connector, and results write back to Memory and the Audit Log. Key concepts include Connectors, Signals, Memory, Loop, Decisions, Cards, Attention Agent, Audit Log, and ActionKind. The flow also uses Screen Capture memories (macOS) as a separate input path, and the Automation system for scheduled jobs. The glossary explains Relationships: Memory holds context; Loop judges and queues cards; Attention Agent surfaces Cards; Action Runners carry out actions through Connectors; outcomes are written back to Memory and the Audit Log.
When to use it
Use when users ask about OpenLoomi features, capabilities, or usage. Trigger examples include inquiries like "What platforms does openloomi support?", "How do I use scheduled tasks?", or "How does the attention agent work?" (as described in the description and usage sections).
What it can touch
The skill references and interacts with: Connectors, Memory, Loop, Attention Agent (Loomi), Audit Log, Card UI, ActionRunners, and scheduled jobs/Automation. It describes how these pieces connect and what they produce (Signals, Decisions, Cards, Actions).
Caveats
The content notes that readiness may require running openloomi-setup first and mentions the OpenLoomi Desktop installation step if needed. It defines licensing as Apache-2.0 for the OpenLoomi project. All facts are drawn from the defined glossary and flow descriptions.
> **Note:** If OpenLoomi readiness is unknown, use `openloomi-setup` first. If OpenLoomi Desktop is not installed, follow [Getting Started](https://openloomi.ai/docs/getting-started). # 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. The terms used here (Loop, Signal, Decision, Card, ActionKind, Attention Agent, Connector, Memory, Audit Log, Plugin, Agent Runtime, Composio, etc.) are defined in the **Glossary** below — read it first if a user asks anything conceptual. --- ## What is OpenLoomi OpenLoomi is an **open-source AI coworker, driven by an attention agent**. It connects your authorized work tools and screen content, builds a **holistic context** of your people, projects, and decisions, and tells you what happened, why it matters, what to do next — and surfaces daily summaries — saving your attention for what matters. Use it standalone, or plug any Agent framework into the same resident desktop: **Claude Code, Codex, OpenCode, Hermes, and OpenClaw** all work. The desktop attention agent (a small fox named **Loomi**) lives on top of yo
- What is OpenLoomi
- Glossary
- How the concepts fit together
- Core concepts
- Supporting concepts
- Common distinctions
- Core Capabilities
- Capability Highlights
- 🐾 Attention Agent
- 🧠 Holistic Context
- 🔌 Platform Connectors
- ⏰ Proactive Tasks
- 🧩 Any Agent Integration
- Reference
What does the openloomi-feature-guide skill do?
Use this when users ask about openloomi features, capabilities, or how to use it. Examples: 'openloomi 怎么用', '你能做什么', 'What can you do?', 'How does openloomi work?', 'Tell me about openloomi features', 'What platforms does openloomi support?', 'How do I use scheduled tasks?', 'What is Loop?', 'How does the attention agent work?', 'What is a Decision Card?', 'How do connectors work?', 'How do I extend Loop with custom types?', 'What is a classifier rule?', 'How do I plug openloomi into Claude Code / Codex?'
How do I install it?
Run `npx skills add melandlabs/openloomi --skill openloomi-feature-guide --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From melandlabs/openloomi, a repository with 764 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.