A standardized framework for AI agents to execute tasks, sync Markdown documents, and collaborate within the CoMind platform using Model Context Protocol.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install comind
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install comind using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is CoMind AI Member Operations?
CoMind is a sophisticated human-machine collaboration platform designed to integrate AI members into professional team workflows. By leveraging Openclaw Skills, this skill provides a rigorous operational manual for AI agents to handle task pushing, status tracking, and multi-channel communication. It transforms how agents interact with human-led projects by enforcing standardized protocols for every action.
The core of the skill lies in its triple-channel architecture: high-efficiency conversation actions, reliable MCP API calls, and convenient Markdown synchronization. This ensures that AI agents remain productive and synchronized with the team database, whether they are updating a simple task status or delivering a complex technical architecture document for human approval.
CoMind AI Member Operations Use Cases
- Automated task lifecycle management from assignment to completion reporting.
- Batch processing of project tasks and schedules via Markdown synchronization.
- Formal document delivery workflows including human-in-the-loop review and approval cycles.
- Real-time AI status monitoring to provide transparency on agent workload and progress.
How CoMind AI Member Operations Works
- The AI agent receives a task push or a user request containing the necessary project context and task IDs.
- The agent utilizes Openclaw Skills to update its internal status to working and the specific task status to in_progress.
- Depending on the complexity, the agent performs work and logs progress through the conversation channel or direct API calls.
- Documents are generated with specific YAML front matter that triggers an automated sync to the CoMind database.
- Upon completion, the agent submits deliverables and uses the verification loop to ensure the platform database reflects the final state correctly.
CoMind AI Member Operations Setup
To enable this skill, configure the connection to your CoMind instance using environment variables. These Openclaw Skills require a valid API token obtained from the CoMind member management dashboard.
# Set environment variables in your .env file or shell
export COMIND_BASE_URL="http://localhost:3000"
export COMIND_API_TOKEN="your_mcp_api_token_here"
Alternatively, if using the Openclaw Gateway, the configuration can be requested dynamically via a WebSocket event: comind.config.request.
CoMind AI Member Operations Data Schema & Taxonomy
The skill organizes data by mapping Markdown elements directly to the CoMind database schema:
| Markdown Element | CoMind Entity | Mapping Rules |
|---|---|---|
| H1 or Front Matter | Documents | Parsed as document title and metadata |
Task List (- [ ]) |
Tasks | Automatically creates or updates task entries |
| @MemberName | Members | Maps human or AI names to internal IDs |
Front Matter delivery_status |
Deliveries | Triggers the creation of reviewable delivery records |
| YAML Metadata | Projects | Associates documents and tasks with specific project IDs |
CoMind AI Member Operations Advanced Features
- Triple-channel failover logic: Automatically uses MCP API as a fallback when WebSocket actions fail.
- Idempotency support: Uses unique keys to prevent duplicate task creation during network retries.
- Automated audit logging: Records every API call to a persistent database for traceability.
- Integrated verification scripts: Built-in bash templates to confirm that database states match AI expectations after batch operations.
- Multi-platform delivery support: Syncs deliverables across local storage, Feishu, Notion, and Tencent Docs.
SKILL.md
Loading
Related Openclaw Skills
Star Office UI
A collaborative pixel-art dashboard that visualizes the real-time status and movement of multiple AI agents in a virtual workspace.
Reve AI Image Generation
A high-performance CLI tool for generating, editing, and remixing images using the Reve AI API and Bun runtime.
qmd Local Markdown Search
A high-performance CLI tool for indexing and searching local markdown knowledge bases using keyword, vector, and hybrid search methods.
Naver Search Skill
A specialized search integration for OpenClaw agents to access real-time Korean web data including news, shopping, images, and local business information.
Telegram Body Scan
A high-precision AI measurement skill that extracts body data from Telegram video uploads using AnthroVision bridge tools.
Proposal Discovery Interview
A structured AI interview agent that extracts unique professional facts to generate approved, reusable statements for high-converting proposals.
Featured*
