A comprehensive CLI-based workflow skill for managing employee inquiries, report cycles, and task synchronization within the CWork platform.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install cwork-skill-update
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install cwork-skill-update using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The cms-cwork-workflow provides a robust suite of 9 intent-based orchestration scripts designed specifically for AI agents to interact with the CWork enterprise coordination platform. It encapsulates complex API interactions—including authentication, parameter validation, and retry mechanisms—into developer-friendly Python scripts. This skill enables agents to handle everything from searching employee IDs and sending multi-layered reports to managing todo lists and nudging overdue tasks, ensuring high reliability through an Agent-First design. By using these Openclaw Skills, developers can build agents that seamlessly bridge the gap between LLM reasoning and enterprise workflow execution without manual API handling.
Ensure you have Python 3.9+ installed and the cms-auth-skills dependency configured. Install the skill into your agent's environment and set the necessary environment variables for authentication.
# Clone the repository containing the workflow scripts
git clone https://github.com/xgjk/cwork-skills.git
# Navigate to the skill directory
cd cwork-skills/cms-cwork-workflow
# Optional: Configure GITHUB_TOKEN for automated issue reporting
export GITHUB_TOKEN="your_github_token_here"
The skill uses standardized JSON structures for both input and output to ensure consistency across different automation tools.
| Data Component | Format | Description |
|---|---|---|
| Employee Info | JSON Object | Contains empId, name, title, department, and status. |
| Workflow Levels | Array | Defines 'suggest', 'decide', or 'read' nodes for reports. |
| Task Metadata | JSON Object | Includes task title, content, deadline, and assignee info. |
| Error Response | JSON (stderr) | Returns success: false with specific API error codes and messages. |
Loading
A comprehensive AI-driven framework for managing end-to-end finance and accounting operations from invoicing to cash flow forecasting.

Polyclanker enables AI agents to compete in play-money prediction markets, mirroring real-world data from Polymarket to test AI reasoning and calibration.

A sophisticated intelligence framework for monitoring global risks, tracking sanctions, and delivering actionable geopolitical briefings.

A structured emotional mapping engine that organizes fragmented memories of significant past figures into a clear, archival dossier for self-reflection and closure.

A comprehensive automation skill for government ministries and public institutions to manage formal documentation, reporting, and inter-departmental communication.

An AI-powered operational assistant designed to manage patient scheduling, medical records, and clinic workflows for healthcare facilities.








































