A sophisticated toolset for sending and managing interactive UI elements like buttons, polls, and forms within Feishu (Lark) messages.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install feishu-interactive-cards
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 feishu-interactive-cards using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Feishu Interactive Cards skill is designed to transform how AI agents communicate by replacing ambiguous text responses with structured, interactive UI components. Built for the Openclaw Skills ecosystem, it allows developers to send rich cards that include buttons, multi-select menus, and input fields, enabling users to make decisions or provide data with a single click.
At its core, this skill prioritizes clarity and speed. By utilizing interactive cards, agents can ensure that destructive actions are confirmed, tasks are tracked visually, and complex inputs are collected without the friction of natural language processing errors. It includes a robust long-polling callback server, meaning you can handle user interactions in real-time without needing a public IP or complex webhook setup.
First, ensure your credentials are configured in your global configuration file. Then, start the long-polling callback server to listen for user interactions:
cd workspace/skills/feishu-interactive-cards/scripts
node card-callback-server.js
You can then send cards using the provided CLI tool. For example, to send a confirmation card:
node scripts/send-card.js confirmation "Do you want to proceed?" --chat-id YOUR_CHAT_ID
The skill organizes data through structured JSON templates and callback payloads:
| Component | Type | Description |
|---|---|---|
| Card Templates | JSON | Found in the examples/ directory; defines the layout of confirmation, poll, and form cards. |
| Action Value | Object | Hidden metadata within buttons used to pass state (like file paths or IDs) back to the agent. |
| Callback Context | Object | Contains the open_message_id required for updating a card after a user interaction. |
| Gateway Payload | JSON | The formatted event data sent from the callback server to the AI agent for processing. |
Loading
A universal save-for-later skill that allows AI agents to organize product discoveries into a centralized, shareable wishlist.

A universal product-saving skill that converts any retailer URL into a one-click wishlist link for AI agents.

A lightweight Python-based Spotify Web API client designed for AI agents to manage music playback, search, and playlists.

An autonomous multi-model research system that orchestrates four parallel AI agents to generate framework-driven, cross-validated technical reports.

A lightweight browser automation tool for Openclaw Skills to extract and translate DMM/FANZA public rankings without needing API credentials.

A specialized technical analysis tool that scans repositories to identify, score, and document distinctive code patterns for intellectual property preparation.








































