lark-event

Stream Lark IM, VC, Minutes, and Whiteboard events as NDJSON via lark-cli.

4|Updated Mar 8, 2026
One-click install
npx skills add https://github.com/FradSer/skills --skill lark-event-fradser
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lark-event
Source: https://github.com/FradSer/skills/tree/main/skills/lark/lark-event
Command: npx skills add https://github.com/FradSer/skills --skill lark-event-fradser

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Ingest and stream Lark/Feishu real-time events to downstream AI agents, enabling immediate processing and decision-making from live streams.

Core Features & Use Cases

  • Real-time event streaming: subscribe to IM, VC, Minutes, and Whiteboard events and emit NDJSON for AI consumption.
  • Bounded-run support: leverage --max-events and --timeout to control runtime and ensure predictable finishes.
  • Ready-marker aware: designed for AI subprocess workflows with deterministic startup signaling and robust error reporting.

Quick Start

Start streaming events by running lark-cli event consume im.message.receive_v1 --as bot to begin receiving NDJSON payloads.

Frequently Asked Questions about lark-event

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I stream Lark events in real-time for AI agents?

To stream Lark events for AI agents, you can process real-time IM, VC, Minutes, and Whiteboard events and deliver them as NDJSON using a CLI workflow. This requires lark-cli to subscribe to and consume the live event streams.

What types of Feishu events can I consume for real-time event streaming?

Real-time event streaming supports Feishu IM, VC (Video Conferencing), Minutes, and Whiteboard events. These events are processed and emitted as structured NDJSON payloads for immediate AI agent consumption.

How do I control the runtime when consuming a Lark event stream?

You can control Lark event stream runtime using bounded-run arguments like --max-events and --timeout. These parameters ensure predictable finishes by capping the number of consumed events or setting a maximum execution duration.

Do I need lark-cli to process NDJSON event streams for AI workflows?

Yes, lark-cli is a required dependency to process NDJSON event streams. It provides the necessary command-line interface to subscribe to Lark events, handle deterministic startup signaling via a ready-marker contract, and output structured data.

How does an AI subprocess know when a Lark event stream is ready?

A Lark event stream uses a ready-marker contract to provide deterministic startup signaling for AI subprocess workflows. This mechanism ensures the agent knows exactly when the event consumption process has successfully initialized and is ready to deliver data.

What is the best way to integrate live Feishu messages into an AI agent?

The best way to integrate live Feishu messages is to run lark-cli event consume im.message.receive_v1 --as bot. This subscribe to IM events and emits structured NDJSON payloads directly to your AI agent for immediate processing.