What problem does it solve? Building Lark/Feishu bots and real-time integrations normally requires standing up webhook servers and handling push callbacks. This Skill lets an AI agent subscribe to Lark platform events (IM messages, reactions, chat changes, VC meeting endings, Minutes generation) directly from the command line, streaming them as NDJSON without any server infrastructure. ## Core Features & Use Cases - Event Discovery & Schema Inspection: List all subscribable EventKeys and inspect each key's parameters, output schema, and field semantics before consuming. - Bounded or Continuous Consumption: Stream events with --max-events / --timeout limits, jq-based filtering and projection, and per-event file output. - Subprocess Contract for AI Agents: A stderr ready-marker, stdin-EOF graceful shutdown, and documented exit codes make it safe to run as a long-lived subprocess. - Use Case: Build a Lark bot that watches im.message.receive_v1, filters for group text messages with jq, and reacts to each message in real time — all orchestrated by an AI agent running lark-cli event consume as a subprocess. ## Quick Start Ask the agent to listen for incoming Lark messages by running lark-cli event consume im.message.receive_v1 as the bot identity and show each received message.