What problem does it solve? Building Lark/Feishu bots and real-time integrations normally requires standing up webhook servers and handling push infrastructure. This Skill lets an AI agent subscribe to and consume Lark platform events (IM messages, approval status changes, task updates, meeting lifecycle, minutes, whiteboard edits) directly as NDJSON streams through the lark-cli event consume command, with a subprocess contract designed for agent callers. ## Core Features & Use Cases - Event discovery and schema inspection: List all subscribable EventKeys with lark-cli event list and inspect each key's params and output schema via lark-cli event schema before writing jq filters. - Bounded or unbounded consumption: Stream events to stdout as NDJSON, with --max-events and --timeout for bounded runs, --jq for filtering/projection, and a stderr ready-marker plus structured exit codes for reliable subprocess orchestration. - Domain references: Detailed per-domain catalogs for IM (12 EventKeys), Approval, Task, VC meetings, Minutes, Whiteboard, and Application bot menu events, including auth scopes, subscription lifecycle, and field-level gotchas. - Use Case: Build a Lark bot that listens for incoming messages with lark-cli event consume im.message.receive_v1 --as bot, filters group text messages via jq, and replies through the IM skill. ## Quick Start Ask the agent to listen for incoming Lark messages by running lark-cli event consume im.message.receive_v1 with the bot identity and show each received message.