What problem does it solve? When you already hold a Lark (Feishu) meeting note_id, you still need to resolve what the note contains—its display type, AI summary document token, verbatim transcript token, and shared documents—before you can read any content. This Skill routes note_id-based lookups through lark-cli so you get the right document tokens and unified raw transcripts without guessing. ## Core Features & Use Cases - Note detail lookup: Run note +detail --note-id to retrieve note_display_type, note_doc_token, verbatim_doc_token, and shared_doc_tokens. - Unified transcript retrieval: Run note +transcript --note-id to pull the full raw verbatim record of unified-type notes, saved locally as Markdown or plain text. - Routing guidance: Built-in routing tables map inputs like meeting_id, minute_token, event_id, or vc-node-id to the correct upstream skill (lark-vc, lark-minutes, lark-calendar) before entering the Note domain. - Use Case: A user has a note_id from a meeting detail query and wants the verbatim transcript; the Skill checks note_display_type, then either fetches the verbatim Docx via docs or pulls the unified transcript directly. ## Quick Start Ask the assistant to look up the meeting note details and transcript for your known note_id using the lark-note skill.