What problem does it solve? Turning Feishu/Lark API operations into reusable, discoverable AI Skills requires knowing which lark-cli commands exist, what parameters and OAuth scopes each API needs, and how to structure a valid SKILL.md. This Skill guides that entire authoring process so new Skills are consistent and correctly triggered. ## Core Features & Use Cases - API Research Workflow: Inspect registered APIs and Shortcuts with lark-cli <service> --help, query parameter definitions via lark-cli schema, and call any unregistered Feishu OpenAPI endpoint through lark-cli api. - SKILL.md Template: Provides a ready-made frontmatter and body template covering description triggers, command examples, multi-step orchestration, and a permission scope table. - Authoring Principles: Enforces best practices such as trigger-oriented descriptions, OAuth scope documentation, --dry-run previews for write operations, and rollback guidance for multi-step flows. - Use Case: You want to package a multi-step approval workflow (initiate instance, query status, approve) as a reusable Skill. Use this Skill to research the required endpoints, then generate a skills/lark-approval-flow/SKILL.md with correct commands and scopes. ## Quick Start Ask the AI to create a new lark-cli Skill that wraps a specific Feishu API operation, for example creating calendar events, and have it generate the SKILL.md file.
