What problem does it solve? Building a builtin tool for the LobeHub agent runtime requires coordinating five separate faces — manifest, ExecutionRuntime, frontend executor, client UI surfaces, and registry wiring — and missing any one causes silent failures like "tool not found", blank result cards, or stuck placeholders. This Skill provides the complete authoring guide, conventions, and checklists to create or extend builtin tools correctly the first time. ## Core Features & Use Cases - Five-face architecture guidance: Explains where manifests, ExecutionRuntime logic, BaseExecutor subclasses, and the six client UI surfaces (Inspector, Render, Placeholder, Streaming, Intervention, Portal) live and how they connect. - Design rules and contracts: Covers identifier naming (lobe-<domain>), ApiName const objects, the result contract (content/state/error), the mandatory toResult() funnel, and i18n key conventions. - Registry wiring checklist: Lists every registry file that must be updated so tools appear and run correctly, plus a diagnostics table mapping symptoms to fixes. - Use Case: When adding a new packages/builtin-tool-<name>/ package or a new API to an existing tool, follow the authoring checklist and copy the closest reference tool (calculator, task, web-browsing, or local-system) to ship a fully wired tool with passing tests. ## Quick Start Ask the agent to scaffold a new builtin tool package following the builtin-tool guide, including its manifest, ExecutionRuntime, executor, and Inspector.