productivity▌

IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.

当用户提出请求时，根据以下规则选择性读取文档。不要一次性读取所有文档，只读取与用户请求相关的文件。

Write and maintain Storybook stories using CSF 3.0 best practices with type safety. \n \n Use CSF 3.0 format with satisfies Meta<typeof Component> for type-safe story definitions; omit title to let Storybook infer it from file paths \n Define shared args at the Meta level and override only differences in individual stories; avoid hardcoding props or repeating args across variants \n Leverage automatic argTypes inference from TypeScript component types; manually specify argTypes only for Rea

Refactor code while preserving behavior, improving clarity, and reducing complexity. \n \n Covers five core refactoring patterns: Extract Method, DRY principle removal, conditional-to-polymorphism conversion, parameter object introduction, and SOLID principle application \n Includes behavior validation workflow with pre-refactoring analysis, post-refactoring testing (unit, type, lint, snapshot), and change documentation \n Provides refactoring checklist covering function length, parameter count,

Master index for all Odoo 19 development guides. Read the appropriate guide from references/ based on your task.

Role: Telegram Mini App Architect

Generate Excalidraw diagrams from natural language descriptions in multiple formats. \n \n Supports nine diagram types: flowcharts, relationship diagrams, mind maps, architecture diagrams, data flow diagrams, swimlane business flows, class diagrams, sequence diagrams, and ER diagrams \n Outputs valid .excalidraw JSON files that open directly in Excalidraw or the VS Code extension \n Includes layout guidelines, element count recommendations, and color schemes for consistent visual design \n Optio

This skill enables AI agents to perform a comprehensive, holistic UX audit based on the Interaction Design Foundation's methodology from "The Basics of User Experience Design". It evaluates products across multiple dimensions and proposes strategic redesign recommendations.

paper-audit is now deep-review-first. Its core job is to behave like a serious reviewer: find technical, methodological, claim-level, and cross-section issues; keep script-backed findings separate from reviewer judgment; and return a structured issue bundle plus a revision roadmap.

Research-backed market intelligence with source attribution and decision-oriented analysis. \n \n Covers investor diligence, competitive analysis, market sizing, and technology vendor research with structured output including findings, implications, risks, and recommendations \n Enforces sourcing standards: every claim requires attribution, stale data is flagged, and contrarian evidence is included alongside supporting data \n Separates fact, inference, and recommendation clearly to support deci