去中心化金融

To install the Playwright browser defined in config, run this when the browser is missing or not installed.

Coordinate multi-agent workflows: sequential, parallel, and iterative patterns.Defines agent handoffs, dependencies, communication protocols, and integration.Use when designing multi-agent workflows, coordinating agent handoffs,planning agent dependencies, or building complex agent pipelines.

Plan sprints and backlogs in an AI-Driven Development workflow. Define features (backlogs), organize sprints as cumulative demo-able milestones, and manage the full development lifecycle.

Create and manage database migrations with proper rollback methods, focused changes, and zero-downtime deployment considerations. Use this skill when creating new database migration files, modifying table schemas, adding or removing columns, creating or dropping indexes, or managing database version control. When working with migration directories, schema definition files, or database change scripts. When implementing backwards-compatible database changes for production deployments. When separating schema changes from data migrations.

Design reusable, composable UI components with single responsibility, clear interfaces, and proper state management. Use this skill when creating or refactoring React, Vue, Svelte, or other framework components. When defining component props, interfaces, or APIs. When managing component state or lifting state up to parent components. When building reusable UI elements like buttons, cards, forms, modals, or lists. When implementing component composition patterns. When working with component files (.jsx, .tsx, .vue, .svelte). When documenting component usage or creating component libraries.

Transform PBIs into ready status for AI execution. Use when refining backlog items, splitting stories, or ensuring Definition of Ready.

Design and implement RESTful API endpoints following REST principles, consistent naming conventions, and proper HTTP methods. Use this skill when creating or modifying API routes, controllers, or handlers in backend code. When implementing endpoint logic that handles HTTP requests (GET, POST, PUT, PATCH, DELETE). When working with API versioning, query parameters, or response formatting. When defining URL structures for resource-based endpoints. When setting up rate limiting or HTTP status code handling. When working with files like route definitions, controller files, API handler modules, or web framework configuration files.

Sync skill definitions to agent proxy files (.agent/workflows/skills.md and .github/copilot-instructions.md). Use after adding, removing, or modifying skills.

Define database models with clear naming, appropriate data types, proper constraints, and relationship definitions. Use this skill when creating or modifying ORM model files, database entity definitions, or data structure schemas. When defining table relationships, foreign keys, and cascade behaviors. When implementing model validation rules, timestamps, or indexes. When working with model files in frameworks like SQLAlchemy, Sequelize, ActiveRecord, SQLx, Prisma, or similar ORMs. When choosing appropriate data types for columns or establishing data integrity constraints (NOT NULL, UNIQUE, foreign keys).

Define technical specifications including tech stack, security, theme standards (from UX mockup), coding standards, and testing standards. Use when user asks to define tech specs, choose tech stack, or start Stage 7 after architecture.

Create Claude Code subagent configurations for .claude/agents/. Defines specialized agents with isolated contexts. Use when creating dedicated agents for code review, testing, or domain-specific tasks.

Create/Updates detailed user personas and prioritized user stories based on target users and market research. Use when user asks to create personas, define user stories, or start Stage 2 after market research or init-ideas.

List all tables in a database and show table structure (columns, types, constraints) for 30+ databases using DbCli. Use when user wants to explore database schema, see what tables exist, check table structure, or understand column definitions.

Create comprehensive Product Requirements Document (PRD) defining product behavior, functional and non-functional requirements. Use when user asks to create PRD, write requirements, or start Stage 4 after MVP definition.

TypeScript type safety including type guards and advanced type system features. **ALWAYS use when writing ANY TypeScript code (frontend AND backend)** to ensure strict type safety, avoid `any` types, and leverage the type system. Examples - "create function", "implement class", "define interface", "type guard", "discriminated union", "type narrowing", "conditional types", "handle unknown types".

Verify Definition of Done and acceptance criteria for Sprint increments. Use when completing sprints, running verification commands, or preparing for acceptance.

To search for symbols across Dart workspaces, resolve a symbol name to find definitions or catch spelling errors.

Define MVP scope, success metrics, and explicit out-of-scope items to focus on the smallest testable product. Use when user asks to define MVP, scope MVP, or start Stage 3 after personas.

Guide Sprint Planning in AI-Agentic Scrum. Use when selecting PBI, defining Sprint Goal, or breaking into subtasks.

Execute DDL (Data Definition Language) statements - CREATE, ALTER, DROP tables, indexes, views on 30+ databases using DbCli. CRITICAL - requires mandatory backup before DROP/ALTER operations. Use when user needs to create schema, modify structure, or drop database objects.