去中心化金融

This skill provides comprehensive knowledge for working with the Anthropic Claude Agent SDK. It should be used when building autonomous AI agents, creating multi-step reasoning workflows, orchestrating specialized subagents, integrating custom tools and MCP servers, or implementing production-ready agentic systems with Claude Code's capabilities.Use when building coding agents, SRE systems, security auditors, incident responders, code review bots, or any autonomous system that requires programmatic interaction with Claude Code CLI, persistent sessions, tool orchestration, and fine-grained permission control.Keywords: claude agent sdk, @anthropic-ai/claude-agent-sdk, query(), createSdkMcpServer, AgentDefinition, tool(), claude subagents, mcp servers, autonomous agents, agentic loops, session management, permissionMode, canUseTool, multi-agent orchestration, settingSources, CLI not found, context length exceeded

Generate and validate JSON Schema definitions. Use when asked to create schemas, validate JSON structure, or document API payloads.

Fluid typography and spacing tokens using Utopia.fyi with cqi (container query inline) units. Reference for the exact type steps and space tokens defined in this project.

Add new states or transitions to Bob The Skull's state machine. Use when adding new states, defining transitions, implementing state behavior, or modifying state machine logic.

Generates RBS type signatures from Ruby source files. Triggers when creating type definitions, adding types to Ruby code, or generating .rbs files for classes/modules without existing RBS signatures.

Define the holistic testing approach across functional, non-functional, and automation layers for the initiative.

Collaborative design refinement that transforms rough ideas into fully-formed specifications through Socratic questioning. Explores alternatives, validates incrementally, and presents designs in digestible chunks for feedback. Use before writing code or implementation plans when requirements are unclear or multiple approaches exist. Do NOT use when requirements are already well-defined, you're implementing a known pattern, or making small changes - proceed directly to implementation instead.

Creates well-formed tasks following a template that engineers can implement. Use when creating tasks, defining work items, creating tasks from PRD, breaking down features, or converting requirements into actionable tasks.

Document placement rules, visibility protocols, and timeline test (before-code vs after-code). Defines where documentation belongs (dev/docs/ vs coordination/), documentation-first PR protocol, and phase artifact placement. Critical for documentation organization and visibility.

Generates a research-grade Product Requirements Document (PRD) defining problems, goals, scope, constraints, and success criteria. Use when creating or updating a PRD for a product or major initiative.

Automatically applies when creating data models for API responses and validation. Uses Pydantic BaseModel with validators, field definitions, and proper serialization.

Implement robust error handling with user-friendly messages, proper exception types, and graceful degradation. Use this skill when writing try-catch blocks, defining custom exceptions, or handling failures from external services. When implementing retry strategies, cleaning up resources, or designing centralized error handling. When validating preconditions or failing fast with clear error messages.

Adds static typing to JavaScript with TypeScript including type annotations, interfaces, generics, and advanced type utilities. Use when setting up TypeScript projects, defining types, creating generic utilities, or debugging type errors.

Provides guidance on creating custom error types with thiserror, including proper derive macros, error messages, and source error chaining. Activates when users define error enums or work with thiserror.

This skill should be used when translating a spec into code using parallel subagents. Use when the orchestrator invokes the implement phase or when executing a well-defined implementation plan.

Document placement rules, visibility protocols, and timeline test (before-code vs after-code). Defines where documentation belongs (dev/docs/ vs coordination/), documentation-first PR protocol, and phase artifact placement. Critical for documentation organization and visibility.

Generate GraphQL schema definition files (SDL) with types, queries, mutations, subscriptions, and resolvers for API development. Triggers on "create GraphQL schema", "generate GraphQL types", "GraphQL API for", "SDL schema".

BDD specifications using Gherkin syntax, feature files, step definitions

Defines project-wide code conventions for magic number elimination, constant usage, performance optimization, and coordinate system separation. Use when implementing, testing, or reviewing code to ensure consistency across the codebase.

Intelligently choose between semantic and text search based on query intent. Automatically selects the best search mode (semantic for concepts, text for exact terms, symbols for definitions) and provides relevant results. Use when user wants to find code.