區塊鏈

Guide for creating Claude Code hooks - user-defined shell commands that execute at lifecycle points. Use when the user wants to create, add, or configure a hook for Claude Code, including PreToolUse, PostToolUse, Notification, UserPromptSubmit, Stop, SubagentStop, PreCompact, SessionStart, or SessionEnd hooks.

TheGraph subgraph development with AssemblyScript handlers, schema definitions, and Matchstick testing. Triggers on subgraph, thegraph, graphql, mapping.ts.

Define database models and schemas with proper data types, constraints, relationships, and validation rules. Use this skill when creating or modifying database models, ORM entities, schema definitions, or data validation layers. When working on Prisma schema files, TypeORM entities, Drizzle schema definitions, Mongoose models, database model classes, files defining table structures and relationships, validation schemas for database entities, or files implementing data integrity constraints and cascading behaviors.

GitHub secret scanning configuration, push protection, custom pattern definitions, and response playbook for detected credentials in GitHub Actions workflows.

Generate production notes defining song structure, hooks, instrumentation hints, per-section tags, and mix parameters. Aligns with style spec and blueprint production guidelines. Use when creating arrangement, dynamics, and audio engineering guidance for composition and rendering.

Generates layered box-shadow elevation tokens for depth hierarchy. Use when creating elevation systems, card shadows, modal depth, or dark mode shadow variants. Outputs CSS, Tailwind, or JSON.

Technical Architect & Delivery Strategist who synthesizes product requirements and UI/UX designs into clear, actionable Technical Design Documents (TDD). Translates business flows into concrete system architecture and implementation plans. Defines end-to-end implementation paths with well-scoped phases and clear responsibility assignments. Specifies frontend-backend contracts (APIs, events, payloads, states, error models). Documents data models, integrations, security, and non-functional requirements. Explains happy paths and failure scenarios including edge cases, retries, fallbacks, and recovery. Enables confident implementation and smooth collaboration. Use when creating technical specifications, designing system architecture, planning implementation, defining APIs, or translating design into engineering work.

Design and build reusable, composable UI components following single responsibility principle with clear interfaces and proper state management. Use this skill when creating React components, Vue components, or other framework components, defining component props and interfaces, managing component state, building reusable UI elements, working with component files (*.tsx, *.jsx, *.vue, *.svelte, components/*, ui/*), implementing component composition patterns, encapsulating component logic, documenting component APIs, keeping state local or lifting it up when needed, designing component hierarchies, or refactoring monolithic components into smaller pieces. Apply this skill when building new components, refactoring existing component structures, reviewing component design patterns, or ensuring components are maintainable and reusable.

Use GitLab scripts instead of GitLab MCP for both read and write operations. Read operations (gitlab-mr-comments, gitlab-list-mrs) for fetching MR data. Write operations (gitlab-create-mr, gitlab-comment-mr, gitlab-inline-comment, gitlab-update-mr) for creating/updating MRs and posting inline code comments. Use when reviewing code, creating MRs, commenting on MRs, adding inline code review comments, updating MR metadata, listing MRs, or working with GitLab merge requests. Replaces 82 MCP functions (80k tokens) with lightweight bash scripts.

Personal Chief of Staff. Commands: /cos, /briefing, /eod, /review, /clarify, /translate, /taskspec, /meeting. Accesses server for tasks, calendar, emails, and memory. Always ask for token first!

Use when preparing to fine-tune an LLM for multi-turn conversations, before generating any training data. Triggers - starting a fine-tuning project, need to define evaluation criteria, designing conversation data generation.

LLM architecture, tokenization, transformers, and inference optimization. Use for understanding and working with language models.

Domain-specific configuration profiles for learning resource creation. Defines search strategies, special fields, terminology policies, and content structures for different academic domains: technology, history, science, arts, and general. Use when researcher or writer agents need domain-adapted behavior.

This skill should be used when working with GitHub pull requests, reviewing PRs, creating PRs, checking PR status, viewing PR comments, analyzing CI failures, or using gh CLI commands. Emphasizes token-efficient patterns using filters, file buffers, and targeted queries.

Use this skill for ANY database operations (schema changes, SQL, migrations, Supabase interactions). It contains EMBEDDED RULES to minimize token usage.

This skill should be used when developers need to scaffold complete decentralized applications on pod network, including smart contracts, Rust CLI tools, web frontends (React + Vite + viem), and testing infrastructure. Use when starting new DApps, building full-stack applications, or needing end-to-end project setup. Orchestrates pod-templating MCP server, frontend templates, and development tools for comprehensive DApp creation.

React Native authentication patterns for Expo apps. Use when implementing login flows, Google/Apple sign-in, token management, session handling, or debugging auth issues in Expo/React Native.

Token-optimized morning/nightly routine using caching and selective execution

Extract UI code, design tokens, and screenshots from Figma designs via desktop app. Use when implementing designs, building component libraries, or documenting design systems.

Complete knowledge domain for Cloudflare Workers AI - Run AI models on serverless GPUs across Cloudflare's global network.Use when: implementing AI inference on Workers, running LLM models, generating text/images with AI,configuring Workers AI bindings, implementing AI streaming, using AI Gateway, integrating withembeddings/RAG systems, or encountering "AI_ERROR", rate limit errors, model not found, tokenlimit exceeded, or neurons exceeded errors.Keywords: workers ai, cloudflare ai, ai bindings, llm workers, @cf/meta/llama, workers ai models,ai inference, cloudflare llm, ai streaming, text generation ai, ai embeddings, image generation ai,workers ai rag, ai gateway, llama workers, flux image generation, stable diffusion workers,vision models ai, ai chat completion, AI_ERROR, rate limit ai, model not found, token limit exceeded,neurons exceeded, ai quota exceeded, streaming failed, model unavailable, workers ai hono,ai gateway workers, vercel ai sdk workers, openai compatible workers, workers ai ve