區塊鏈

Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or validating DeFi protocols.

Deep code intelligence via Narsil MCP providing 76 tools for security scanning (OWASP, CWE, taint analysis), call graph analysis (CFG, DFG, callers/callees), structural queries (symbols, definitions, references), and supply chain security (SBOM, license compliance). Accessed via Code Mode for token efficiency.

Access cached codebase documentation via MCP. Use when searching for project architecture, agent definitions, skill documentation, or deployment procedures. Provides 90% token savings vs. reading files directly.

Calculate cryptographic hashes (MD5, SHA1, SHA256, SHA512) for text and files. Compare hashes, verify integrity, and batch process directories.

Design and implement domain entities, DTOs, and data transfer objects following the project's domain-driven design patterns. Use this skill when creating or modifying domain entity classes in shared/domain/, DTO classes in features/{feature}/dto/, entity mappers in shared/mapper/, or shared type interfaces in packages/shared/types/src/dto/. This includes implementing the static factory pattern (Entity.create()), writing DTO validation decorators (class-validator), creating response DTOs with static from() methods, and defining shared interfaces that API DTOs must implement. Apply when working with @imkdw-dev/types package interfaces, ArticleContent value objects, or any file ending in .dto.ts, domain entities, or mapper classes.

Build video conferencing integrations using Digital Samba's API and SDK. Use when creating meeting rooms, embedding video calls, generating participant tokens, managing recordings, or integrating real-time collaboration features. Triggers include "Digital Samba", "video conferencing API", "embed video calls", "meeting room integration", "WebRTC iframe", "participant tokens".

Apply when implementing API authentication: JWT tokens, session management, API keys, and auth middleware. Follows JWT Best Current Practices (RFC 8725).

Node.js platform functions for the East language. Use when writing East programs that need Console I/O, FileSystem operations, HTTP Fetch requests, Cryptography, Time operations, Path manipulation, Random number generation, or Testing. Triggers for: (1) Writing East programs with @elaraai/east-node-std, (2) Using platform functions like Console.log, FileSystem.readFile, Fetch.get, Crypto.uuid, Time.now, Path.join, Random.normal, (3) Testing East code with describeEast and Assert.

Expert guidance for Drizzle ORM including schema definition, queries, relations, migrations, TypeScript integration with SQLite/PostgreSQL, and Drizzle Studio. Use this when working with type-safe database operations, schema management, or ORM queries.

Execute approved technical implementation plans with verification checkpoints. This skill should be used when implementing pre-approved development plans, feature implementations, or technical specifications that have defined phases, success criteria, and verification steps. Triggers on requests like "implement the plan", "execute the implementation plan", or when given a path to a plan file.

Defines accessibility requirements for UI elements including semantic markup, ARIA attributes, focus management, and screen reader support. Updates the "アクセシビリティ" section in screen spec.md.

Security fix patterns for cryptographic vulnerabilities (weak algorithms, insecure randomness, TLS issues). Provides language-specific secure implementations.

"Use Gemini CLI when processing images, PDFs, large files, needing 1M+ token context, or requiring Gemini's strong reasoning and fine-grained domain knowledge.

Frontend-backend API contracts, routes, clients, and type definitions. Handles API endpoint definitions, request/response types, route configuration, and cross-stack integration. Use when working with API endpoints, request/response types, route definitions, or frontend-backend integration, or when user mentions API design, adding endpoints, type mismatches, API contracts, REST endpoints, client integration, "404 Not Found" errors, "Type error" in API calls, or route configuration issues.

Enforces Head Shakers Cloudinary media conventions when working with image uploads, URL generation, transformations, social sharing images, and photo management components. This skill covers the complete media workflow including CloudinaryService operations, URL utilities, CldImage/CldUploadWidget components, path organization, type definitions, and Sentry integration.

Use this skill when creating or refining Claude Code skill definitions. Skills are model-invoked capabilities that Claude activates autonomously based on context. Helps design focused skills with discovery-optimized descriptions, proper directory structures, and supporting resources. Automatically invoked when user requests "create a skill", "make a capability", "add autonomous behavior", or mentions skill development. Ensures skills follow Anthropic specifications with clear activation triggers.

IntelliFill authentication flow patterns using Supabase Auth, JWT tokens, and backend auth mode

Add bot protection with Turnstile (CAPTCHA alternative). Use when: protecting forms, securing login/signup, preventing spam, migrating from reCAPTCHA, integrating with React/Next.js/Hono, implementing E2E tests, or debugging CSP errors, token validation failures, or error codes 100*/300*/600*.

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

Build RAG systems, semantic search, and document clustering with Gemini embeddings API (gemini-embedding-001). Generate 768-3072 dimension embeddings for vector search, integrate with Cloudflare Vectorize, and use 8 task types (RETRIEVAL_QUERY, RETRIEVAL_DOCUMENT, SEMANTIC_SIMILARITY) for optimized retrieval. Use when: implementing vector search with Google embeddings, building retrieval-augmented generation systems, creating semantic search features, clustering documents by meaning, integrating embeddings with Cloudflare Vectorize, optimizing dimension sizes (128-3072), or troubleshooting dimension mismatch errors, incorrect task type selections, rate limit issues (100 RPM free tier), vector normalization mistakes, or text truncation errors (2,048 token limit).