create-skill
Create a new Claude Code skill following official specifications. Use when creating custom skills, adding skill documentation, or setting up skill directories. Covers YAML frontmatter, markdown structure, and best practices.
Create a new Claude Code skill following official specifications. Use when creating custom skills, adding skill documentation, or setting up skill directories. Covers YAML frontmatter, markdown structure, and best practices.
Guide for creating Claude Code hooks in the liv-conventions plugin. This skill should be used when users want to create a new hook to validate, block, or guide Claude's tool usage (Write, Bash, Edit, etc.). Covers the HookHandler pattern, PreToolUseInput/Response APIs, glob matching, plugin.json configuration, and testing.
Create and maintain the interactive Streamlit playground for learning VRP-Toolkit through hands-on exploration. Use this skill when adding playground features, integrating new algorithms, or enhancing the learning experience.
Codex-native skill creator. Self-contained 4-phase methodology for creating production-ready Claude Code skills. Adapted from SkillCreator v3.2 for Codex agents with embedded methodology and simulated synthesis panel.
Ralph Loop integration patterns for iterative AI development. Use when starting Ralph loops, managing iterations, or recovering from context compaction. Covers TDD, debugging, context management, and memory persistence.
Use this agent when you need to design, implement, or optimize FastAPI backend applications. This includes API endpoint creation, database integration, authentication/authorization implementation, cloud deployment strategies, business logic architecture, performance optimization, and following FastAPI best practices.
TensorFlow Lite integration for on-device ML in React Native. Trigger: When working with object detection, image classification, or ML models.
Optimize training performance for Kaggle competitions. Use PROACTIVELY when training is slow, GPU memory issues occur, or user asks about performance tuning. Keywords: 遅い, 最適化, OOM, CUDA, batch_size, num_workers, 高速化, パフォーマンス
Embedding backends (InsightFace/PyTorch+ONNXRuntime vs TensorRT). Use when optimizing embedding throughput or debugging drift/fallbacks.
Optimize CoreML models for iOS and macOS deployment. Covers quantization, palettization, pruning, Neural Engine targeting, compute unit selection, and performance profiling. Use when converting ML models to CoreML, optimizing model size/latency, debugging Neural Engine issues, or benchmarking on-device inference.
Expert guidance for writing database migrations using golang-migrate for the mediaz SQLite database. Covers migration creation, testing, rollback capability, data preservation, and mediaz-specific patterns. Activates when users mention migrations, schema changes, database alterations, or golang-migrate.
Redis pub/sub messaging patterns and implementations. Use when implementing real-time messaging, event-driven architectures, notification systems, or message broadcasting with Redis pub/sub.
Caching patterns, TTL management, eviction policies for Redis implementations. Use when implementing cache-aside, write-through, write-back patterns, TTL management, or cache invalidation strategies.
Test game mechanics via SQL. Use game_* tools for gameplay flow.
Comprehensive guide to database transactions, ACID properties, isolation levels, locking, and distributed transactions.
Build FastAPI applications with SQLModel ORM and NEON serverless PostgreSQL. This skill should be used when creating database models, setting up NEON connections, building CRUD endpoints, defining relationships (1:1, 1:N, N:N), or adding pagination. Triggers: "create models", "setup database", "add CRUD", "SQLModel", "NEON", "database relationships", "connect to postgres", "add pagination".
Expertise in better-sqlite3 and schema management for the 5BulletMethod app.
Generate comprehensive database schemas with proper relations, migrations, and ORM/ODM models for PostgreSQL, MongoDB, and SQLite. Use when creating database schemas that integrate with FastAPI applications, including SQLAlchemy models for SQL databases, PyMongo/ODMantic models for MongoDB, Alembic migrations, and proper relationship definitions.
Prisma 5+ ORM with schema-first design, type-safe client, migrations, and database integrations (Supabase, PlanetScale, Neon). Use for TypeScript/JavaScript database access.
Database schema design patterns for SQL and NoSQL databases
Master Supabase patterns for migrations, RLS policies, pgvector, and authentication. Use when creating database schemas, writing migrations, implementing row-level security, setting up auth, or debugging Supabase issues. Triggers on "supabase migration", "RLS policy", "row level security", "pgvector", "supabase auth", "magic link".