ORM

Analyze Rust compilation profiling data using DuckDB to find performance bottlenecks, trait explosions, and monomorphization issues. Use after generating chrome_profiler.json with crox.

Generates UI components and feedback forms. Use when user mentions コンポーネント, component, UI, ヒーロー, hero, フォーム, form, フィードバック, feedback, 問い合わせ. Do NOT load for: 認証機能, バックエンド実装, データベース操作, ビジネスロジック.

Spatial indexing and retrieval system for finding information within memorypalaces using multi-modal search.Triggers: knowledge search, find information, locate concept, recall, spatialquery, cross-reference, discovery, memory retrieval, pr review search,past decisions, review patternsUse when: searching for stored knowledge, cross-referencing concepts,discovering connections, retrieving from palaces, finding past PR decisionsDO NOT use when: creating new palace structures - use memory-palace-architect.DO NOT use when: processing new external resources - use knowledge-intake.Consult this skill when searching or navigating stored knowledge.

Create and manage database migrations with reversible changes, proper naming conventions, and zero-downtime deployment strategies. Use this skill when creating database migration files, modifying schema, adding or removing tables/columns, managing indexes, or handling data migrations. Apply when working with migration files (e.g., db/migrate/, migrations/, alembic/, sequelize migrations), schema changes, database versioning, rollback implementations, or when you need to ensure backwards compatibility during deployments. Use for any task involving database structure changes, index creation, constraint modifications, or data transformation scripts.

Write secure, optimized database queries using parameterized queries, eager loading to prevent N+1 problems, and strategic indexing for performance. Use this skill when writing SQL queries, ORM queries, database interactions, or optimizing data fetching logic. Apply when working with query files, repository patterns, data access layers, SQL statements, ORM methods (ActiveRecord, Sequelize, Prisma queries), JOIN operations, WHERE clauses, preventing SQL injection, implementing eager loading or includes, adding query timeouts, wrapping operations in transactions, or caching expensive queries. Use for any task involving database reads, writes, complex queries, query optimization, or data fetching performance.

Implement comprehensive validation with server-side enforcement, client-side UX feedback, early failure, specific error messages, allowlists over blocklists, type checking, input sanitization, and consistent validation across all entry points. Use this skill when implementing validation logic in forms, API endpoints, data models, user inputs, or any data processing. Apply when validating form inputs, API request parameters, database model fields, implementing client-side validation for user experience, enforcing server-side validation for security, sanitizing user input to prevent injection attacks, checking data types and formats, validating business rules, or providing field-specific error messages. Use for any task involving input validation, data integrity checks, security validation, or user input processing.

Define database models with clear naming, appropriate data types, constraints, relationships, and validation at multiple layers. Use this skill when creating or modifying database model files, ORM classes, schema definitions, or data model relationships. Apply when working with model files (e.g., models.py, models/, ActiveRecord classes, Prisma schema, Sequelize models), defining table structures, setting up foreign keys and relationships, configuring cascade behaviors, implementing model validations, adding timestamps, or working with database constraints (NOT NULL, UNIQUE, foreign keys). Use for any task involving data integrity enforcement, relationship definitions, or model-level data validation.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

Mobile UX patterns for touch gestures, haptic feedback, accessibility, and platform-native interactions. Essential for building truly mobile-friendly apps.

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Creates a fully functional Drizzle ORM setup with a provisioned Neon database. Installs dependencies, provisions database credentials, configures connections, generates schemas, and runs migrations. Results in working code that can immediately connect to and query the database. Use when creating new projects with Drizzle, adding ORM to existing applications, or modifying database schemas.

Use Neon serverless Postgres with branching, connection pooling, and instant scalability for modern applications with Prisma or Drizzle ORM integration. Use when setting up serverless Postgres databases, implementing database branching for preview environments, configuring connection pooling, optimizing for serverless cold starts, using Prisma with Neon, implementing database migrations, scaling databases automatically, or building applications on Vercel/Netlify with Postgres.

Plan and execute database migrations, data transformations, and system migrations safely with rollback strategies and data integrity validation. Use when migrating databases, transforming data schemas, moving between database systems, implementing versioned migrations, handling data transformations, ensuring data integrity, or planning zero-downtime migrations.

Build efficient React applications using Next.js Server Components that render on the server, reducing client bundle size, improving performance, and enabling direct database access. Use when fetching data server-side, reducing JavaScript bundle size, accessing databases directly in components, implementing streaming with Suspense, creating layouts that only render once, optimizing Core Web Vitals, or building SEO-friendly applications with server-first architecture.

Systematically review pull requests, feature implementations, and code changes to ensure quality, maintainability, security, and adherence to best practices. Use when reviewing code before merging, conducting peer reviews, performing self-reviews, auditing code quality, checking for security vulnerabilities, ensuring consistent coding standards, verifying test coverage, assessing performance implications, evaluating architectural decisions, or providing constructive feedback to improve team code quality.

Implement React Server Actions in Next.js 14+ for secure, progressively enhanced form handling and server mutations without API routes. Use when handling form submissions, performing server-side mutations, implementing progressive enhancement, creating actions that work without JavaScript, validating data on the server, revalidating cached data after mutations, handling file uploads server-side, implementing optimistic UI updates, or building forms that gracefully degrade without client-side JavaScript.

Use when validating and casting data with Ecto changesets including field validation, constraints, nested changesets, and data transformation. Use for ensuring data integrity before database operations.