Databases

Complete guide to ActiveRecord query optimization, associations, scopes, and PostgreSQL-specific patterns. Use this skill when writing database queries, designing model associations, creating migrations, optimizing query performance, or debugging N+1 queries and grouping errors.

Ask Gemini 3.0 Pro Preview for design advice, spatial awareness analysis, and visual/design questions. Use when you need expert design feedback, want to review design intentions or changes, need spatial understanding of layouts, or want a second opinion on visual aesthetics. Gemini excels at design critique, layout analysis, and understanding visual relationships. Supports up to 10 images per request for comparison.

Comprehensive toolkit for developing with the CocoIndex library. Use when users need to create data transformation pipelines (flows), write custom functions, or operate flows via CLI or API. Covers building ETL workflows for AI data processing, including embedding documents into vector databases, building knowledge graphs, creating search indexes, or processing data streams with incremental updates.

Converts app ideas into shippable MVPs by providing structured product planning, technical guidance, and decision-making support focused on rapid validation. Use when the user shares an app idea, needs help scoping an MVP, wants to generate PRDs or starter prompts for Claude Code, needs product decisions during a build, or when they need to be kept focused on shipping rather than over-engineering. Also use for questions about tech stack choices (Next.js/Supabase/Vercel), feature prioritization, or avoiding common early-stage mistakes.

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.

Master Redis replication - master-replica setup, Sentinel for HA, failover handling, and read scaling patterns

Delete a snapshot. Requires authentication. Use for Agentuity cloud platform operations

SEMO 패키지 피드백 이슈 수집 및 리스트업. Use when (1) "피드백 확인", "피드백 있는지", (2) "유저 피드백 체크", (3) SEMO 관련 open 이슈 조회.

Master OPAL window functions for row-relative calculations, rankings, and moving aggregates. Covers lag(), lead(), row_number(), rank(), dense_rank(), moving averages, first(), and last(). Use when comparing rows to neighbors, ranking within partitions, calculating rate of change, or computing time-based moving windows. CRITICAL - OPAL uses window() function wrapper, NOT SQL OVER clause.

Build production-grade FastAPI backends with SQLModel, Pydantic, and JWT authentication. Use this skill when building REST APIs, integrating with Neon PostgreSQL, implementing Better Auth JWT verification, or creating CRUD endpoints. Includes patterns for audit logging, worker/agent parity, and OpenAPI documentation.

Validate completed implementation against plan tasks and acceptance criteria. Sixth phase of research-discussion-specification-plan-implement-review workflow. Use when: (1) Implementation phase is complete, (2) User wants validation before merging/shipping, (3) Quality gate check needed after implementation. Reviews ALL plan tasks for implementation correctness, test adequacy, and code quality. Produces structured feedback (approve, request changes, or comments) - does NOT fix code.

Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like DPO.

Schema design, migrations, query optimization

Get snapshot details. Requires authentication. Use for Agentuity cloud platform operations

Feature module pattern organizing domain logic into queries, mutations, and actions. Use when implementing data fetching with filters, API mutations with loading states, business logic with UI feedback, or organizing domain-specific code.

Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims. | Sử dụng khi review code, đánh giá code, xem xét PR, pull request, cải thiện chất lượng code.

Expert in photo content recognition, intelligent curation, and quality filtering. Specializes in face/animal/place recognition, perceptual hashing for de-duplication, screenshot/meme detection, burst photo selection, and quick indexing strategies. Activate on 'face recognition', 'face clustering', 'perceptual hash', 'near-duplicate', 'burst photo', 'screenshot detection', 'photo curation', 'photo indexing', 'NSFW detection', 'pet recognition', 'DINOHash', 'HDBSCAN faces'. NOT for GPS-based location clustering (use event-detection-temporal-intelligence-expert), color palette extraction (use color-theory-palette-harmony-expert), semantic image-text matching (use clip-aware-embeddings), or video analysis/frame extraction.

Top 1% development standard for OC Pipeline and federal-grade construction software. Use when Bill asks to build features, fix bugs, write code, create components, or do any software development work. Activates for requests involving Supabase, Vercel, React, Node.js, database work, API development, or any coding tasks for OC Pipeline or related projects.

Redis and Upstash Vector integration patterns for rate-limiting, vector search, embeddings, and memory systems. Use when implementing caching, rate-limiting, or semantic search features.

Expert in API integration with React Query, SWR, RTK Query, REST/GraphQL clients, WebSocket real-time, optimistic updates, caching strategies, and error handling