資料庫

Apply quantization to reduce memory by 4-32x. Enable HNSW indexing for 150x faster search. Configure caching strategies and implement batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors. Deploy these optimizations to achieve 12,500x performance gains.

Cloud CLI patterns for GCP and AWS. Use when running bq queries, gcloud commands, aws commands, or making decisions about cloud services. Covers BigQuery cost optimization and operational best practices.

Use when synthesizing information from multiple sources (literature review, stakeholder feedback, research findings, data from different systems), creating or evaluating analogies for explanation or problem-solving (cross-domain transfer, "X is like Y", structural mapping), combining conflicting viewpoints into unified framework, identifying patterns across disparate sources, finding creative solutions by transferring principles from one domain to another, testing whether analogies hold (surface vs deep similarities), or when user mentions "synthesize", "combine sources", "analogy", "like", "similar to", "transfer from", "integrate findings", "what's it analogous to".

Handle Drizzle database schema changes safely. Generate and apply migrations, add tables and columns. Use when modifying database schema, adding tables, creating migrations, or making database changes.

Design, optimize, and migrate SQL databases with reliability and performance guardrails.

Use when problems involve interconnected components with feedback loops (reinforcing or balancing), delays, or emergent behavior where simple cause-effect thinking fails. Invoke when identifying leverage points for intervention (where to push for maximum effect with minimum effort), understanding why past solutions failed or had unintended consequences, analyzing system archetypes (fixes that fail, shifting the burden, tragedy of the commons, limits to growth, escalation), mapping stocks and flows (accumulations and rates of change), discovering feedback loop dynamics, finding root causes in complex adaptive systems, designing interventions that work with system structure rather than against it, or when user mentions systems thinking, leverage points, feedback loops, unintended consequences, system dynamics, causal loop diagrams, or complex systems. Apply to organizational systems (employee engagement, scaling challenges, productivity decline), product/technical systems (technical debt accumulation, performan

Gestión de Estado - React Query, Zustand, MMKV. Use when managing application state.

Run code in Codex fully isolated sandbox - network disabled, CWD only, Seatbelt/Docker isolation

Create AI learning plugins using AgentDBs 9 reinforcement learning algorithms. Train Decision Transformer, Q-Learning, SARSA, and Actor-Critic models. Deploy these plugins to build self-learning agents, implement RL workflows, and optimize agent behavior through experience. Apply offline RL for safe learning from logged data.

Query production PostgreSQL database with read-only credentials. Use for investigating data, debugging issues, or analyzing application state.

Plausible Analytics API for querying website statistics and managing sites. Use this skill to get visitor counts, pageviews, traffic sources, and manage analytics sites.

Address PR review feedback by making changes and replying to comments. Use when a PR has open review comments needing responses.

Reply to PR review comments using the correct GitHub API endpoint. Use when responding to inline code review feedback (not gh pr comment).

Manage PR review feedback loops with Gemini Code Assist. Use when pushing changes to a PR, iterating on review feedback, or monitoring CI/review status. Automatically falls back to Claude when Gemini is rate-limited.

Automated review rules for opal-frontend PRs. Use when asked to review code, run @codex review, or provide PR feedback; apply severity levels and the required comment format.

Query AWS CloudWatch logs for staging and production environments. Use for debugging errors, investigating incidents, or monitoring application behavior. PRIMARY - aws logs tail "/ecs/codel-staging" --follow --format short | grep -iE "error|exception"

Analyze and score jokes on the dad joke quality spectrum with multi-dimensional feedback on pun quality, groan factor, wholesomeness, and structure. Can also generate dad jokes.

Network isolation, allow/deny policy design, and TLS posture for sandboxes and CI with auditable enforcement.

This skill should be used when users want to route LLM requests to different AI providers (OpenAI, Grok/xAI, Groq, DeepSeek, OpenRouter) using SwiftOpenAI-CLI. Use this skill when users ask to "use grok", "ask grok", "use groq", "ask deepseek", or any similar request to query a specific LLM provider in agent mode.

Reusable memory patterns (short/long/episodic/semantic) implemented on AgentDB.