productivity▌

Expert patterns for Neon serverless Postgres, branching, connection pooling, and ORM integration. \n \n Covers Prisma and Drizzle ORM setup with Neon, including dual connection string configuration (pooled vs. direct) for migrations and application queries \n Explains PgBouncer connection pooling limits (10K concurrent connections) and reserved superuser connections \n Provides guidance on choosing between Neon's neon-http driver (single queries) and neon-serverless driver (transactions and WebS

Use this skill when you need to run or design asc commands for App Store Connect.

Before dispatching, analyze the task systematically. Think through step by step:

You are a browser automation expert who has debugged thousands of flaky tests and built scrapers that run for years without breaking. You've seen the evolution from Selenium to Puppeteer to Playwright and understand exactly when each tool shines.

Guides GEO/AEO strategy for AI search visibility. GEO optimizes content for ChatGPT, Claude, Perplexity, and AI search summaries (Google AI Overviews, Bing Copilot, Yandex Search with AI)—getting cited in AI-generated answers rather than ranking in traditional SERPs. See serp-features for AI search as SERP features; featured-snippet for snippet optimization that overlaps with AI Overviews.

Post, like, retweet, and manage Twitter/X accounts via CLI commands. \n \n Nine app commands covering tweet posting with media, liking, retweeting, DM sending, user following, and profile retrieval \n Supports media attachment through URLs, enabling workflows that combine image or video generation with social posting \n Requires inference.sh CLI authentication; integrates with other inference.sh skills for end-to-end content creation and distribution pipelines \n

Technical rigor in code review: receiving feedback critically, requesting systematic reviews, and verifying before any completion claims. \n \n Three core practices: receiving feedback with technical evaluation over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before status claims \n Includes decision tree and protocols for handling feedback from human partners versus external reviewers, with explicit rules against performative

Memory architecture for agents: retrieval strategies that determine whether agents remember or forget. \n \n Covers five memory types: short-term (context window), long-term (vector stores), working memory, episodic memory, and semantic memory, each suited to different information patterns \n Emphasizes retrieval as the core challenge; provides chunking strategies, embedding quality guidance, and metadata filtering to surface the right memories at decision time \n Includes anti-patterns like sto

PREREQUISITE: Read ../gws-shared/SKILL.md for auth, global flags, and security rules. If missing, run gws generate-skills to create it.

Comprehensive performance optimization guide for Postgres, maintained by Supabase. Contains rules across 8 categories, prioritized by impact to guide automated query optimization and schema design.