productivity▌

28 ClickHouse best practices rules organized by schema design, query optimization, and data ingestion strategy. \n \n Covers three critical areas: primary key and data type selection (immutable design decisions), JOIN and query optimization, and insert batching with mutation avoidance \n Includes 28 rules prioritized by impact, with schema design and query optimization rules marked CRITICAL due to ClickHouse's columnar storage and sparse index mechanics \n Provides structured review procedures f

Alias: skill-creator \n This skill name is kept for compatibility. \n Use sentry-skills:skill-writer as the canonical skill for creating and updating skills. \n If invoked via skill-creator , run the same workflow and conventions documented in sentry-skills:skill-writer .

Create platform-specific social media posts that respect each platform's conventions, character limits, and audience expectations. Produces copy-paste-ready content.

Check for package-lock.json (npm), pnpm-lock.yaml (pnpm), yarn.lock (yarn), bun.lockb (bun). Use whichever is present. Default to npm if unclear.

Design and deploy analytics dashboards connecting BigQuery data to Looker Studio visualizations. \n \n Supports native BigQuery connector with custom SQL queries, scheduled queries for performance optimization, and multi-table joins for complex data transformations \n Includes F-pattern dashboard layout guidance with KPI tiles, trend charts, comparison visualizations, and interactive filters for user-driven exploration \n Provides performance optimization strategies using partition keys, data ex

Semantic search across web, research papers, and similar content discovery via Exa API. \n \n Five endpoint modes: semantic/keyword search, content extraction, similar page discovery, direct answers, and structured research with custom output schemas \n Supports search type selection (neural embeddings, fast keyword, deep comprehensive, or auto), category filtering (research papers, GitHub, news, PDFs, tweets, etc.), and date range constraints \n Two-phase architecture with main skill for intent

Control your existing Chrome browser via Playwright code snippets in a stateful local sandbox. \n \n Connects to your running Chrome instance instead of launching a new one, ideal for JavaScript-heavy sites like Instagram, Twitter, and pages with login walls or lazy-loaded content \n Executes Playwright code in a stateful sandbox with session management, context variables, and utility functions \n Requires reading full documentation via playwriter skill command before use to understand timeout c

Write high-engagement Twitter/X threads via inference.sh CLI.

Spring Boot development patterns and idioms tailored for Kotlin applications. \n \n Use primary constructors for dependency injection, data class for DTOs, and the kotlin-jpa plugin to automatically open entity classes without boilerplate. \n Organize code by feature/domain rather than layer; leverage Kotlin's null-safety to clearly define optional vs. required entity fields. \n Apply @ConfigurationProperties with data class for type-safe, immutable configuration; use application.yml and Spring

Browser-based visual whiteboard for sketching ideas and collaborating with Copilot through drawings and sticky notes. \n \n Opens an interactive canvas on the user's desktop where they can draw, sketch, and add sticky notes, then share back to Copilot via a \"Share with Copilot\" button \n Reads whiteboard content through PNG snapshots (visual interpretation of sketches, diagrams, and layout) and optional JSON clipboard data (precise text from sticky notes and labels) \n Designed for non-technic