productivity▌

Use the bundled scripts inside this skill directory.

Systematically identify and fix performance bottlenecks across loading, rendering, animations, and bundle size. \n \n Covers five optimization areas: image optimization, JavaScript/CSS reduction, font loading, rendering performance, and animation efficiency \n Includes Core Web Vitals guidance (LCP, FID/INP, CLS) with specific thresholds and remediation strategies \n Provides code examples for common patterns: lazy loading, code splitting, layout thrashing prevention, GPU-accelerated animations,

PostgreSQL-backed GraphQL backend with auto-generated type-safe SDKs for web, mobile, and Flutter. \n \n Define GraphQL schema with @table decorators and relationships; Data Connect generates SQL and GraphQL operations automatically \n Write queries and mutations in GraphQL with filtering, ordering, pagination, and upsert support; transactions available via @transaction \n Secure operations with @auth levels (PUBLIC, USER, NO_ACCESS) and row-level controls using @check and @redact \n Generate ty

Check current Railway project status, services, and deployment state. \n \n Verifies Railway CLI installation and authentication before querying project status \n Returns project name, workspace, active environment, and list of services with their deployment status \n Displays active deployments and configured domains for the linked project \n Handles common errors: missing CLI, authentication failures, and unlinked projects with clear remediation steps \n

Systematic code review practices for constructive feedback, bug detection, and team knowledge sharing. \n \n Covers the complete review workflow: context gathering, high-level architecture assessment, line-by-line analysis, and decision-making with clear severity labeling (blocking, important, nit, suggestion) \n Includes language-specific patterns for Python, TypeScript, and JavaScript, plus specialized review techniques for security, testing, and architectural changes \n Provides templates, ch

Audit and fix animation performance issues including layout thrashing, compositor properties, and scroll-linked motion. \n \n Covers nine rule categories by priority: never patterns, mechanism selection, measurement batching, scroll-linked motion, paint optimization, layer promotion, blur/filter constraints, view transitions, and tool boundaries \n Provides file-level review mode that identifies violations with exact line quotes, impact explanation, and concrete code fixes \n Includes FLIP-style

Comprehensive quality review covering performance, accessibility, SEO, and best practices across 150+ checks. \n \n Analyzes code and projects across four audit categories: Performance (Core Web Vitals, resource optimization, loading strategy), Accessibility (perceivable, operable, understandable, robust), SEO (crawlability, on-page, technical), and Best Practices (security, standards, UX patterns) \n Categorizes findings by severity (Critical, High, Medium, Low) with specific, actionable recomm

Structured sprint retrospective facilitation with three proven formats and actionable outcome tracking. \n \n Offers three retrospective formats: Start-Stop-Continue, Mad-Sad-Glad, and 4Ls (Liked-Learned-Lacked-Longed For), each suited to different team dynamics and reflection styles \n Enforces blame-free discussion, specific action items with owners and due dates, and limits to 2-3 actions per retrospective to ensure follow-through \n Includes time-boxing guidance (1 hour), facilitator rotatio

ClinVar is NCBI's freely accessible archive of reports on relationships between human genetic variants and phenotypes, with supporting evidence. The database aggregates information about genomic variation and its relationship to human health, providing standardized variant classifications used in clinical genetics and research.

Prompt repetition technique that improves lightweight model accuracy by 67% across benchmarks. \n \n Auto-applies to claude-haiku, gemini-flash, and gpt-4o-mini; uses 2× repetition for general tasks and 3× for position-based queries \n Mitigates causal attention limitations by reprocessing the entire prompt, strengthening attention weights on key concepts without architectural changes \n Skips automatically when Chain-of-Thought patterns detected; includes duplicate-application prevention via ma