Loading...
Loading...
Found 2,445 Skills
CUDA kernel development, debugging, and performance optimization for Claude Code. Use when writing, debugging, or optimizing CUDA code, GPU kernels, or parallel algorithms. Covers non-interactive profiling with nsys/ncu, debugging with cuda-gdb/compute-sanitizer, binary inspection with cuobjdump, and performance analysis workflows. Triggers on CUDA, GPU programming, kernel optimization, nsys, ncu, cuda-gdb, compute-sanitizer, PTX, GPU profiling, parallel performance.
Execute iterative refinement workflows with validation loops until quality criteria are met. Use for test-fix cycles, code quality improvement, performance optimization, or any task requiring repeated action-validate-improve cycles.
Principal backend engineering intelligence for Node.js runtime systems. Actions: plan, design, build, implement, review, fix, optimize, refactor, debug, secure, scale backend code and architectures. Focus: correctness, reliability, performance, security, observability, scalability, operability, cost.
PostgreSQL 16 database documentation. Use for SQL queries, indexes, transactions, JSON operations, full-text search, and performance tuning.
Analyze code quality, security, performance, and architecture. Use when user asks to analyze code, review codebase health, or identify issues.
Audit and improve SwiftUI runtime performance. Use for slow rendering, janky scrolling, high CPU, memory usage, excessive view updates, layout thrash, body evaluation cost, identity churn, view lifetime issues, lazy loading, Instruments profiling guidance, and performance audit requests.
Zoomd platform help — mobile user acquisition across 600+ media sources, mobile DSP with real-time bidding, creator-generated content (CGC), Albert.ai autonomous campaign optimization, and Digital 360 performance marketing. Use when app install costs (CPI/CPA) are too high and you need multi-channel optimization, you want to manage UA campaigns across Meta/Google/TikTok/programmatic from one dashboard, mobile DSP campaigns aren't scaling or hitting ROAS targets, you need creator content for app marketing, Albert.ai isn't optimizing as expected, or you're comparing Zoomd with other mobile UA platforms. Do NOT use for web retargeting or display ads (use /sales-retargeting or /sales-adroll), B2B account-based advertising (use /sales-b2b-advertising).
Scores completed OKR sets at cycle close with KR-level scoring per the canonical OKR type enum (committed | aspirational | learning | operational_health | compliance_or_safety), committed-vs-aspirational interpretation, evidence quality assessment, learning synthesis, and next-cycle recommendations. Refuses to retroactively change targets or shrink committed scope, average away guardrail KRs, treat 0.7 as success for committed or compliance_or_safety KRs, equate effort with impact, or use scores for individual performance. Hands off to iterate-lessons-log, iterate-retrospective, define-hypothesis, measure-dashboard-requirements, measure-instrumentation-spec, and foundation-okr-writer.
Use when investigating slow queries, analyzing execution plans, or optimizing database performance. Invoke for index design, query rewrites, configuration tuning, partitioning strategies, lock contention resolution.
Senior graphics programmer specializing in Three.js, WebGL, shaders, and performance optimizationUse when "three.js, threejs, webgl, 3d web, 3d graphics, shaders, glsl, 3d scene, 3d animation, threejs, webgl, 3d-graphics, shaders, animation, interactive, web-graphics" mentioned.
Comprehensive guide for this Neovim configuration - a modular, performance-optimized Lua-based IDE. Use when configuring plugins, adding keybindings, setting up LSP servers, debugging, or extending the configuration. Covers lazy.nvim, 82+ plugins across 9 categories, DAP debugging, AI integrations, and performance optimization.
Generates high-quality, non-generic UI designs with a focus on performance, progressive disclosure, and distinctive aesthetics.