Optimize prompt systems for cache efficiency, stable prefixes, fork-safe reuse, compact summarization, and instruction budgets.
Restructure an LLM call to maximize prompt-cache hit rate and add response/semantic caching — move the stable prefix (system prompt, instructions, few-shot, context) to the front…
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, resp — from…
Loaded when user builds with Anthropic API and needs to cut cost or latency via prompt caching. Covers TTL, cache breakpoints, stacking, invalidation, and measuring hit rate.
프롬프트 캐시 최적화 전략 — Dynamic Boundary 배치, 토큰 예산 관리, 정적/동적 영역 분리. Use when optimizing prompt structure, managing token budgets, or configuring CLAUDE.md layout for cache efficiency.
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for syst — from…
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability. — from Asymmetric-al/core
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production.
Versioniert alle Spalten- und Zeilenprompts mit semantischer Versions-ID — patch fuer Wortlautfeinheiten minor fuer geaenderte Antworttypen oder Ampelregeln major fuer geaenderte…
Analizza e migliora il codice di PunxFilm OS: code review, refactoring, bug fix, performance, nuove feature.
Progressive Web App development guidelines covering service workers, caching strategies, offline functionality, and installability
Progressive Web App development with Service Workers, offline support, and app-like behavior. Use for caching strategies, install prompts, push notifications, background sync.
Profile the execution time of a Python script using py-spy and visualize the result with speedscope. Use when the user wants to benchmark performance, find slow code paths, or…
QuickNode performance tuning — blockchain RPC and Web3 infrastructure integration. Use when working with QuickNode for blockchain development.
Expert in building blazing-fast reactive dashboards with comprehensive testing. Masters React performance patterns, testing strategies for async components, and real-world…
RealtimeSTT is a Python library for real-time speech-to-text with advanced voice activity detection, wake word activation, and instant transcription.
Use when the user references a PAST DECISION, choice, or rationale — "what did we decide about caching?", "why is X done this way?", "didn't we agree to use Y?", "remind me how we…
Redis - in-memory database, caching, pub/sub, sessions, rate limiting, data structures
Apply the Green IT "Network Efficiency" principle — every transferred and every stored byte costs energy across server, network, and device.
Regular expressions including pattern design, lookaheads, lookbehinds, performance optimization, and engine differences.
Expert in writing, debugging, and explaining regular expressions. Covers readable regex patterns, performance optimization, debugging techniques, and knowing when NOT to use…
Remove AI-generated code smells (slop) from branch changes or an explicit file list. Locks behavior with regression tests FIRST, then runs categorized cleanup via parallel `deep`…
Optimize Replit app performance: cold start, memory, Nix caching, and deployment speed. Use when experiencing slow startup, high memory usage, deployment timeouts, or optimizing…
Postgres + Supabase RLS 效能診斷與優化手冊。Use when 寫/改 RLS policy、 跑 EXPLAIN ANALYZE、排查 PGRST003 pool timeout、設計 index、 優化 pagination、使用者抱怨 API 變慢、或需要診斷 connection pool 問題時。涵蓋…
Optimiza políticas RLS de Supabase usando el patrón (select auth.uid()) para mejor performance. Usa cuando trabajes con RLS policies, auth.uid() reevaluación, o tareas 1.3 y 2.1…
Audits and optimizes the five global Claude layers (User Preferences, Styles, Global Memory, Skills, MCP Connectors) using the Global Layer Scorecard (six dimensions, anchored 1-5…
Rebalances context across Memory, Custom Instructions, knowledge files, and User Preferences in Claude Projects.
Produces structured XML session continuation documents for multi-session workflows. Captures all active work streams, decisions with rationale, uploaded file content, conversation…
MANDATORY when editing files matching ["api/src/**/*.py", "frontend/src/**/*.{ts,tsx}"]. Performance budgets, query discipline, caching, and rendering strategy
Add Axiom's Apple OS skills, agents, and commands so coding assistants can diagnose Xcode builds, Swift issues, crashes, logs, UI flows, and performance traces.
Use Reasonix when an operator wants a persistent terminal coding agent tuned for DeepSeek-style prefix caching, project memory, MCP-compatible plugins, and reviewable code-edit…
Structured investigation and troubleshooting for production incidents, build failures, performance issues, and mysterious bugs.
Execute load testing, stress testing, and performance benchmarking. Use when performing specialized testing.
Vercel Runtime Cache API guidance — ephemeral per-region key-value cache with tag-based invalidation. Shared across Functions, Routing Middleware, and Builds.
Profiles ccusage performance. Use when debugging slow Rust CLI commands, TypeScript package scripts, launchers, benchmarks, packaging hot paths, or branch-vs-main speed changes.
Optimize SalesLoft API performance with caching, pagination strategies, and connection pooling. Use when experiencing slow API responses, reducing latency for bulk operations, or…
Teaches how to use the sayt2 Python library to build search-as-you-type applications. Use when the user asks how to use sayt2, wants to build a search index, or needs help with…
Queue approved posts to scheduling tools (Buffer, Hypefury, Typefully, native schedulers) with platform-specific formatting, optimized posting times, media attachments, and…
Use first, before any writing, to stress-test whether a result clears Science's desk-reject filter — broad significance and general interest across disciplines.
Optimize SerpApi performance with caching, async searches, and result filtering. Use when reducing latency, minimizing credit consumption, or optimizing search throughput.
Service worker patterns for offline support, caching strategies, and PWA functionality. Use when implementing offline-first features, caching, or background sync.
Progressive Web App offline-first patterns — Service Worker lifecycle, caching strategies, background sync, and offline fallbacks for resilient web applications
End-to-end SGLang SOTA performance workflow. Use when a user names an LLM model and wants SGLang to match or beat the best observed vLLM and TensorRT-LLM serving performance by…
On-the-fly image optimization using Sharp (libvips Node.js bindings) with CDN-aware caching headers. Supports responsive srcset generation, AVIF/WebP transcoding, and blur…
Optimize Shopify API performance with GraphQL query cost reduction, bulk operations, caching strategies, and Storefront API for high-traffic storefronts.
Optimize agent skills for discoverability on ClawdHub/MoltHub. Use when improving search ranking, writing descriptions for semantic search, understanding how the registry indexes…
Search for Slack users by username with intelligent caching. Returns user IDs for DMs and maintains a local cache to avoid repeated API calls.
Construct optimized search URLs for major platforms and navigate to results with the browser. Replaces the built-in web_search tool for targeted, platform-specific searches.
Discover social media profiles for a person or company using search engines, platform-specific searches, and website extraction — returns canonical profile URLs across LinkedIn,…
Solid Router data APIs: query for caching/deduplication, createAsync for reactive promises, createAsyncStore for store-based async, revalidate for cache invalidation.
SolidStart service workers: registration, caching strategies, offline support, background sync, PWA features.
Optimize Speak API latency with audio preprocessing, response caching, and connection pooling. Use when implementing performance tuning, or managing Speak language learning…
Find and fix performance bottlenecks — N+1 queries, missing indexes, sync bottlenecks, caching gaps. Use when asked "why is this slow", "performance issue", "optimize this…
Analyze Swift Package Manager dependencies, package plugins, module variants, and CI-oriented build overhead that slow Xcode builds.
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries.
Analyzes and optimizes SQL queries across different data warehouse platforms (Snowflake, BigQuery, Redshift, Databricks) with platform-specific recommendations.
Analyze SQL Server execution plans for performance anti-patterns. Applies all 87 checks (S1–S27 statement-level, N1–N60 node-level).
Expert Site Reliability Engineer specializing in SLOs, error budgets, and reliability engineering practices.
Starlight - Full-featured documentation theme built on Astro for creating beautiful, accessible, high-performance documentation websites with built-in search, i18n, and c — from…
Starlight - Full-featured documentation theme built on Astro for creating beautiful, accessible, high-performance documentation websites with built-in search, i18n, and c — from…