缓存
缓存策略与实现
context-optimization
ken-cavanagh-glean
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.
moai-baas-vercel-ext
AJBcoding
Enterprise Vercel Edge Platform with AI-powered modern deployment, Context7 integration, and intelligent edge orchestration for scalable web applications
moai-context7-integration
AJBcoding
"Enhanced context7 integration with AI-powered features"
turborepo-caching
EngineerWithAI
Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.
tree-of-thoughts
kimasplund
Advanced recursive reasoning methodology for systematic problem-solving. Use when you need to explore multiple solution approaches in parallel, evaluate them rigorously, and recursively deepen the best path. Ideal for complex decisions with trade-offs, optimization problems, or strategic planning. Example: "Should we use microservices or monolith?" → Apply ToT to spawn 5+ architectural approaches, evaluate each systematically, recurse on the winner.
Cache Invalidation
AmnadTaowsoam
'> "There are only two hard things in Computer Science: cache invalidation
buffer-overflow
tangjunyi23
Buffer overflow vulnerability hunting in IoT embedded binaries. Use when reverse-engineering ARM/MIPS/x86 binaries for stack-based or heap-based overflow vulnerabilities, analyzing unsafe memory operations (strcpy, sprintf, gets, memcpy), checking binary protections (NX, ASLR, canary), or building overflow PoCs for embedded targets.
state-management
mrsknetwork
Designs and implements state management architecture for both frontend (global client state, server cache, URL state) and backend (Redis caching, session management, distributed locks). Use when a user needs to share data across components without prop drilling, cache expensive API responses, sync state to the URL, manage Redis, or prevent race conditions in concurrent server operations. Trigger when user mentions "global state", "Zustand", "Redux", "React Query", "caching", "Redis", "session", "why does my data disappear on page refresh", or "how do I share state across pages".
query-sub-agent
knowlet
專責處理 IDF (Information Display Frame) 類型的需求。讀取規格目錄結構，生成/審查 Query Side 設計與實作。支援 Java、TypeScript、Go 多語言。
resolve-kwai-cdn-url
httprunner
Resolve Kuaishou (快手 / Kwai) share links or share text into video CDN URLs. Use for single links, share text, or CSV inputs when output must be JSONL with CDNURL/error_msg. Prefer videodl (videofetch); fall back to GraphQL/mobile-page extraction with cookies when needed.
commerce-blueprint
gravito-framework
Deep expertise in E-commerce domain logic (Cart, Checkout, SKU). Trigger this when building shopping features on top of MVC or ADR.
system-architecture
mrsknetwork
Designs high-level system architectures, produces C4 model diagrams, writes Architectural Decision Records (ADRs), and defines Non-Functional Requirements (NFRs). Use when planning a new application, migrating systems, evaluating trade-offs between architectural patterns, or documenting a key technical decision.
wayback-range
Mearman
Show the archive time span for a URL from the Wayback Machine. Use when the user wants to see both the oldest and newest captures, the archive range, or how long a URL has been archived.
npms-compare
Mearman
Compare multiple npm packages side-by-side using NPMS.io quality scores. Use when the user asks to compare packages, evaluate alternatives, or choose between multiple options.
npm-info
Mearman
Get detailed metadata for an npm package including versions, dependencies, maintainers, and repository information. Use when the user asks for package details, version history, or package metadata.
npms-analyze
Mearman
Analyze npm package quality using NPMS.io scores for quality, popularity, and maintenance. Use when the user asks for package quality analysis, NPMS scores, or package evaluation metrics.
reading-onchain-state
SanctifiedOps
Patterns for reading Solana on-chain state efficiently: getAccountInfo, getProgramAccounts, caching, and reactivity. Use for frontends and services.
wayback-list
Mearman
List Wayback Machine snapshots for a URL. Use when the user wants to see archive history, view all snapshots, find older versions, or browse archived copies of a webpage.
wayback-frequency
Mearman
Analyze Wayback Machine capture frequency and rate for a URL. Use when the user wants to see how often a URL is archived, capture statistics, or archive density over time.
cloud-architect
gaebalai
Copilot agent for cloud architecture design, AWS/Azure/GCP configuration, IaC code generation (Terraform/Bicep), and cost optimization Trigger terms: cloud architecture, AWS, Azure, GCP, cloud infrastructure, IaC, Terraform, CloudFormation, cloud design, serverless, cloud migration Use when: User requests involve cloud architect tasks.
php-performance
peixotorms
Use when optimizing PHP performance, configuring OPcache or JIT, setting up caching (Redis, Memcached), tuning database queries (PDO), choosing faster function alternatives, managing memory, or profiling. Covers OPcache configuration, opcache.validate_timestamps, preload, preloading, php.ini tuning, memory_limit, realpath_cache, JIT tracing, micro-optimizations, function choices, loops, casting, memory management, connection pooling, lazy loading, N+1 query problem, SPL data structures, SplFixedArray, PDO best practices, caching patterns, Xdebug profiler, and Blackfire production profiling.
wayback-screenshot
Mearman
Retrieve screenshots from the Wayback Machine. Use when the user wants to see how a webpage looked, get a visual snapshot, find archived screenshots, or view historical page appearance.
markdown-html-ppt
skygreen2001
将 Markdown 文档或文本转换为演示文稿。首先通过 reveal.js 转换为交互式 HTML PPT，然后可选择性地转换为 PowerPoint 文件。支持丰富的 Markdown 语法（加粗、斜体、代码、引用、代码块），5个精美主题，智能分页算法。输出格式可选：HTML（reveal.js）或 PowerPoint（.pptx）。版本：v2.4.0
wp-performance
peixotorms
Use when optimizing WordPress performance, debugging slow queries, configuring caching, reviewing database code, or preparing for high traffic. Covers WP_Query optimization (get_posts, meta_query, tax_query, no_found_rows, update_post_meta_cache, fields), object cache (wp_cache_get, wp_cache_set, Redis, Memcached), transients (set_transient, get_transient), autoload options, Query Monitor, Debug Bar, slow query profiling, anti-patterns (posts_per_page -1, query_posts, N+1), WP-CLI profiling, asset loading strategies, and platform-specific guidance.