Performance
Performance profiling and optimization
db-query-optimization
by KentoShimizu
"Query optimization workflow for reducing latency and resource cost through plan-aware rewrites and access-path improvements. Use when hot-path query behavior is the bottleneck; do not use for conceptual schema redesign without workload evidence."
agent-memory-mcp
by ngxtm
"A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions)."
performance-audit
by serkan-ozal
Analyze web and backend performance using Web Vitals, network timing, and Node.js metrics. Use when the user asks about page performance, load times, Core Web Vitals (LCP, CLS, INP), slow pages, backend bottlenecks, or SEO performance factors.
code-review-performance
by KentoShimizu
"Run performance-focused code review when changes may affect latency, throughput, or CPU/memory/I/O efficiency on critical paths. Use for merge decisions requiring explicit performance-risk findings; do not use for broad non-performance review scope."
agent-memory-systems
by ngxtm
"Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector s..."
swift-patterns
by efremidze
Review, refactor, or build SwiftUI features with correct state management, modern API usage, optimal view composition, navigation patterns, performance optimization, and testing best practices.
concurrency-patterns
by KentoShimizu
"Design and review concurrency strategy for shared state, coordination, and contention control. Use when parallel execution or async coordination introduces race/deadlock/liveness risk and explicit pattern selection is required; do not use for persistence schema or deployment topology decisions."
css-coder
by schalkneethling
CSS authoring guidance emphasizing web standards, accessibility, and performance. Use when writing, reviewing, or refactoring CSS. Provides patterns, snippets, and conventions that prioritize native CSS over frameworks, semantic structure, and maintainable code. Refer to references/patterns.md for specific patterns and snippets.
故人 (Guren)
by chenxing9200
故人 Skill - 以逝者的口吻继续陪伴，基于聊天记录重建人格与记忆
Agent Memory Systems
by mayurrathi
"Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector s..."
ai-agents-architect
by ngxtm
"Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool ..."
cost-optimization-cloud
by KentoShimizu
"Optimize cloud spend with explicit tradeoffs across cost, performance, and reliability. Use when spend or forecast misses budget targets and teams need concrete optimization actions without violating SLOs or compliance constraints; do not use for purely functional product behavior design."
agent-orchestration-multi-agent-optimize
by ngxtm
"Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability."
wechat-miniprogram-skill
by Gourdbaby
Expert guidelines for Native WeChat Mini Program development focusing on performance, code size, and native compatibility. Use when developing WeChat Mini Programs in native JavaScript.
wide-events
by front-depiction
Conceptual guide to wide events (canonical log lines) for observability. Use when thinking about instrumentation strategy, span annotations, or designing what context to capture.
chrome-devtools
by johnlindquist
Control and inspect Chrome browser using Chrome DevTools Protocol - navigate pages, debug network requests, analyze performance, take screenshots, interact with elements, and automate browser tasks.
pmf-survey
by wdavidturner
Use when asked to "PMF survey", "measure product-market fit", "40% rule", "Sean Ellis test", "Rahul Vohra method", or "how disappointed would you be". Helps quantify product-market fit and systematically improve it. The PMF Survey framework (created by Sean Ellis, popularized by Rahul Vohra at Superhuman) measures how disappointed users would be without your product and turns that data into a roadmap.
shape-up
by wdavidturner
Use when asked to "shape up", "run a shaping session", "set an appetite", "scope a project without estimates", "betting table", or "ship in fixed cycles". Helps teams escape estimate-driven development and Scrum fatigue. The Shape Up method (created by Ryan Singer at Basecamp/37signals) uses fixed time boxes, variable scope, and collaborative shaping to ship meaningful work predictably.
review
by johnlindquist
Centralizes persona-driven code reviews (Fowler, Torvalds, Carmack, React core, etc.) so Claude can pick or combine expert viewpoints when the user asks for a code review or perspective-specific critique.
radical-candor
by wdavidturner
Use when asked to "radical candor", "give feedback that cares", "have a difficult conversation", "challenge directly", "manage performance issues", or "give praise that lands". Helps deliver direct feedback while showing you care. The Radical Candor framework (created by Kim Scott) teaches how to challenge directly while caring personally.
memory-integration
by troykelly
Use to maintain context across sessions - integrates episodic-memory for conversation recall and mcp__memory knowledge graph for persistent facts
compare-options
by Agentient
Multi-expert comparison and ranking of options with structured deliberation. PROACTIVELY activate for: (1) decision making between alternatives, (2) trade-off analysis, (3) option evaluation, (4) vendor/tool comparison, (5) strategy selection. Triggers: "compare options", "evaluate alternatives", "rank options", "which should I choose", "compare these", "trade-off analysis", "decision between"
swiftui-expert
by SwiftyJourney
Write, review, or improve SwiftUI code following best practices
ask-questions
by ferueda
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.