性能
性能分析与优化
moai-formats-data
modu-ai
Data format specialist covering TOON encoding, JSON/YAML optimization, serialization patterns, and data validation for modern applications. Use when optimizing data for LLM transmission, implementing high-performance serialization, validating data schemas, or converting between data formats.
pseo-performance
lisbeth718
Optimize a programmatic SEO application for Core Web Vitals, build performance, and scalability at 1000+ pages, including static generation, incremental regeneration, bundle optimization, and caching. Use when builds are slow, pages are large, Core Web Vitals scores are poor, or when scaling to many pages causes performance issues.
iterative-academic-writer
iamseungpil
Iteratively write academic documents (paper sections, research proposals, technical documents) with quality improvement loop. Uses academic-planner for structure design and academic-reviewer for quality evaluation. Ensures no hallucinations through fact verification.
code-reviewer
paulund
Use when reviewing code, pull requests, or auditing code quality and best practices.
survey-paper
iamseungpil
arxiv 논문을 체계적으로 분석하여 Obsidian 서베이 노트를 생성한다. arxiv 페이지/ID를 입력받아 (1) Paper Digest 스타일 핵심 요약, (2) Iterative Writing 원칙 기반 세부 정리, (3) 플로우 다이어그램 포함 Obsidian 페이지를 생성한다. TRIGGERS: "논문 서베이", "paper survey", "arxiv 정리", "논문 노트", "서베이 페이지", "survey note"
note
ReinaMacCredy
Manage persistent working memory. Add priority context, manual notes, or working memory that persists across sessions.
loom-plan-writer
cosmix
REQUIRED skill for creating Loom execution plans. Designs DAG-based plans with mandatory knowledge-bootstrap and integration-verify bookends, parallel subagent execution within stages, and concurrent worktree stages for maximum throughput. Trigger keywords: loom, plan, stage, worktree, orchestration, parallel execution, parallel stages, concurrent execution, knowledge-bootstrap, integration-verify, acceptance criteria, signal, handoff, execution graph, dag, dependencies, loom plan, create plan, write plan, execution plan, orchestration plan, stage dependencies, parallel subagents, functional verification, wiring verification, smoke test.
browser-debugging
aj-geddes
Debug client-side issues using browser developer tools. Identify JavaScript errors, styling issues, and performance problems in the browser.
vercel-react-best-practices
guanyang
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
memory-systems
guanyang
Guides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem), and designs persistence architectures for cross-session knowledge retention. Use when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph for agents", "track entities over time", "add long-term memory", "choose a memory framework", or mentions temporal knowledge graphs, vector stores, entity memory, or memory benchmarks (LoCoMo, LongMemEval).
context-optimization
guanyang
This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.
evaluation
guanyang
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.
multi-agent-patterns
guanyang
This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.
supabase-postgres-best-practices
guanyang
Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.
context-degradation
guanyang
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.
k8s-cost
rohitg00
Optimize Kubernetes costs through resource right-sizing, unused resource detection, and cluster efficiency analysis. Use for cost optimization, resource analysis, and capacity planning.
performance-testing
cosmix
Performance testing and load testing expertise including k6, locust, JMeter, Gatling, artillery, API load testing, database query optimization, benchmarking strategies, profiling techniques, metrics analysis (p95/p99 latency, throughput, RPS), performance budgets, and bottleneck identification. Use when implementing load tests, stress tests, spike tests, soak tests, analyzing system behavior under concurrent users, measuring saturation points, or optimizing application performance under load. Trigger keywords: performance testing, load testing, stress testing, stress test, load test, performance test, k6, locust, JMeter, Gatling, artillery, benchmark, benchmarking, profiling, latency, throughput, RPS, requests per second, concurrent users, virtual users, percentile, p95, p99, p50, median latency, saturation, bottleneck, performance budget, API load testing, database performance, query optimization, slow queries, scalability testing, capacity planning, response time, error rate, apdex.
performance-trace-guide
proflead
Guide collection and analysis of performance traces. Use when a mid-level developer needs to diagnose slowness.
ai-analyzer
huifer
AI驱动的综合健康分析系统，整合多维度健康数据、识别异常模式、预测健康风险、提供个性化建议。支持智能问答和AI健康报告生成。
emergency-card
huifer
生成紧急情况下快速访问的医疗信息摘要卡片。当用户需要旅行、就诊准备、紧急情况或询问"紧急信息"、"医疗卡片"、"急救信息"时使用此技能。提取关键信息（过敏、用药、急症、植入物），支持多格式输出（JSON、文本、二维码），用于急救或快速就医。
emergency-card
huifer
生成紧急情况下快速访问的医疗信息摘要卡片。当用户需要旅行、就诊准备、紧急情况或询问"紧急信息"、"医疗卡片"、"急救信息"时使用此技能。提取关键信息（过敏、用药、急症、植入物），支持多格式输出（JSON、文本、二维码），用于急救或快速就医。
tcm-constitution-analyzer
huifer
分析中医体质数据、识别体质类型、评估体质特征,并提供个性化养生建议。支持与营养、运动、睡眠等健康数据的关联分析。
口腔健康分析技能
huifer
分析口腔健康数据、识别口腔问题模式、评估口腔健康状况、提供个性化口腔健康建议。支持与营养、慢性病、用药等其他健康数据的关联分析。
Vite 构建产物体积优化
TencentBlueKing
使用 Rollup Visualizer 分析产物，并通过拆包 (Code Splitting) 和 Tree Shaking 减少首屏体积。