性能
性能分析与优化
vercel-react-best-practices
ocrbase-hq
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.
Environment-Specific Bash Mastery
Sounder25
Generate optimized scripts that utilize the specific hardware (cores, GPU, OS) of the execution environment.
langgraph-tutor
timothywarner-org
Expert skill for teaching LangGraph - the orchestration framework for stateful AI agents. Covers StateGraph, nodes, edges, conditional routing, checkpointing, human-in-the-loop, and multi-agent patterns. Invoke when users ask about LangGraph, building agent graphs, state machines for LLMs, or workflow orchestration. Keywords: langgraph, state graph, agent workflow, orchestration, multi-agent, checkpointing, human-in-the-loop.
spatial-thinking
dylantarre
Use when animation involves depth, perspective, volume, or three-dimensional awareness—camera moves, character positioning, environmental interaction, or maintaining consistent spatial relationships.
meta-dialogue-v2
gongebb
Advanced metacognitive dialogue skill with cross-session accumulation. Builds a meta-profile of hypotheses about your thinking patterns, detects when patterns break (more valuable than confirmation), and includes frame-health safeguards against self-negation and direction errors. Hypothesis-first approach — challenges before confirms. 세션 간 축적형 메타인지 대화 스킬. 가설 기반 메타 프로필을 누적하고, 패턴 깨짐을 감지하며, 자기부정/방향오류 안전장치를 포함합니다. 확인보다 도전을 먼저 하는 대화 방식.
timing-mastery
dylantarre
Use when determining how fast or slow motion should be—pacing action sequences, dramatic pauses, comedic beats, or any situation where the duration of movement matters.
naturalistic-motion
dylantarre
Use when animation should feel organic and lifelike—creature animation, realistic characters, nature elements, or any motion that needs to breathe with authentic living quality.
exaggerated-clarity
dylantarre
Use when motion needs to read clearly and powerfully—broad comedy, action highlights, important story beats, or any moment that must unmistakably communicate to the audience.
memory-defrag
basicmachines-co
"Defragment and reorganize agent memory files: split bloated files, merge duplicates, remove stale information, and restructure the memory hierarchy. Use when memory files have grown unwieldy, contain redundancies, or need reorganization. Run periodically (weekly) or on demand."
memory-ingest
basicmachines-co
"Process unstructured external input (meeting transcripts, conversation logs, pasted documents) into structured Basic Memory entities. Extracts entities, searches for existing matches, proposes new entities with approval, creates notes with observations and relations, and captures action items."
performance-optimization
srstomp
Use when analyzing performance issues, optimizing slow pages or APIs, setting up load testing (k6, Artillery), implementing caching, reducing bundle sizes, establishing performance budgets, or profiling bottlenecks. Covers frontend (Core Web Vitals, rendering, bundle size) and backend (query optimization, caching, async patterns) optimization.
memory-lifecycle
basicmachines-co
"Manage entity status transitions in Basic Memory: archive completed work, move notes between status folders, update frontmatter, and handle edge cases. Use when marking items complete, archiving old entities, or managing any folder-based status workflow."
memory-reflect
basicmachines-co
"Sleep-time memory reflection: review recent conversations and daily notes, extract insights, and consolidate into long-term memory. Use when triggered by cron, heartbeat, or explicit request to reflect on recent activity. Runs as background processing to improve memory quality over time."
memory-notes
basicmachines-co
"How to write well-structured Basic Memory notes: frontmatter, observations with semantic categories, relations with wiki-links, and best practices for building a rich knowledge graph. Use when creating or improving notes."
agent-assistant
nahisaho
Agent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agents Trigger terms: agent stuck, loop detected, session memory, agent learning, condense memory, stuck detection, agent memory, session learnings, extraction Use when: User reports agent is stuck, looping, or needs memory/learning management
quality-assurance
nahisaho
Copilot agent that assists with comprehensive QA strategy and test planning to ensure product quality through systematic testing and quality metrics Trigger terms: QA, quality assurance, test strategy, QA plan, quality metrics, test planning, quality gates, acceptance testing, regression testing Use when: User requests involve quality assurance tasks.
performance-optimizer
nahisaho
Copilot agent that assists with performance analysis, bottleneck detection, optimization strategies, and benchmarking Trigger terms: performance optimization, performance tuning, profiling, benchmark, bottleneck analysis, scalability, latency optimization, memory optimization, query optimization Use when: User requests involve performance optimizer tasks.
frontend-async-best-practices
sergiodxa
Async/await and Promise optimization guidelines. Use when writing, reviewing, or refactoring asynchronous code to eliminate waterfalls and maximize parallelism. Triggers on tasks involving data fetching, loaders, actions, or Promise handling.
Animation Principles - Absolute Beginner
dylantarre
Use when someone has never heard of animation principles, needs the simplest explanation possible, or is a complete newcomer to animation
swiftui-expert-skill
third774
Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, modern APIs, Swift concurrency, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.
qlora
itsmostafa
Memory-efficient fine-tuning with 4-bit quantization and LoRA adapters. Use when fine-tuning large models (7B+) on consumer GPUs, when VRAM is limited, or when standard LoRA still exceeds memory. Builds on the lora skill.
lora
itsmostafa
Parameter-efficient fine-tuning with Low-Rank Adaptation (LoRA). Use when fine-tuning large language models with limited GPU memory, creating task-specific adapters, or when you need to train multiple specialized models from a single base.
aptos-gas-optimization
raintree-technology
Aptos gas optimization expert for Move smart contracts. Covers storage costs, execution efficiency, inline functions, aggregators for parallel execution, Table vs SmartTable vs vector tradeoffs, event optimization, struct packing, and gas profiling tools.
VCR Skill — AI Agent Reference
coltonbatts
Always validate with check before rendering. It catches schema errors, expression errors, and missing references instantly without the cost of GPU initialization.