性能
性能分析与优化
forge-quick-test
fwehrling
FORGE Quick QA — Zero-config testing with automatic framework detection. Lightweight alternative to /forge-verify. Usage: /forge-quick-test
masm-rust-constant-parity
tomevault-io
Use when changing a numeric or string constant in Rust or MASM that has a counterpart on the other side — keep the two definitions from drifting apart.
browser-use
Jackiexiao
自动进行浏览器交互，以进行Web测试、表单填充、屏幕截图和数据提取。当用户需要浏览网站、与网页交互、填写表单、截屏或从网页中提取信息时使用。
citadel-low-latency-systems
copyleftdev
Build trading systems in the style of Citadel Securities, the world's largest market maker. Emphasizes ultra-low latency, deterministic execution, kernel bypass networking, and high-frequency trading infrastructure. Use when building latency-critical systems, market making engines, or high-performance trading platforms.
note
Nomik94
컴팩션에서 살아남는 영구 메모 시스템. 긴 세션에서 중요 컨텍스트 손실 방지.
chrome-devtools
artivilla
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests.
tonejs
HongmingWang-Rabbit
Best practices for Tone.js - programmatic music and audio synthesis in the browser using the Web Audio API. Covers synths, effects, sequencing, timing, samples, signals, patterns, MIDI, visualization, browser audio, music emotion mapping, rhythm/beat construction, music theory utilities, generative/algorithmic composition, performance optimization, offline rendering/recording, and React/Next.js integration.
graphiti
aeonbridge
Comprehensive skill for Graphiti and Zep - temporal knowledge graph framework for AI agents with dynamic context engineering
desktop-app-dev
YPYT1
Desktop App Dev subagent
vercel-react-best-practices
yldgio
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.
paid-ads-guide
nowork-studio
Explain NotFair's paid-ads skills, installation, platform boundaries, account connections, and current product capabilities. Use for questions about how NotFair works, what it supports, how to install or connect it, plans or limits, or paid-media troubleshooting that is not an account-performance request.
react-rerender-auditor
handxr
Audit React components for unnecessary re-renders, inline object/array/function creation in JSX props, Context.Provider with unstable values, useEffect anti-patterns (async callbacks, setState loops, missing deps), expensive unmemoized render operations, and component complexity issues. Use when reviewing React performance, debugging slow components, auditing a codebase for re-render issues, or when a user asks to check their React code for performance problems, find unnecessary re-renders, optimize components, or audit hook usage. Triggers on tasks involving .jsx/.tsx/.js/.ts files with React components.
agent-builder
YPYT1
Build high-performing OpenClaw agents end-to-end. Use when you want to design a new agent (persona + operating rules) and generate the required OpenClaw workspace files (SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md, optional MEMORY.md + memory/YYYY-MM-DD.md). Also use to iterate on an existing agent’s behavior, guardrails, autonomy model, heartbeat plan, and skill roster.
upsell-sequence-assembler
tonyflo79
Assemble all upsell sequence pieces (order bump + upsell + downsell) into a cohesive sequence document with cross-page narrative validation. Use after U1-U3 have produced their individual pieces. This is an ASSEMBLY + VALIDATION skill, not a writing skill — it combines existing pieces, validates threading between them, verifies pricing cascade compliance, and catches inconsistencies that individual skill validations miss. Produces assembled sequence document plus E0 handoff for email integration. Trigger when users mention assembling the upsell funnel, compiling upsell pages, sequence validation, or building the complete post-purchase flow. Requires U0-U3 outputs.
wandb-experiment-memory
wilfred-dore
Query Weights & Biases experiment history to retrieve past optimization runs, compare configurations, and inform the next optimization decision. Use this skill when asked to review past AI optimization experiments, find the best configuration tried so far, understand what has already been explored, or suggest the next experiment to run based on W&B history.
javascript-best-practices
jcastillotx
JavaScript coding standards and best practices. This skill should be used when writing, reviewing, or refactoring JavaScript code. Triggers on tasks involving vanilla JavaScript, DOM manipulation, async operations, or performance optimization.
timeline-skill
tower1229
Factual timeline layer. Given a time range, retrieves or generates structured episode facts from memory and session history. Returns a TimelineWindow JSON object. Writes new episodes to disk (Append-Only).
expression-coach
ethansage0618
一个用于生成语言表达组织训练场景的技能。当您需要系统性地练习在不同情境下的口语沟通能力时，请使用此技能。
generate-jest-unit-tests
Olino3
Intelligent Jest unit test generation for Angular components, services, and more with Socratic planning and project-specific memory.
cost-optimization
TriNgo0108
Optimize cloud costs through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
data-quality
masterkram
Diagnose and fix data quality problems in datasets. Use when working with dirty data, finding duplicates, handling missing values, detecting outliers/anomalies, validating constraints (functional dependencies, referential integrity), profiling datasets, or cleaning data for analysis or ML. Covers the full data quality lifecycle - define, detect, clean, measure.
web-perf-ux
october-academy
Web application performance and UX optimization through automated analysis. Use when developers need to (1) measure and diagnose performance issues using Lighthouse and Core Web Vitals, (2) identify root causes of LCP, CLS, INP problems, (3) analyze UX pain points like layout shifts or slow interactivity, (4) generate actionable improvement plans with concrete code-level fixes. Triggers on requests like "analyze performance", "why is my page slow", "fix CLS issues", "optimize web vitals", "run Lighthouse", "performance audit", or "improve page speed".
character-profile-generator
BizShuk
This skill generates detailed virtual character profiles based on a standardized template. Use this skill when a user wants to create or refine a character for stories, roleplay, or virtual assistants. It guides the user through a clarifying dialogue to establish core personality, behavior, and background before generating the final profile.
svelte
NikiSkaarup
Guide Svelte 5 component development with runes, props, and performance-aware patterns.