技能创建器
skill-creator
创建、改进和评估自定义技能，把专业流程转化为可重复使用的 AI 能力。
THE SKILLS DIRECTORY
探索全部技能.
一个技能，一个新的可能。找到适合你的 AI 工作流。
React 最佳实践
vercel-react-best-practices
优化 React 与 Next.js 应用的渲染、加载和运行性能。
diagnosing-bugs
diagnosing-bugs
【开发与工程】Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
auto-perf-optimize
auto-perf-optimize
【数据与研究】Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
cpu-profile-analysis
cpu-profile-analysis
【数据与研究】Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-*.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating user timing marks.
benchmark
benchmark
【开发与工程】Web performance regression detection. (gstack)
qa-acceptance
qa-acceptance
【效率与协作】Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
triton-kernel-writing
triton-kernel-writing
【开发与工程】Write or review Triton kernels for vLLM, with practical guidance for generated-code inspection, launch grids, indexing, specialization, tuning, and representative performance validation.
GroqCloud Automation
GroqCloud Automation
【效率与协作】Automate AI inference, chat completions, audio translation, and TTS voice management through GroqCloud's high-performance API via Composio
google_search_console-automation
google_search_console-automation
【开发与工程】Automate Google Search Console tasks via Rube MCP (Composio): search performance, URL inspection, sitemaps, and indexing status. Always search tools first for current schemas.
langsmith-fetch
langsmith-fetch
【开发与工程】Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.
frontendchecklist
frontendchecklist
【设计与创意】Review frontend code and live pages against the Front-End Checklist (380+ rules for accessibility, performance, SEO, security, HTML, CSS, JavaScript, images, i18n, privacy, testing) using the `frontendchecklist` CLI. Use when writing, reviewing, or shipping HTML/CSS/JS/JSX/TSX/Vue/Svelte/Astro code, before a commit or PR, or when asked to audit a pub…
animation-performance
animation-performance
【开发与工程】Use when reviewing stylesheets, component styles, and responsive behavior related to Use transform and opacity for animations. Check the rendered layout across breakpoints and interaction states before proposing a fix.
back-forward-cache
back-forward-cache
【开发与工程】Use when reviewing navigation performance, browser lifecycle events, or resume-from-memory behavior. Check the actual browser lifecycle and restore path, not only static code patterns.
browser-required
browser-required
【数据与研究】Use when auditing slow page loads, heavy assets, or rendering delays related to Perform browser-based performance audits. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.
dom-performance
dom-performance
【开发与工程】Use when reviewing scripts, client components, bundles, or runtime behavior related to Minimize costly DOM read/write operations. Inspect both source code and the browser execution path so fixes target the real bottleneck or bug. In React, repeated requestAnimationFrame-driven state updates across multiple mounted components are a valid performance s…
performance-budget
performance-budget
【数据与研究】Use when reviewing CI configuration, bundle analysis workflows, or pull requests that add dependencies and assets. Distinguish bundle-size budgets from runtime budgets such as Lighthouse or Core Web Vitals so teams can enforce both.
performance-resource-hints
performance-resource-hints
【数据与研究】Use when auditing slow page loads, heavy assets, or rendering delays related to Use resource hints for faster loading. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.
18 / 5880