Loading...
Loading...
Found 2,257 Skills
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
Senior React Native and Expo engineer for building production-ready cross-platform mobile apps. Use when building React Native components, implementing navigation with Expo Router, optimizing list and scroll performance, working with animations via Reanimated, handling platform-specific code (iOS/Android), integrating native modules, or structuring Expo projects. Triggers on React Native, Expo, mobile app, iOS app, Android app, cross-platform, native module, FlatList, FlashList, LegendList, Reanimated, Expo Router, mobile performance, app store. Do NOT use for Flutter, web-only React, or backend Node.js tasks.
Use this skill when writing or debugging Grafana k6 load testing code. Provides access to the latest official k6 documentation including API references, examples, and best practices for creating performance tests.
Use when analyzing Xiaohongshu account data, interpreting performance metrics, making data-driven content decisions, or explaining what each metric means for account growth
Envoy Gateway production deployment — deployment modes, performance tuning, observability, operational guidance
Benchmark any agent skill to measure whether it actually improves performance. Use when the user wants to evaluate, test, or compare a skill against baseline, or when they mention "benchmark", "eval", "skill performance", or "does this skill help". Runs isolated eval sessions with and without the skill, grades outputs via layered grading (deterministic checks + LLM-as-judge), analyzes behavioral signals, and generates a comparison report with a USE / DON'T USE verdict.
Run Lighthouse CLI audits for websites and web applications from environment setup through result interpretation. Use when the user wants to audit performance, accessibility, SEO, best practices, PWA readiness, Core Web Vitals, Lighthouse CI, batch URL scans, localhost pages, or production pages. Trigger this skill for Lighthouse setup and troubleshooting in Linux or WSL, browser launcher failures such as "Cannot find Chrome" or "ECONNREFUSED 127.0.0.1", Chrome or Chromium detection issues, PageSpeed-style analysis requests, or any request to generate Lighthouse HTML and JSON reports with actionable recommendations.
AscendC Operator Design Completion - Assist users in completing operator architecture design, interface definition, and performance planning. Use this skill when users mention operator design, operator development, tiling strategy, memory planning, AscendC kernel design, two-level tiling, inter-core splitting, or intra-core splitting.
Analyze Huawei Ascend NPU profiling data to discover hidden performance anomalies and produce a detailed model architecture report reverse-engineered from profiling. Trigger on Ascend profiling traces, NPU bottlenecks, device idle gaps, host-device issues, kernel_details.csv / trace_view.json / op_summary / communication.json. Also trigger on "profiling", "step time", "device bubble", "underfeed", "host bound", "device bound", "AICPU", "wait anchor", "kernel gap", "Ascend performance", "model architecture", "layer structure", "forward pass", "model structure". Runs anomaly discovery (bubble detection, wait-anchor, AICPU exposure) alongside model architecture analysis (layer classification, per-layer sub-structure, communication pipeline). Outputs a separate Markdown architecture report alongside anomaly analysis.
Teaches async component loading in Vue for performance optimization. Use when you have heavy components that aren't needed on initial render and can be loaded on demand.
Comprehensive UI/UX quality audit covering visual hierarchy, accessibility, AI slop detection, typography, colour, layout, interaction states, responsive behaviour, performance, and microcopy. Produces severity-rated findings with actionable...
End-to-end SGLang SOTA performance workflow. Use when a user names an LLM model and wants SGLang to match or beat the best observed vLLM and TensorRT-LLM serving performance by searching each framework's best deployment command, benchmarking them fairly, profiling SGLang if it is slower, identifying kernel/overlap/fusion bottlenecks, patching SGLang code, and revalidating with real model runs.