全部能力

Optimizes Pine Script for performance, user experience, and visual appeal on TradingView. Use when improving script speed, reducing load time, enhancing UI,…

订阅 AI 和技术类 RSS 订阅源，并使用成熟的 Python 工具（feedparser + sqlite3）将规范化后的元数据持久化存储到 SQLite。在添加订阅源时使用……

High-performance Kimi Delta Attention CUDA kernels built on CUTLASS for efficient recurrent state inference

Use when working with camera, photos, audio, haptics, ShazamKit, or Now Playing. Covers AVCaptureSession, PHPicker, PhotosPicker, AVFoundation, Core Haptics,…

当需要使用 gh CLI 处理 GitHub 开放 Pull Request 上的审查或 issue 评论时。

Comprehensive Tailscale VPN setup, configuration, and management for mesh networking, secure access, and zero-trust infrastructure. Covers installation, CLI…

Complete CI/CD guide for Capacitor apps covering GitHub Actions, GitLab CI, build automation, app signing, and deployment pipelines. Use this skill when users…

Professional video ad creation with Remotion — Instagram Reels (9:16), website explainers (16:9), and carousels (4:5). Use when creating video ads, animated…

USE FOR getting AI-generated POI text descriptions. Requires POI IDs obtained from web-search (with result_filter=locations). Returns markdown descriptions…

Run regression analyses in Stata with publication-ready output tables.

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing…

Processes meeting notes or transcripts to extract structured information. Use after meetings to quickly generate action items, capture decisions, and create follow-up tasks. Extracts: action items with owners, decisions made, key discussion points, follow-up tasks with priorities.

Apply when implementing retry logic, rate limit handling, or resilience patterns in VTEX API integrations. Covers VTEX rate limit headers…

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm,…

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with…

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

Use when the user asks to "research code", "how does X work", "where is Y defined", "who calls Z", "trace code flow", "find usages", "explore this library",…

Integrate the reusable CDF graph viewer (useGraphViewer) into a Flows app by copying the local code bundle. Use when embedding a graph visualization, adding a…

MUST be used when migrating an existing React app to Flows, or when no Flows auth is wired up. Detects classic vs Apps API flow from `app.json` `infra` field,…

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs,…