Loading...
Loading...
Found 108 Skills
Recipes and configs for serving LLMs locally on RTX 3090 GPUs using vLLM, llama.cpp, and SGLang with OpenAI-compatible API
Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.
Transcribe audio to text using local whisper.cpp. Use when user wants to convert audio/video to text, get transcription, or speech-to-text.
Connect to local LLM endpoints (Ollama, llama.cpp, vLLM) with automatic provider fallback. Use when: (1) you need to run LLM inference locally for privacy/cost, (2) you want to use models not available via cloud APIs, (3) you need offline capability, (4) you want automatic fallback to cloud providers when local fails.
Use this when you need to run static analysis with cppcheck, clang-tidy, or GCC analyzer on embedded C/C++ code, or perform MISRA-C compliance checks.
Local-first AI coding agent powered by llama.cpp with zero tokens costs, Docker sandboxing, 20 built-in tools, LSP/Roslyn intelligence, and MCP integration
When the user wants to design, deploy, or measure Apple Custom Product Pages (CPP) — the alternate App Store product pages with different screenshots, preview videos, and promo text shown to users coming from specific URLs (typically ad campaigns or social posts). Use when the user mentions "Custom Product Page", "CPP", "alternate product page", "App Store URL variant", "ASA CPP", "campaign-specific landing page", "product page per audience", "App Store Connect CPP", "ppoUrl", "?cpp=" parameter, or "show different screenshots to different ad audiences". For App Store A/B tests on the default page, see ab-test-store-listing. For paid ad campaigns that route to CPPs, see apple-search-ads or ua-campaign.
Build and ship Unity 6 players: build settings and scenes, player/quality settings, the IL2CPP vs Mono scripting backend, managed code stripping, scripted BuildPipeline.BuildPlayer, and CI/headless builds. Use when configuring or automating a build, choosing a scripting backend, shrinking build size, or when the user mentions Unity build, player settings, IL2CPP, code stripping, or Addressables.
Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.
REQUIRED: After creating ANY .swift, .m, .mm, .c, .cpp, or .h file in a directory containing a .xcodeproj, you MUST run add_to_xcode.rb to register it with the project. Without this step, the file will NOT appear in Xcode and will NOT compile.
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT", "TTR", "Search Match", "exact match", "broad match", "CPP in ads", "ASA bidding", or "Search Ads budget". For Meta/Google UAC/TikTok paid UA, see ua-campaign.
Use when working with DataAsset, DataTable, soft reference, hard reference, TSoftObjectPtr, async loading, Asset Manager, StreamableManager, or game data structures in Unreal Engine. See references/asset-loading-patterns.md for async loading and StreamableManager patterns. See references/data-driven-design.md for data-driven gameplay architecture. For serialization, see ue-serialization-savegames. For C++ foundations, see ue-cpp-foundations.