Loading...
Loading...
Found 423 Skills
Fast, accurate code search for AI agents using ~98% fewer tokens than grep+read. Indexes any local or remote repository in under a second (~250ms on CPU, no GPU or API key needed). Supports natural-language and symbol queries, semantic similar-code discovery, and MCP server integration for Claude Code, Codex, Cursor, and OpenCode. Python library available for programmatic use. Triggers on: semble, code search, semantic code search, semble search, token-efficient search, find code, code search mcp, agent code search, semble find-related, semble savings.
Verify whether a set of specific PC hardware items are compatible with each other using Newegg's real PC Builder compatibility engine. Use when the user has parts in mind (model names or Newegg item numbers) and asks whether they work together — "do these work together", "will this GPU work with my PSU", "can this RAM go on this motherboard", "is this build compatible", "这些硬件兼容吗", "这个显卡能配我的电源吗", "我想升级显卡，原来的电源够不够". Trigger when the user names two or more specific hardware items and wants a verdict. Do NOT use for from-scratch build recommendations where the user has not picked specific parts.
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
C++ Reinforcement Learning best practices using libtorch (PyTorch C++ frontend) and modern C++17/20. Use when: - Implementing RL algorithms in C++ for performance-critical applications - Building production RL systems with libtorch - Creating replay buffers and experience storage - Optimizing RL training with GPU acceleration - Deploying RL models with ONNX Runtime
Self-hosted ML coding practice platform with 68 problems covering Transformers, diffusion, RLHF, and more — instant browser feedback, no GPU required.
SSH into host `h100_sglang`, enter Docker container `sglang_bbuf`, work in `/sgl-workspace/sglang`, and use the ready H100 remote environment for SGLang development and validation. Use when a task needs remote CUDA work, GPU-backed smoke tests, diffusion checks, or a safe remote copy instead of local-only execution.
Profile a target (script, process, GPU, memory, interconnect) using external tools and code instrumentation. Produces structured performance reports with actionable recommendations. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.
Analyze host/CPU overhead in TensorRT-LLM inference from nsys traces. Detect whether host overhead is the bottleneck using GPU idle ratio, host prep exposed ratio, and per-phase evidence. For regressions, isolate forward steps via allreduce/NVTX patterns, compare host operation breakdowns across versions, and identify scheduling or request-management overhead. Supports optional inter-kernel gap, eager-vs-graph, pattern mapping, and multi-rank straggler drill-down. Use standalone or within perf-analysis. Triggers: host overhead, inter-step gap, scheduling overhead, forward step isolation, nsys iteration analysis, NVTX breakdown, request management overhead, GPU idle, host bottleneck, host prep exposed, inter-kernel gap, bubble analysis, graph coverage, eager kernel, rank imbalance, straggler detection.
AWS Startups reference content — Activate FAQ, credits guide, programs, partner offers, sample architectures, and hundreds of learn articles spanning generative AI, cloud architecture, cost optimization, security, fundraising, go-to-market, and real-world startup case studies. Use when the user asks factual questions about AWS Activate (eligibility, credits, programs, providers), wants a sample architecture or solution guide, or needs an AWS-curated learn article on a specific startup topic. For copy-paste AI prompts (RAG chatbot, MVP scaffold, security baseline, GPU quota, etc.), see the prompt-library-for-startups skill. Do not use for: account-specific lookups (credits balance, Activate membership status, application status), real-time event listings beyond the events stub, or content not present in the bundled `references/` tree.
three.js Scene graph root object, linear Fog and exponential FogExp2, Scene.background for solid colors or textures, and high-level environment background concepts that tie to PMREM and loaders in other skills. Use when configuring world container, atmospheric fog, or background; for HDR env map file loading use threejs-loaders; for GPU texture settings after load use threejs-textures; for tone mapping use threejs-renderers.
three.js textures: Texture, DataTexture, CubeTexture, CompressedTexture variants, DepthTexture, VideoTexture, CanvasTexture, 3D/array textures, Source; sampling parameters, mipmaps, anisotropy, wrap/mag/min filters; PMREMGenerator in Extras for environment map prefiltering. Use when configuring GPU texture objects and PMREM; for Draco/KTX2 transcoder file paths use threejs-loaders; for material map slots use threejs-materials; for output color pipeline use threejs-renderers.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.