312 个 · 按相关度排序
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
中文简介正在准备中。当前显示原文说明。
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package.
中文简介正在准备中。当前显示原文说明。
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
中文简介正在准备中。当前显示原文说明。
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with 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, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
中文简介正在准备中。当前显示原文说明。
Use for real-time performance and multimedia operator work: technical show-control execution (signal flows, OSC/DMX, MCP orchestration, hardware limits) for tools like grandMA3, Resolume, Unreal, Rhino, Vectorworks, and Adobe MCP.
中文简介正在准备中。当前显示原文说明。
Access security tokens and smart cards using CryptoTokenKit. Use when building token driver extensions with TKTokenDriver and TKToken, communicating with smart cards via TKSmartCard, implementing certificate-based authentication, managing token sessions, or integrating hardware security tokens with the system keychain.
中文简介正在准备中。当前显示原文说明。
Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.
中文简介正在准备中。当前显示原文说明。
Quantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence, quantum optics, or cavity QED. Best for physics research, open system dynamics, and educational simulations. NOT for circuit-based quantum computing—use qiskit, cirq, or pennylane for quantum algorithms and hardware execution.
中文简介正在准备中。当前显示原文说明。
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
中文简介正在准备中。当前显示原文说明。
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
中文简介正在准备中。当前显示原文说明。
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
中文简介正在准备中。当前显示原文说明。
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
中文简介正在准备中。当前显示原文说明。
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
中文简介正在准备中。当前显示原文说明。
Generate a single-file industrial-archive product landing page (Nordic museum aesthetic, hash-routed detail pages). Takes a natural-language description of one or more "exhibit-style" products (objects, tools, hardware, watches, kitchenware, lighting, audio, instruments, anything with a designed/forged/restrained quality); outputs ONE working .html file. Visitors see a black-framed cover that flips between exhibits, sidebar index, side meta column (material/origin/year/dimension), and click any exhibit → full detail page (giant italic title, spec table, hero image, lead + 3 prose paragraphs, gallery, prev/next). Runs in BOTH Claude Code (writes to ~/Desktop) and GLM / online chat (outputs HTML inline). Trigger: "做个工业风产品落地页", "做克制之物风格的展品页", "industrial-archive-gen ...", or when user drags this skill folder into chat asking for a product page in the Nordic-industrial archive style.
中文简介正在准备中。当前显示原文说明。
Generate a single-file product landing page with a layered ASCII cosmos hero (rotating ASCII planet, drifting irregular asteroids, comet trails, nebula gas clouds — each in its own harmonious color) plus full marketing sections (about / features grid / showcase / spec / pricing / CTA / footer). Takes a natural-language description of one product (any kind — a note app, a coffee subscription, a CLI tool, an indie hardware, a hosting service…) and outputs ONE working .html file with deep-space dark or warm-letterpress theme. Runs in BOTH Claude Code (writes to ~/Desktop) and GLM / online chat (outputs HTML inline). Trigger phrases: "做个宇宙风产品落地页", "生成 ASCII 产品官网", "ascii-cosmos-gen ...", "做个独立软件 / 独立硬件落地页", or when user drags this skill folder into chat asking for an atmospheric product landing page.
中文简介正在准备中。当前显示原文说明。
Build premium scroll-driven web pages and product showcases inspired by high-end app, hardware, and product interaction patterns. Use for Raycast-like, Apple-like, NVIDIA-like, RTX/GPU, SaaS, AI browser, parallax, sticky scroll, pinned reveal, Three.js GLB model, Web Audio sound effect, responsive accessibility, and performance-safe frontend requests.
中文简介正在准备中。当前显示原文说明。
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
中文简介正在准备中。当前显示原文说明。
Drive Keel agent test-first or evidence-first execution for a selected OpenSpec task. Use when a task needs software tests, hardware testbench, assertions, lint, new behavior proof, regression coverage, or red/green evidence before implementation.
中文简介正在准备中。当前显示原文说明。
Maxim 3D CGI product render — engineered for purchase confidence and premium positioning. Uses Material Realism + Endowment Effect + Photorealism Trust Signals to move premium-product viewers toward purchase. Use for luxury product reveals, architectural visualization, tech hardware marketing, high-ticket commerce.
中文简介正在准备中。当前显示原文说明。
Adopt a virtual Shiba Inu dog at animalhouse.ai. Cat software running on dog hardware. Independent, stubborn, meme-worthy. Feeding every 5 hours. Rare tier dog.
中文简介正在准备中。当前显示原文说明。
Expert firmware analyst specializing in embedded systems, IoT security, and hardware reverse engineering. Masters firmware extraction, analysis, and vulnerability research for routers, IoT devices, automotive systems, and industrial controllers. Use PROACTIVELY for firmware security audits, IoT penetration testing, or embedded systems research.
中文简介正在准备中。当前显示原文说明。
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
中文简介正在准备中。当前显示原文说明。
Make a web app feel native on a phone — the small CSS and meta-tag fixes that separate "a website in a browser" from something that feels installed. Covers sticky hover states, tap highlight flashes, the 100vh bug, inputs that zoom the page, laggy taps, pull-to-refresh hijacking scroll, content under the notch, long-press selecting button text, carousels that scroll the wrong way, mismatched status bars, and the rule that you test on real hardware. Use when a web app is being built for or reviewed on mobile, when something "works in Chrome but feels wrong on my phone", when building a PWA, a bottom sheet, a carousel, a full-screen layout, or any touch interaction. For motion itself use animate; for React Native use animate-expo.
中文简介正在准备中。当前显示原文说明。
IoT and embedded device security testing methodology. Covers hardware reconnaissance (UART, JTAG, SWD, SPI flash, I2C EEPROM, eMMC chip-off), firmware acquisition (vendor portals, OTA capture, flash dump, binwalk extraction), firmware analysis (filesystem mounting, binary triage, hardcoded secrets, default credential discovery), bootloader attacks (U-Boot console, secure-boot bypass, fault injection), runtime attacks on embedded Linux/RTOS (busybox CVEs, MTD writes, /dev/mem), wireless protocol attacks (Zigbee, BLE, Z-Wave, LoRaWAN, Thread/Matter, sub-GHz), MQTT/CoAP/Modbus/BACnet/OPC-UA exploitation, mobile companion app analysis, cloud-IoT API abuse, and side-channel/glitching basics. Use for IoT pentest, smart-home assessment, ICS/OT testing, or embedded vulnerability research.
中文简介正在准备中。当前显示原文说明。