[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M758R08HK36WMESA6BSC9CDH":3,"skill-same:01M758R08HK36WMESA6BSC9CDH":82},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":14,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M758R08HK36WMESA6BSC9CDH","nanogpt",null,"Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).","zengrong233\u002Fdevin-skills","zengrong233","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F55529920?v=4","01M758DNYKQQCQX87XFVAGX5MW","songzengrong","01M758DNZVEJJQNM71DSRVHFEB",0,"MIT","https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills\u002Fblob\u002Fskills\u002F.agents\u002Fskills\u002Fnanogpt\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: nanogpt\ndescription: Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).\nversion: 1.0.0\nauthor: Orchestra Research\nlicense: MIT\ntags: [Model Architecture, NanoGPT, GPT-2, Educational, Andrej Karpathy, Transformer, Minimalist, From Scratch, Training]\ndependencies: [torch, transformers, datasets, tiktoken, wandb]\n---\n\n# nanoGPT - Minimalist GPT Training\n\n## Quick start\n\nnanoGPT is a simplified GPT implementation designed for learning and experimentation.\n\n**Installation**:\n```bash\npip install torch numpy transformers datasets tiktoken wandb tqdm\n```\n\n**Train on Shakespeare** (CPU-friendly):\n```bash\n# Prepare data\npython data\u002Fshakespeare_char\u002Fprepare.py\n\n# Train (5 minutes on CPU)\npython train.py config\u002Ftrain_shakespeare_char.py\n\n# Generate text\npython sample.py --out_dir=out-shakespeare-char\n```\n\n**Output**:\n```\nROMEO:\nWhat say'st thou? Shall I speak, and be a man?\n\nJULIET:\nI am afeard, and yet I'll speak; for thou art\nOne that hath been a man, and yet I know not\nWhat thou art.\n```\n\n## Common workflows\n\n### Workflow 1: Character-level Shakespeare\n\n**Complete training pipeline**:\n```bash\n# Step 1: Prepare data (creates train.bin, val.bin)\npython data\u002Fshakespeare_char\u002Fprepare.py\n\n# Step 2: Train small model\npython train.py config\u002Ftrain_shakespeare_char.py\n\n# Step 3: Generate text\npython sample.py --out_dir=out-shakespeare-char\n```\n\n**Config** (`config\u002Ftrain_shakespeare_char.py`):\n```python\n# Model config\nn_layer = 6          # 6 transformer layers\nn_head = 6           # 6 attention heads\nn_embd = 384         # 384-dim embeddings\nblock_size = 256     # 256 char context\n\n# Training config\nbatch_size = 64\nlearning_rate = 1e-3\nmax_iters = 5000\neval_interval = 500\n\n# Hardware\ndevice = 'cpu'  # Or 'cuda'\ncompile = False # Set True for PyTorch 2.0\n```\n\n**Training time**: ~5 minutes (CPU), ~1 minute (GPU)\n\n### Workflow 2: Reproduce GPT-2 (124M)\n\n**Multi-GPU training on OpenWebText**:\n```bash\n# Step 1: Prepare OpenWebText (takes ~1 hour)\npython data\u002Fopenwebtext\u002Fprepare.py\n\n# Step 2: Train GPT-2 124M with DDP (8 GPUs)\ntorchrun --standalone --nproc_per_node=8 \\\n  train.py config\u002Ftrain_gpt2.py\n\n# Step 3: Sample from trained model\npython sample.py --out_dir=out\n```\n\n**Config** (`config\u002Ftrain_gpt2.py`):\n```python\n# GPT-2 (124M) architecture\nn_layer = 12\nn_head = 12\nn_embd = 768\nblock_size = 1024\ndropout = 0.0\n\n# Training\nbatch_size = 12\ngradient_accumulation_steps = 5 * 8  # Total batch ~0.5M tokens\nlearning_rate = 6e-4\nmax_iters = 600000\nlr_decay_iters = 600000\n\n# System\ncompile = True  # PyTorch 2.0\n```\n\n**Training time**: ~4 days (8× A100)\n\n### Workflow 3: Fine-tune pretrained GPT-2\n\n**Start from OpenAI checkpoint**:\n```python\n# In train.py or config\ninit_from = 'gpt2'  # Options: gpt2, gpt2-medium, gpt2-large, gpt2-xl\n\n# Model loads OpenAI weights automatically\npython train.py config\u002Ffinetune_shakespeare.py\n```\n\n**Example config** (`config\u002Ffinetune_shakespeare.py`):\n```python\n# Start from GPT-2\ninit_from = 'gpt2'\n\n# Dataset\ndataset = 'shakespeare_char'\nbatch_size = 1\nblock_size = 1024\n\n# Fine-tuning\nlearning_rate = 3e-5  # Lower LR for fine-tuning\nmax_iters = 2000\nwarmup_iters = 100\n\n# Regularization\nweight_decay = 1e-1\n```\n\n### Workflow 4: Custom dataset\n\n**Train on your own text**:\n```python\n# data\u002Fcustom\u002Fprepare.py\nimport numpy as np\n\n# Load your data\nwith open('my_data.txt', 'r') as f:\n    text = f.read()\n\n# Create character mappings\nchars = sorted(list(set(text)))\nstoi = {ch: i for i, ch in enumerate(chars)}\nitos = {i: ch for i, ch in enumerate(chars)}\n\n# Tokenize\ndata = np.array([stoi[ch] for ch in text], dtype=np.uint16)\n\n# Split train\u002Fval\nn = len(data)\ntrain_data = data[:int(n*0.9)]\nval_data = data[int(n*0.9):]\n\n# Save\ntrain_data.tofile('data\u002Fcustom\u002Ftrain.bin')\nval_data.tofile('data\u002Fcustom\u002Fval.bin')\n```\n\n**Train**:\n```bash\npython data\u002Fcustom\u002Fprepare.py\npython train.py --dataset=custom\n```\n\n## When to use vs alternatives\n\n**Use nanoGPT when**:\n- Learning how GPT works\n- Experimenting with transformer variants\n- Teaching\u002Feducation purposes\n- Quick prototyping\n- Limited compute (can run on CPU)\n\n**Simplicity advantages**:\n- **~300 lines**: Entire model in `model.py`\n- **~300 lines**: Training loop in `train.py`\n- **Hackable**: Easy to modify\n- **No abstractions**: Pure PyTorch\n\n**Use alternatives instead**:\n- **HuggingFace Transformers**: Production use, many models\n- **Megatron-LM**: Large-scale distributed training\n- **LitGPT**: More architectures, production-ready\n- **PyTorch Lightning**: Need high-level framework\n\n## Common issues\n\n**Issue: CUDA out of memory**\n\nReduce batch size or context length:\n```python\nbatch_size = 1  # Reduce from 12\nblock_size = 512  # Reduce from 1024\ngradient_accumulation_steps = 40  # Increase to maintain effective batch\n```\n\n**Issue: Training too slow**\n\nEnable compilation (PyTorch 2.0+):\n```python\ncompile = True  # 2× speedup\n```\n\nUse mixed precision:\n```python\ndtype = 'bfloat16'  # Or 'float16'\n```\n\n**Issue: Poor generation quality**\n\nTrain longer:\n```python\nmax_iters = 10000  # Increase from 5000\n```\n\nLower temperature:\n```python\n# In sample.py\ntemperature = 0.7  # Lower from 1.0\ntop_k = 200       # Add top-k sampling\n```\n\n**Issue: Can't load GPT-2 weights**\n\nInstall transformers:\n```bash\npip install transformers\n```\n\nCheck model name:\n```python\ninit_from = 'gpt2'  # Valid: gpt2, gpt2-medium, gpt2-large, gpt2-xl\n```\n\n## Advanced topics\n\n**Model architecture**: See [references\u002Farchitecture.md](references\u002Farchitecture.md) for GPT block structure, multi-head attention, and MLP layers explained simply.\n\n**Training loop**: See [references\u002Ftraining.md](references\u002Ftraining.md) for learning rate schedule, gradient accumulation, and distributed data parallel setup.\n\n**Data preparation**: See [references\u002Fdata.md](references\u002Fdata.md) for tokenization strategies (character-level vs BPE) and binary format details.\n\n## Hardware requirements\n\n- **Shakespeare (char-level)**:\n  - CPU: 5 minutes\n  - GPU (T4): 1 minute\n  - VRAM: \u003C1GB\n\n- **GPT-2 (124M)**:\n  - 1× A100: ~1 week\n  - 8× A100: ~4 days\n  - VRAM: ~16GB per GPU\n\n- **GPT-2 Medium (350M)**:\n  - 8× A100: ~2 weeks\n  - VRAM: ~40GB per GPU\n\n**Performance**:\n- With `compile=True`: 2× speedup\n- With `dtype=bfloat16`: 50% memory reduction\n\n## Resources\n\n- GitHub: https:\u002F\u002Fgithub.com\u002Fkarpathy\u002FnanoGPT ⭐ 48,000+\n- Video: \"Let's build GPT\" by Andrej Karpathy\n- Paper: \"Attention is All You Need\" (Vaswani et al.)\n- OpenWebText: https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FSkylion007\u002Fopenwebtext\n- Educational: Best for understanding transformers from scratch\n\n\n","# nanoGPT - Minimalist GPT Training\n\n## Quick start\n\nnanoGPT is a simplified GPT implementation designed for learning and experimentation.\n\n**Installation**:\n```bash\npip install torch numpy transformers datasets tiktoken wandb tqdm\n```\n\n**Train on Shakespeare** (CPU-friendly):\n```bash\n# Prepare data\npython data\u002Fshakespeare_char\u002Fprepare.py\n\n# Train (5 minutes on CPU)\npython train.py config\u002Ftrain_shakespeare_char.py\n\n# Generate text\npython sample.py --out_dir=out-shakespeare-char\n```\n\n**Output**:\n```\nROMEO:\nWhat say'st thou? Shall I speak, and be a man?\n\nJULIET:\nI am afeard, and yet I'll speak; for thou art\nOne that hath been a man, and yet I know not\nWhat thou art.\n```\n\n## Common workflows\n\n### Workflow 1: Character-level Shakespeare\n\n**Complete training pipeline**:\n```bash\n# Step 1: Prepare data (creates train.bin, val.bin)\npython data\u002Fshakespeare_char\u002Fprepare.py\n\n# Step 2: Train small model\npython train.py config\u002Ftrain_shakespeare_char.py\n\n# Step 3: Generate text\npython sample.py --out_dir=out-shakespeare-char\n```\n\n**Config** (`config\u002Ftrain_shakespeare_char.py`):\n```python\n# Model config\nn_layer = 6          # 6 transformer layers\nn_head = 6           # 6 attention heads\nn_embd = 384         # 384-dim embeddings\nblock_size = 256     # 256 char context\n\n# Training config\nbatch_size = 64\nlearning_rate = 1e-3\nmax_iters = 5000\neval_interval = 500\n\n# Hardware\ndevice = 'cpu'  # Or 'cuda'\ncompile = False # Set True for PyTorch 2.0\n```\n\n**Training time**: ~5 minutes (CPU), ~1 minute (GPU)\n\n### Workflow 2: Reproduce GPT-2 (124M)\n\n**Multi-GPU training on OpenWebText**:\n```bash\n# Step 1: Prepare OpenWebText (takes ~1 hour)\npython data\u002Fopenwebtext\u002Fprepare.py\n\n# Step 2: Train GPT-2 124M with DDP (8 GPUs)\ntorchrun --standalone --nproc_per_node=8 \\\n  train.py config\u002Ftrain_gpt2.py\n\n# Step 3: Sample from trained model\npython sample.py --out_dir=out\n```\n\n**Config** (`config\u002Ftrain_gpt2.py`):\n```python\n# GPT-2 (124M) architecture\nn_layer = 12\nn_head = 12\nn_embd = 768\nblock_size = 1024\ndropout = 0.0\n\n# Training\nbatch_size = 12\ngradient_accumulation_steps = 5 * 8  # Total batch ~0.5M tokens\nlearning_rate = 6e-4\nmax_iters = 600000\nlr_decay_iters = 600000\n\n# System\ncompile = True  # PyTorch 2.0\n```\n\n**Training time**: ~4 days (8× A100)\n\n### Workflow 3: Fine-tune pretrained GPT-2\n\n**Start from OpenAI checkpoint**:\n```python\n# In train.py or config\ninit_from = 'gpt2'  # Options: gpt2, gpt2-medium, gpt2-large, gpt2-xl\n\n# Model loads OpenAI weights automatically\npython train.py config\u002Ffinetune_shakespeare.py\n```\n\n**Example config** (`config\u002Ffinetune_shakespeare.py`):\n```python\n# Start from GPT-2\ninit_from = 'gpt2'\n\n# Dataset\ndataset = 'shakespeare_char'\nbatch_size = 1\nblock_size = 1024\n\n# Fine-tuning\nlearning_rate = 3e-5  # Lower LR for fine-tuning\nmax_iters = 2000\nwarmup_iters = 100\n\n# Regularization\nweight_decay = 1e-1\n```\n\n### Workflow 4: Custom dataset\n\n**Train on your own text**:\n```python\n# data\u002Fcustom\u002Fprepare.py\nimport numpy as np\n\n# Load your data\nwith open('my_data.txt', 'r') as f:\n    text = f.read()\n\n# Create character mappings\nchars = sorted(list(set(text)))\nstoi = {ch: i for i, ch in enumerate(chars)}\nitos = {i: ch for i, ch in enumerate(chars)}\n\n# Tokenize\ndata = np.array([stoi[ch] for ch in text], dtype=np.uint16)\n\n# Split train\u002Fval\nn = len(data)\ntrain_data = data[:int(n*0.9)]\nval_data = data[int(n*0.9):]\n\n# Save\ntrain_data.tofile('data\u002Fcustom\u002Ftrain.bin')\nval_data.tofile('data\u002Fcustom\u002Fval.bin')\n```\n\n**Train**:\n```bash\npython data\u002Fcustom\u002Fprepare.py\npython train.py --dataset=custom\n```\n\n## When to use vs alternatives\n\n**Use nanoGPT when**:\n- Learning how GPT works\n- Experimenting with transformer variants\n- Teaching\u002Feducation purposes\n- Quick prototyping\n- Limited compute (can run on CPU)\n\n**Simplicity advantages**:\n- **~300 lines**: Entire model in `model.py`\n- **~300 lines**: Training loop in `train.py`\n- **Hackable**: Easy to modify\n- **No abstractions**: Pure PyTorch\n\n**Use alternatives instead**:\n- **HuggingFace Transformers**: Production use, many models\n- **Megatron-LM**: Large-scale distributed training\n- **LitGPT**: More architectures, production-ready\n- **PyTorch Lightning**: Need high-level framework\n\n## Common issues\n\n**Issue: CUDA out of memory**\n\nReduce batch size or context length:\n```python\nbatch_size = 1  # Reduce from 12\nblock_size = 512  # Reduce from 1024\ngradient_accumulation_steps = 40  # Increase to maintain effective batch\n```\n\n**Issue: Training too slow**\n\nEnable compilation (PyTorch 2.0+):\n```python\ncompile = True  # 2× speedup\n```\n\nUse mixed precision:\n```python\ndtype = 'bfloat16'  # Or 'float16'\n```\n\n**Issue: Poor generation quality**\n\nTrain longer:\n```python\nmax_iters = 10000  # Increase from 5000\n```\n\nLower temperature:\n```python\n# In sample.py\ntemperature = 0.7  # Lower from 1.0\ntop_k = 200       # Add top-k sampling\n```\n\n**Issue: Can't load GPT-2 weights**\n\nInstall transformers:\n```bash\npip install transformers\n```\n\nCheck model name:\n```python\ninit_from = 'gpt2'  # Valid: gpt2, gpt2-medium, gpt2-large, gpt2-xl\n```\n\n## Advanced topics\n\n**Model architecture**: See [references\u002Farchitecture.md](references\u002Farchitecture.md) for GPT block structure, multi-head attention, and MLP layers explained simply.\n\n**Training loop**: See [references\u002Ftraining.md](references\u002Ftraining.md) for learning rate schedule, gradient accumulation, and distributed data parallel setup.\n\n**Data preparation**: See [references\u002Fdata.md](references\u002Fdata.md) for tokenization strategies (character-level vs BPE) and binary format details.\n\n## Hardware requirements\n\n- **Shakespeare (char-level)**:\n  - CPU: 5 minutes\n  - GPU (T4): 1 minute\n  - VRAM: \u003C1GB\n\n- **GPT-2 (124M)**:\n  - 1× A100: ~1 week\n  - 8× A100: ~4 days\n  - VRAM: ~16GB per GPU\n\n- **GPT-2 Medium (350M)**:\n  - 8× A100: ~2 weeks\n  - VRAM: ~40GB per GPU\n\n**Performance**:\n- With `compile=True`: 2× speedup\n- With `dtype=bfloat16`: 50% memory reduction\n\n## Resources\n\n- GitHub: https:\u002F\u002Fgithub.com\u002Fkarpathy\u002FnanoGPT ⭐ 48,000+\n- Video: \"Let's build GPT\" by Andrej Karpathy\n- Paper: \"Attention is All You Need\" (Vaswani et al.)\n- OpenWebText: https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FSkylion007\u002Fopenwebtext\n- Educational: Best for understanding transformers from scratch\n\n\n",{"name":5,"tags":24,"author":34,"license":15,"version":35,"description":7,"dependencies":36},[25,26,27,28,29,30,31,32,33],"Model Architecture","NanoGPT","GPT-2","Educational","Andrej Karpathy","Transformer","Minimalist","From Scratch","Training","Orchestra Research","1.0.0",[37,38,39,40,41],"torch","transformers","datasets","tiktoken","wandb","skills","4fb202b97f2676132ac8713dbd2370cefacacb81",".agents\u002Fskills\u002Fnanogpt","https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills","https:\u002F\u002Fgithub.com\u002Fzengrong233","https:\u002F\u002Fwtu.edu.cn\u002F","my name songzengrong\r\n  research interest's:NLP","2026-06-04 10:48:22",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add zengrong233\u002Fdevin-skills --skill nanogpt",{"tool":56,"command":57},"bunx","bunx skills add zengrong233\u002Fdevin-skills --skill nanogpt",{"tool":59,"command":60},"pnpm","pnpm dlx skills add zengrong233\u002Fdevin-skills --skill nanogpt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills\u002Fblob\u002Fskills\u002F.agents\u002Fskills\u002Fnanogpt\u002FSKILL.md",true,[64,70,74,78],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},".openskills.json","REFERENCE","参考文档",235,"https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills\u002Fblob\u002Fskills\u002F.agents\u002Fskills\u002Fnanogpt\u002F.openskills.json",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Farchitecture.md",11716,"https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills\u002Fblob\u002Fskills\u002F.agents\u002Fskills\u002Fnanogpt\u002Freferences\u002Farchitecture.md",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fdata.md",11212,"https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills\u002Fblob\u002Fskills\u002F.agents\u002Fskills\u002Fnanogpt\u002Freferences\u002Fdata.md",{"path":79,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Ftraining.md",13551,"https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills\u002Fblob\u002Fskills\u002F.agents\u002Fskills\u002Fnanogpt\u002Freferences\u002Ftraining.md",[83,90,97,106,114,121],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M759188DV0S9ARY1ETHCEY45","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills\u002Fblob\u002Fskills\u002F.agents\u002Fskills\u002Fwhisper\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M75913ZB4EDVWYGYRTRWTKD1","weights-and-biases","Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform","https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills\u002Fblob\u002Fskills\u002F.agents\u002Fskills\u002Fweights-and-biases\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":101,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M75910YNW7H0KZQDR96TGWZ9","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills\u002Fblob\u002Fskills\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills\u002Fblob\u002Fskills\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":101,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7590X6XJR78KVSHCVFYB59A","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills\u002Fblob\u002Fskills\u002F.agents\u002Fskills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills\u002Fblob\u002Fskills\u002F.agents\u002Fskills\u002Fweb-artifacts-builder\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M7590RENMJJTXV44P8G553ZQ","serving-llms-vllm","Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency\u002Fthroughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ\u002FAWQ\u002FFP8), and tensor parallelism.","https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills\u002Fblob\u002Fskills\u002F.agents\u002Fskills\u002Fvllm\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":19},"01M7590GA6EZKJA8GAAMMPAXBB","verl-rl-training","Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.","https:\u002F\u002Fgithub.com\u002Fzengrong233\u002Fdevin-skills\u002Fblob\u002Fskills\u002F.agents\u002Fskills\u002Fverl\u002FSKILL.md",[],[]]