[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ADWJDRXM66AQV06HFPH9C0":3,"skill-same:01M6ADWJDRXM66AQV06HFPH9C0":312},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":63,"ownerHtmlUrl":64,"ownerBlogUrl":65,"ownerDescription":66,"updatedAt":67,"install":68,"resources":81},"01M6ADWJDRXM66AQV06HFPH9C0","optimization-hqq",null,"Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4\u002F3\u002F2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-hqq\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"HQQ","Optimization","optimization hqq","Transformers","when","calibration","for","orchestra","with","Model Compression","Memory Efficiency","bit","efficiency","use","model","llms","vLLM","data","HuggingFace","fast","compression","workflows","research","memory","inference","2026-11-10 10:12:30",false,"---\nname: optimization-hqq\ndescription: Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4\u002F3\u002F2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  author: Orchestra Research\n  tags: [Quantization, HQQ, Optimization, Memory Efficiency, Inference, Model Compression]\n  dependencies: [hqq>=0.2.0, torch>=2.0.0]\n---\n\n# HQQ - Half-Quadratic Quantization\n\nFast, calibration-free weight quantization supporting 8\u002F4\u002F3\u002F2\u002F1-bit precision with multiple optimized backends.\n\n## When to use HQQ\n\n**Use HQQ when:**\n- Quantizing models without calibration data (no dataset needed)\n- Need fast quantization (minutes vs hours for GPTQ\u002FAWQ)\n- Deploying with vLLM or HuggingFace Transformers\n- Fine-tuning quantized models with LoRA\u002FPEFT\n- Experimenting with extreme quantization (2-bit, 1-bit)\n\n**Key advantages:**\n- **No calibration**: Quantize any model instantly without sample data\n- **Multiple backends**: PyTorch, ATEN, TorchAO, Marlin, BitBlas for optimized inference\n- **Flexible precision**: 8\u002F4\u002F3\u002F2\u002F1-bit with configurable group sizes\n- **Framework integration**: Native HuggingFace and vLLM support\n- **PEFT compatible**: Fine-tune quantized models with LoRA\n\n**Use alternatives instead:**\n- **AWQ**: Need calibration-based accuracy, production serving\n- **GPTQ**: Maximum accuracy with calibration data available\n- **bitsandbytes**: Simple 8-bit\u002F4-bit without custom backends\n- **llama.cpp\u002FGGUF**: CPU inference, Apple Silicon deployment\n\n## Quick start\n\n### Installation\n\n```bash\npip install hqq\n\n# With specific backend\npip install hqq[torch]      # PyTorch backend\npip install hqq[torchao]    # TorchAO int4 backend\npip install hqq[bitblas]    # BitBlas backend\npip install hqq[marlin]     # Marlin backend\n```\n\n### Basic quantization\n\n```python\nfrom hqq.core.quantize import BaseQuantizeConfig, HQQLinear\nimport torch.nn as nn\n\n# Configure quantization\nconfig = BaseQuantizeConfig(\n    nbits=4,           # 4-bit quantization\n    group_size=64,     # Group size for quantization\n    axis=1             # Quantize along output dimension\n)\n\n# Quantize a linear layer\nlinear = nn.Linear(4096, 4096)\nhqq_linear = HQQLinear(linear, config)\n\n# Use normally\noutput = hqq_linear(input_tensor)\n```\n\n### Quantize full model with HuggingFace\n\n```python\nfrom transformers import AutoModelForCausalLM, HqqConfig\n\n# Configure HQQ\nquantization_config = HqqConfig(\n    nbits=4,\n    group_size=64,\n    axis=1\n)\n\n# Load and quantize\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-3.1-8B\",\n    quantization_config=quantization_config,\n    device_map=\"auto\"\n)\n\n# Model is quantized and ready to use\n```\n\n## Core concepts\n\n### Quantization configuration\n\nHQQ uses `BaseQuantizeConfig` to define quantization parameters:\n\n```python\nfrom hqq.core.quantize import BaseQuantizeConfig\n\n# Standard 4-bit config\nconfig_4bit = BaseQuantizeConfig(\n    nbits=4,           # Bits per weight (1-8)\n    group_size=64,     # Weights per quantization group\n    axis=1             # 0=input dim, 1=output dim\n)\n\n# Aggressive 2-bit config\nconfig_2bit = BaseQuantizeConfig(\n    nbits=2,\n    group_size=16,     # Smaller groups for low-bit\n    axis=1\n)\n\n# Mixed precision per layer type\nlayer_configs = {\n    \"self_attn.q_proj\": BaseQuantizeConfig(nbits=4, group_size=64),\n    \"self_attn.k_proj\": BaseQuantizeConfig(nbits=4, group_size=64),\n    \"self_attn.v_proj\": BaseQuantizeConfig(nbits=4, group_size=64),\n    \"mlp.gate_proj\": BaseQuantizeConfig(nbits=2, group_size=32),\n    \"mlp.up_proj\": BaseQuantizeConfig(nbits=2, group_size=32),\n    \"mlp.down_proj\": BaseQuantizeConfig(nbits=4, group_size=64),\n}\n```\n\n### HQQLinear layer\n\nThe core quantized layer that replaces `nn.Linear`:\n\n```python\nfrom hqq.core.quantize import HQQLinear\nimport torch\n\n# Create quantized layer\nlinear = torch.nn.Linear(4096, 4096)\nhqq_layer = HQQLinear(linear, config)\n\n# Access quantized weights\nW_q = hqq_layer.W_q           # Quantized weights\nscale = hqq_layer.scale       # Scale factors\nzero = hqq_layer.zero         # Zero points\n\n# Dequantize for inspection\nW_dequant = hqq_layer.dequantize()\n```\n\n### Backends\n\nHQQ supports multiple inference backends for different hardware:\n\n```python\nfrom hqq.core.quantize import HQQLinear\n\n# Available backends\nbackends = [\n    \"pytorch\",          # Pure PyTorch (default)\n    \"pytorch_compile\",  # torch.compile optimized\n    \"aten\",            # Custom CUDA kernels\n    \"torchao_int4\",    # TorchAO int4 matmul\n    \"gemlite\",         # GemLite CUDA kernels\n    \"bitblas\",         # BitBlas optimized\n    \"marlin\",          # Marlin 4-bit kernels\n]\n\n# Set backend globally\nHQQLinear.set_backend(\"torchao_int4\")\n\n# Or per layer\nhqq_layer.set_backend(\"marlin\")\n```\n\n**Backend selection guide:**\n| Backend | Best For | Requirements |\n|---------|----------|--------------|\n| pytorch | Compatibility | Any GPU |\n| pytorch_compile | Moderate speedup | torch>=2.0 |\n| aten | Good balance | CUDA GPU |\n| torchao_int4 | 4-bit inference | torchao installed |\n| marlin | Maximum 4-bit speed | Ampere+ GPU |\n| bitblas | Flexible bit-widths | bitblas installed |\n\n## HuggingFace integration\n\n### Load pre-quantized models\n\n```python\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\n# Load HQQ-quantized model from Hub\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"mobiuslabsgmbh\u002FLlama-3.1-8B-HQQ-4bit\",\n    device_map=\"auto\"\n)\ntokenizer = AutoTokenizer.from_pretrained(\"meta-llama\u002FLlama-3.1-8B\")\n\n# Use normally\ninputs = tokenizer(\"Hello, world!\", return_tensors=\"pt\").to(model.device)\noutputs = model.generate(**inputs, max_new_tokens=50)\n```\n\n### Quantize and save\n\n```python\nfrom transformers import AutoModelForCausalLM, HqqConfig\n\n# Quantize\nconfig = HqqConfig(nbits=4, group_size=64)\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-3.1-8B\",\n    quantization_config=config,\n    device_map=\"auto\"\n)\n\n# Save quantized model\nmodel.save_pretrained(\".\u002Fllama-8b-hqq-4bit\")\n\n# Push to Hub\nmodel.push_to_hub(\"my-org\u002FLlama-3.1-8B-HQQ-4bit\")\n```\n\n### Mixed precision quantization\n\n```python\nfrom transformers import AutoModelForCausalLM, HqqConfig\n\n# Different precision per layer type\nconfig = HqqConfig(\n    nbits=4,\n    group_size=64,\n    # Attention layers: higher precision\n    # MLP layers: lower precision for memory savings\n    dynamic_config={\n        \"attn\": {\"nbits\": 4, \"group_size\": 64},\n        \"mlp\": {\"nbits\": 2, \"group_size\": 32}\n    }\n)\n```\n\n## vLLM integration\n\n### Serve HQQ models with vLLM\n\n```python\nfrom vllm import LLM, SamplingParams\n\n# Load HQQ-quantized model\nllm = LLM(\n    model=\"mobiuslabsgmbh\u002FLlama-3.1-8B-HQQ-4bit\",\n    quantization=\"hqq\",\n    dtype=\"float16\"\n)\n\n# Generate\nsampling_params = SamplingParams(temperature=0.7, max_tokens=100)\noutputs = llm.generate([\"What is machine learning?\"], sampling_params)\n```\n\n### vLLM with custom HQQ config\n\n```python\nfrom vllm import LLM\n\nllm = LLM(\n    model=\"meta-llama\u002FLlama-3.1-8B\",\n    quantization=\"hqq\",\n    quantization_config={\n        \"nbits\": 4,\n        \"group_size\": 64\n    }\n)\n```\n\n## PEFT\u002FLoRA fine-tuning\n\n### Fine-tune quantized models\n\n```python\nfrom transformers import AutoModelForCausalLM, HqqConfig\nfrom peft import LoraConfig, get_peft_model\n\n# Load quantized model\nquant_config = HqqConfig(nbits=4, group_size=64)\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-3.1-8B\",\n    quantization_config=quant_config,\n    device_map=\"auto\"\n)\n\n# Apply LoRA\nlora_config = LoraConfig(\n    r=16,\n    lora_alpha=32,\n    target_modules=[\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\"],\n    lora_dropout=0.05,\n    bias=\"none\",\n    task_type=\"CAUSAL_LM\"\n)\n\nmodel = get_peft_model(model, lora_config)\n\n# Train normally with Trainer or custom loop\n```\n\n### QLoRA-style training\n\n```python\nfrom transformers import TrainingArguments, Trainer\n\ntraining_args = TrainingArguments(\n    output_dir=\".\u002Fhqq-lora-output\",\n    per_device_train_batch_size=4,\n    gradient_accumulation_steps=4,\n    learning_rate=2e-4,\n    num_train_epochs=3,\n    fp16=True,\n    logging_steps=10,\n    save_strategy=\"epoch\"\n)\n\ntrainer = Trainer(\n    model=model,\n    args=training_args,\n    train_dataset=train_dataset,\n    data_collator=data_collator\n)\n\ntrainer.train()\n```\n\n## Quantization workflows\n\n### Workflow 1: Quick model compression\n\n```python\nfrom transformers import AutoModelForCausalLM, AutoTokenizer, HqqConfig\n\n# 1. Configure quantization\nconfig = HqqConfig(nbits=4, group_size=64)\n\n# 2. Load and quantize (no calibration needed!)\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-3.1-8B\",\n    quantization_config=config,\n    device_map=\"auto\"\n)\ntokenizer = AutoTokenizer.from_pretrained(\"meta-llama\u002FLlama-3.1-8B\")\n\n# 3. Verify quality\nprompt = \"The capital of France is\"\ninputs = tokenizer(prompt, return_tensors=\"pt\").to(model.device)\noutputs = model.generate(**inputs, max_new_tokens=20)\nprint(tokenizer.decode(outputs[0]))\n\n# 4. Save\nmodel.save_pretrained(\".\u002Fllama-8b-hqq\")\ntokenizer.save_pretrained(\".\u002Fllama-8b-hqq\")\n```\n\n### Workflow 2: Optimize for inference speed\n\n```python\nfrom hqq.core.quantize import HQQLinear\nfrom transformers import AutoModelForCausalLM, HqqConfig\n\n# 1. Quantize with optimal backend\nconfig = HqqConfig(nbits=4, group_size=64)\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-3.1-8B\",\n    quantization_config=config,\n    device_map=\"auto\"\n)\n\n# 2. Set fast backend\nHQQLinear.set_backend(\"marlin\")  # or \"torchao_int4\"\n\n# 3. Compile for additional speedup\nimport torch\nmodel = torch.compile(model)\n\n# 4. Benchmark\nimport time\ninputs = tokenizer(\"Hello\", return_tensors=\"pt\").to(model.device)\nstart = time.time()\nfor _ in range(10):\n    model.generate(**inputs, max_new_tokens=100)\nprint(f\"Avg time: {(time.time() - start) \u002F 10:.2f}s\")\n```\n\n## Best practices\n\n1. **Start with 4-bit**: Best quality\u002Fsize tradeoff for most models\n2. **Use group_size=64**: Good balance; smaller for extreme quantization\n3. **Choose backend wisely**: Marlin for 4-bit Ampere+, TorchAO for flexibility\n4. **Verify quality**: Always test generation quality after quantization\n5. **Mixed precision**: Keep attention at higher precision, compress MLP more\n6. **PEFT training**: Use LoRA r=16-32 for good fine-tuning results\n\n## Common issues\n\n**Out of memory during quantization:**\n```python\n# Quantize layer-by-layer\nfrom hqq.models.hf.base import AutoHQQHFModel\n\nmodel = AutoHQQHFModel.from_pretrained(\n    \"meta-llama\u002FLlama-3.1-8B\",\n    quantization_config=config,\n    device_map=\"sequential\"  # Load layers sequentially\n)\n```\n\n**Slow inference:**\n```python\n# Switch to optimized backend\nfrom hqq.core.quantize import HQQLinear\nHQQLinear.set_backend(\"marlin\")  # Requires Ampere+ GPU\n\n# Or compile\nmodel = torch.compile(model, mode=\"reduce-overhead\")\n```\n\n**Poor quality at 2-bit:**\n```python\n# Use smaller group size\nconfig = BaseQuantizeConfig(\n    nbits=2,\n    group_size=16,  # Smaller groups help at low bits\n    axis=1\n)\n```\n\n## References\n\n- **[Advanced Usage](references\u002Fadvanced-usage.md)** - Custom backends, mixed precision, optimization\n- **[Troubleshooting](references\u002Ftroubleshooting.md)** - Common issues, debugging, benchmarks\n\n## Resources\n\n- **Repository**: https:\u002F\u002Fgithub.com\u002Fmobiusml\u002Fhqq\n- **Paper**: Half-Quadratic Quantization\n- **HuggingFace Models**: https:\u002F\u002Fhuggingface.co\u002Fmobiuslabsgmbh\n- **Version**: 0.2.0+\n- **License**: Apache 2.0\n","# HQQ - Half-Quadratic Quantization\n\nFast, calibration-free weight quantization supporting 8\u002F4\u002F3\u002F2\u002F1-bit precision with multiple optimized backends.\n\n## When to use HQQ\n\n**Use HQQ when:**\n- Quantizing models without calibration data (no dataset needed)\n- Need fast quantization (minutes vs hours for GPTQ\u002FAWQ)\n- Deploying with vLLM or HuggingFace Transformers\n- Fine-tuning quantized models with LoRA\u002FPEFT\n- Experimenting with extreme quantization (2-bit, 1-bit)\n\n**Key advantages:**\n- **No calibration**: Quantize any model instantly without sample data\n- **Multiple backends**: PyTorch, ATEN, TorchAO, Marlin, BitBlas for optimized inference\n- **Flexible precision**: 8\u002F4\u002F3\u002F2\u002F1-bit with configurable group sizes\n- **Framework integration**: Native HuggingFace and vLLM support\n- **PEFT compatible**: Fine-tune quantized models with LoRA\n\n**Use alternatives instead:**\n- **AWQ**: Need calibration-based accuracy, production serving\n- **GPTQ**: Maximum accuracy with calibration data available\n- **bitsandbytes**: Simple 8-bit\u002F4-bit without custom backends\n- **llama.cpp\u002FGGUF**: CPU inference, Apple Silicon deployment\n\n## Quick start\n\n### Installation\n\n```bash\npip install hqq\n\n# With specific backend\npip install hqq[torch]      # PyTorch backend\npip install hqq[torchao]    # TorchAO int4 backend\npip install hqq[bitblas]    # BitBlas backend\npip install hqq[marlin]     # Marlin backend\n```\n\n### Basic quantization\n\n```python\nfrom hqq.core.quantize import BaseQuantizeConfig, HQQLinear\nimport torch.nn as nn\n\n# Configure quantization\nconfig = BaseQuantizeConfig(\n    nbits=4,           # 4-bit quantization\n    group_size=64,     # Group size for quantization\n    axis=1             # Quantize along output dimension\n)\n\n# Quantize a linear layer\nlinear = nn.Linear(4096, 4096)\nhqq_linear = HQQLinear(linear, config)\n\n# Use normally\noutput = hqq_linear(input_tensor)\n```\n\n### Quantize full model with HuggingFace\n\n```python\nfrom transformers import AutoModelForCausalLM, HqqConfig\n\n# Configure HQQ\nquantization_config = HqqConfig(\n    nbits=4,\n    group_size=64,\n    axis=1\n)\n\n# Load and quantize\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-3.1-8B\",\n    quantization_config=quantization_config,\n    device_map=\"auto\"\n)\n\n# Model is quantized and ready to use\n```\n\n## Core concepts\n\n### Quantization configuration\n\nHQQ uses `BaseQuantizeConfig` to define quantization parameters:\n\n```python\nfrom hqq.core.quantize import BaseQuantizeConfig\n\n# Standard 4-bit config\nconfig_4bit = BaseQuantizeConfig(\n    nbits=4,           # Bits per weight (1-8)\n    group_size=64,     # Weights per quantization group\n    axis=1             # 0=input dim, 1=output dim\n)\n\n# Aggressive 2-bit config\nconfig_2bit = BaseQuantizeConfig(\n    nbits=2,\n    group_size=16,     # Smaller groups for low-bit\n    axis=1\n)\n\n# Mixed precision per layer type\nlayer_configs = {\n    \"self_attn.q_proj\": BaseQuantizeConfig(nbits=4, group_size=64),\n    \"self_attn.k_proj\": BaseQuantizeConfig(nbits=4, group_size=64),\n    \"self_attn.v_proj\": BaseQuantizeConfig(nbits=4, group_size=64),\n    \"mlp.gate_proj\": BaseQuantizeConfig(nbits=2, group_size=32),\n    \"mlp.up_proj\": BaseQuantizeConfig(nbits=2, group_size=32),\n    \"mlp.down_proj\": BaseQuantizeConfig(nbits=4, group_size=64),\n}\n```\n\n### HQQLinear layer\n\nThe core quantized layer that replaces `nn.Linear`:\n\n```python\nfrom hqq.core.quantize import HQQLinear\nimport torch\n\n# Create quantized layer\nlinear = torch.nn.Linear(4096, 4096)\nhqq_layer = HQQLinear(linear, config)\n\n# Access quantized weights\nW_q = hqq_layer.W_q           # Quantized weights\nscale = hqq_layer.scale       # Scale factors\nzero = hqq_layer.zero         # Zero points\n\n# Dequantize for inspection\nW_dequant = hqq_layer.dequantize()\n```\n\n### Backends\n\nHQQ supports multiple inference backends for different hardware:\n\n```python\nfrom hqq.core.quantize import HQQLinear\n\n# Available backends\nbackends = [\n    \"pytorch\",          # Pure PyTorch (default)\n    \"pytorch_compile\",  # torch.compile optimized\n    \"aten\",            # Custom CUDA kernels\n    \"torchao_int4\",    # TorchAO int4 matmul\n    \"gemlite\",         # GemLite CUDA kernels\n    \"bitblas\",         # BitBlas optimized\n    \"marlin\",          # Marlin 4-bit kernels\n]\n\n# Set backend globally\nHQQLinear.set_backend(\"torchao_int4\")\n\n# Or per layer\nhqq_layer.set_backend(\"marlin\")\n```\n\n**Backend selection guide:**\n| Backend | Best For | Requirements |\n|---------|----------|--------------|\n| pytorch | Compatibility | Any GPU |\n| pytorch_compile | Moderate speedup | torch>=2.0 |\n| aten | Good balance | CUDA GPU |\n| torchao_int4 | 4-bit inference | torchao installed |\n| marlin | Maximum 4-bit speed | Ampere+ GPU |\n| bitblas | Flexible bit-widths | bitblas installed |\n\n## HuggingFace integration\n\n### Load pre-quantized models\n\n```python\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\n# Load HQQ-quantized model from Hub\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"mobiuslabsgmbh\u002FLlama-3.1-8B-HQQ-4bit\",\n    device_map=\"auto\"\n)\ntokenizer = AutoTokenizer.from_pretrained(\"meta-llama\u002FLlama-3.1-8B\")\n\n# Use normally\ninputs = tokenizer(\"Hello, world!\", return_tensors=\"pt\").to(model.device)\noutputs = model.generate(**inputs, max_new_tokens=50)\n```\n\n### Quantize and save\n\n```python\nfrom transformers import AutoModelForCausalLM, HqqConfig\n\n# Quantize\nconfig = HqqConfig(nbits=4, group_size=64)\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-3.1-8B\",\n    quantization_config=config,\n    device_map=\"auto\"\n)\n\n# Save quantized model\nmodel.save_pretrained(\".\u002Fllama-8b-hqq-4bit\")\n\n# Push to Hub\nmodel.push_to_hub(\"my-org\u002FLlama-3.1-8B-HQQ-4bit\")\n```\n\n### Mixed precision quantization\n\n```python\nfrom transformers import AutoModelForCausalLM, HqqConfig\n\n# Different precision per layer type\nconfig = HqqConfig(\n    nbits=4,\n    group_size=64,\n    # Attention layers: higher precision\n    # MLP layers: lower precision for memory savings\n    dynamic_config={\n        \"attn\": {\"nbits\": 4, \"group_size\": 64},\n        \"mlp\": {\"nbits\": 2, \"group_size\": 32}\n    }\n)\n```\n\n## vLLM integration\n\n### Serve HQQ models with vLLM\n\n```python\nfrom vllm import LLM, SamplingParams\n\n# Load HQQ-quantized model\nllm = LLM(\n    model=\"mobiuslabsgmbh\u002FLlama-3.1-8B-HQQ-4bit\",\n    quantization=\"hqq\",\n    dtype=\"float16\"\n)\n\n# Generate\nsampling_params = SamplingParams(temperature=0.7, max_tokens=100)\noutputs = llm.generate([\"What is machine learning?\"], sampling_params)\n```\n\n### vLLM with custom HQQ config\n\n```python\nfrom vllm import LLM\n\nllm = LLM(\n    model=\"meta-llama\u002FLlama-3.1-8B\",\n    quantization=\"hqq\",\n    quantization_config={\n        \"nbits\": 4,\n        \"group_size\": 64\n    }\n)\n```\n\n## PEFT\u002FLoRA fine-tuning\n\n### Fine-tune quantized models\n\n```python\nfrom transformers import AutoModelForCausalLM, HqqConfig\nfrom peft import LoraConfig, get_peft_model\n\n# Load quantized model\nquant_config = HqqConfig(nbits=4, group_size=64)\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-3.1-8B\",\n    quantization_config=quant_config,\n    device_map=\"auto\"\n)\n\n# Apply LoRA\nlora_config = LoraConfig(\n    r=16,\n    lora_alpha=32,\n    target_modules=[\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\"],\n    lora_dropout=0.05,\n    bias=\"none\",\n    task_type=\"CAUSAL_LM\"\n)\n\nmodel = get_peft_model(model, lora_config)\n\n# Train normally with Trainer or custom loop\n```\n\n### QLoRA-style training\n\n```python\nfrom transformers import TrainingArguments, Trainer\n\ntraining_args = TrainingArguments(\n    output_dir=\".\u002Fhqq-lora-output\",\n    per_device_train_batch_size=4,\n    gradient_accumulation_steps=4,\n    learning_rate=2e-4,\n    num_train_epochs=3,\n    fp16=True,\n    logging_steps=10,\n    save_strategy=\"epoch\"\n)\n\ntrainer = Trainer(\n    model=model,\n    args=training_args,\n    train_dataset=train_dataset,\n    data_collator=data_collator\n)\n\ntrainer.train()\n```\n\n## Quantization workflows\n\n### Workflow 1: Quick model compression\n\n```python\nfrom transformers import AutoModelForCausalLM, AutoTokenizer, HqqConfig\n\n# 1. Configure quantization\nconfig = HqqConfig(nbits=4, group_size=64)\n\n# 2. Load and quantize (no calibration needed!)\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-3.1-8B\",\n    quantization_config=config,\n    device_map=\"auto\"\n)\ntokenizer = AutoTokenizer.from_pretrained(\"meta-llama\u002FLlama-3.1-8B\")\n\n# 3. Verify quality\nprompt = \"The capital of France is\"\ninputs = tokenizer(prompt, return_tensors=\"pt\").to(model.device)\noutputs = model.generate(**inputs, max_new_tokens=20)\nprint(tokenizer.decode(outputs[0]))\n\n# 4. Save\nmodel.save_pretrained(\".\u002Fllama-8b-hqq\")\ntokenizer.save_pretrained(\".\u002Fllama-8b-hqq\")\n```\n\n### Workflow 2: Optimize for inference speed\n\n```python\nfrom hqq.core.quantize import HQQLinear\nfrom transformers import AutoModelForCausalLM, HqqConfig\n\n# 1. Quantize with optimal backend\nconfig = HqqConfig(nbits=4, group_size=64)\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-3.1-8B\",\n    quantization_config=config,\n    device_map=\"auto\"\n)\n\n# 2. Set fast backend\nHQQLinear.set_backend(\"marlin\")  # or \"torchao_int4\"\n\n# 3. Compile for additional speedup\nimport torch\nmodel = torch.compile(model)\n\n# 4. Benchmark\nimport time\ninputs = tokenizer(\"Hello\", return_tensors=\"pt\").to(model.device)\nstart = time.time()\nfor _ in range(10):\n    model.generate(**inputs, max_new_tokens=100)\nprint(f\"Avg time: {(time.time() - start) \u002F 10:.2f}s\")\n```\n\n## Best practices\n\n1. **Start with 4-bit**: Best quality\u002Fsize tradeoff for most models\n2. **Use group_size=64**: Good balance; smaller for extreme quantization\n3. **Choose backend wisely**: Marlin for 4-bit Ampere+, TorchAO for flexibility\n4. **Verify quality**: Always test generation quality after quantization\n5. **Mixed precision**: Keep attention at higher precision, compress MLP more\n6. **PEFT training**: Use LoRA r=16-32 for good fine-tuning results\n\n## Common issues\n\n**Out of memory during quantization:**\n```python\n# Quantize layer-by-layer\nfrom hqq.models.hf.base import AutoHQQHFModel\n\nmodel = AutoHQQHFModel.from_pretrained(\n    \"meta-llama\u002FLlama-3.1-8B\",\n    quantization_config=config,\n    device_map=\"sequential\"  # Load layers sequentially\n)\n```\n\n**Slow inference:**\n```python\n# Switch to optimized backend\nfrom hqq.core.quantize import HQQLinear\nHQQLinear.set_backend(\"marlin\")  # Requires Ampere+ GPU\n\n# Or compile\nmodel = torch.compile(model, mode=\"reduce-overhead\")\n```\n\n**Poor quality at 2-bit:**\n```python\n# Use smaller group size\nconfig = BaseQuantizeConfig(\n    nbits=2,\n    group_size=16,  # Smaller groups help at low bits\n    axis=1\n)\n```\n\n## References\n\n- **[Advanced Usage](references\u002Fadvanced-usage.md)** - Custom backends, mixed precision, optimization\n- **[Troubleshooting](references\u002Ftroubleshooting.md)** - Common issues, debugging, benchmarks\n\n## Resources\n\n- **Repository**: https:\u002F\u002Fgithub.com\u002Fmobiusml\u002Fhqq\n- **Paper**: Half-Quadratic Quantization\n- **HuggingFace Models**: https:\u002F\u002Fhuggingface.co\u002Fmobiuslabsgmbh\n- **Version**: 0.2.0+\n- **License**: Apache 2.0\n",{"name":5,"license":15,"metadata":49,"description":7},{"tags":50,"author":53,"version":54,"dependencies":55},[51,19,20,29,52,28],"Quantization","Inference","Orchestra Research","1.0.0",[56,57],"hqq>=0.2.0","torch>=2.0.0","main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-hqq",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":69,"prompt":79,"zipAvailable":80},[70,73,76],{"tool":71,"command":72},"npx","npx skills add davila7\u002Fclaude-code-templates --skill optimization-hqq",{"tool":74,"command":75},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill optimization-hqq",{"tool":77,"command":78},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill optimization-hqq","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-hqq\u002FSKILL.md",true,[82,88,94,100,104,108,112,116,120,124,128,132,136,140,144,148,152,156,160,164,168,172,176,180,184,188,192,196,200,204,208,212,216,220,224,228,232,236,240,244,248,252,256,260,264,268,272,276,280,284,288,292,296,300,304,308],{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"LICENSE.txt","LICENSE","许可证",1467,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002FLICENSE.txt",{"path":89,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":92,"sourceHtmlUrl":93},"recalc.py","SCRIPT","脚本",6408,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Frecalc.py",{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fadvanced-usage.md","REFERENCE","参考文档",14077,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-hqq\u002Freferences\u002Fadvanced-usage.md",{"path":101,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Ftroubleshooting.md",11086,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-hqq\u002Freferences\u002Ftroubleshooting.md",{"path":105,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":106,"sourceHtmlUrl":107},"scripts\u002Foffice\u002Fhelpers\u002F__init__.py",0,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fhelpers\u002F__init__.py",{"path":109,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":110,"sourceHtmlUrl":111},"scripts\u002Foffice\u002Fhelpers\u002Fmerge_runs.py",5567,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fhelpers\u002Fmerge_runs.py",{"path":113,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":114,"sourceHtmlUrl":115},"scripts\u002Foffice\u002Fhelpers\u002Fsimplify_redlines.py",5754,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fhelpers\u002Fsimplify_redlines.py",{"path":117,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":118,"sourceHtmlUrl":119},"scripts\u002Foffice\u002Fpack.py",4991,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fpack.py",{"path":121,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":122,"sourceHtmlUrl":123},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-contentTypes.xsd",1963,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-contentTypes.xsd",{"path":125,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":126,"sourceHtmlUrl":127},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-coreProperties.xsd",2515,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-coreProperties.xsd",{"path":129,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":130,"sourceHtmlUrl":131},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-digSig.xsd",2856,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-digSig.xsd",{"path":133,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":134,"sourceHtmlUrl":135},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-relationships.xsd",1344,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-relationships.xsd",{"path":137,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":138,"sourceHtmlUrl":139},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chart.xsd",74984,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chart.xsd",{"path":141,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":142,"sourceHtmlUrl":143},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chartDrawing.xsd",6956,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chartDrawing.xsd",{"path":145,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":146,"sourceHtmlUrl":147},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-diagram.xsd",51302,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-diagram.xsd",{"path":149,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":150,"sourceHtmlUrl":151},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-lockedCanvas.xsd",624,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-lockedCanvas.xsd",{"path":153,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":154,"sourceHtmlUrl":155},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-main.xsd",152039,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-main.xsd",{"path":157,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":158,"sourceHtmlUrl":159},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-picture.xsd",1231,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-picture.xsd",{"path":161,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":162,"sourceHtmlUrl":163},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-spreadsheetDrawing.xsd",8862,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-spreadsheetDrawing.xsd",{"path":165,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":166,"sourceHtmlUrl":167},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-wordprocessingDrawing.xsd",14795,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-wordprocessingDrawing.xsd",{"path":169,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":170,"sourceHtmlUrl":171},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fpml.xsd",83612,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fpml.xsd",{"path":173,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":174,"sourceHtmlUrl":175},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-additionalCharacteristics.xsd",1269,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-additionalCharacteristics.xsd",{"path":177,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":178,"sourceHtmlUrl":179},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-bibliography.xsd",7328,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-bibliography.xsd",{"path":181,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":182,"sourceHtmlUrl":183},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-commonSimpleTypes.xsd",6382,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-commonSimpleTypes.xsd",{"path":185,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":186,"sourceHtmlUrl":187},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlDataProperties.xsd",1248,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlDataProperties.xsd",{"path":189,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":190,"sourceHtmlUrl":191},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlSchemaProperties.xsd",880,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlSchemaProperties.xsd",{"path":193,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":194,"sourceHtmlUrl":195},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesCustom.xsd",2608,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesCustom.xsd",{"path":197,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":198,"sourceHtmlUrl":199},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesExtended.xsd",3507,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesExtended.xsd",{"path":201,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":202,"sourceHtmlUrl":203},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesVariantTypes.xsd",7507,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesVariantTypes.xsd",{"path":205,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":206,"sourceHtmlUrl":207},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-math.xsd",23313,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-math.xsd",{"path":209,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":210,"sourceHtmlUrl":211},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-relationshipReference.xsd",1367,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-relationshipReference.xsd",{"path":213,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":214,"sourceHtmlUrl":215},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fsml.xsd",242277,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fsml.xsd",{"path":217,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":218,"sourceHtmlUrl":219},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-main.xsd",26148,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-main.xsd",{"path":221,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":222,"sourceHtmlUrl":223},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-officeDrawing.xsd",25279,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-officeDrawing.xsd",{"path":225,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":226,"sourceHtmlUrl":227},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-presentationDrawing.xsd",535,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-presentationDrawing.xsd",{"path":229,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":230,"sourceHtmlUrl":231},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-spreadsheetDrawing.xsd",5712,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-spreadsheetDrawing.xsd",{"path":233,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":234,"sourceHtmlUrl":235},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-wordprocessingDrawing.xsd",4010,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-wordprocessingDrawing.xsd",{"path":237,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":238,"sourceHtmlUrl":239},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fwml.xsd",171367,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fwml.xsd",{"path":241,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":242,"sourceHtmlUrl":243},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fxml.xsd",4646,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fxml.xsd",{"path":245,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":246,"sourceHtmlUrl":247},"scripts\u002Foffice\u002Fschemas\u002Fmce\u002Fmc.xsd",3127,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmce\u002Fmc.xsd",{"path":249,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":250,"sourceHtmlUrl":251},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2010.xsd",26549,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2010.xsd",{"path":253,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":254,"sourceHtmlUrl":255},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2012.xsd",3745,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2012.xsd",{"path":257,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":258,"sourceHtmlUrl":259},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2018.xsd",901,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2018.xsd",{"path":261,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":262,"sourceHtmlUrl":263},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cex-2018.xsd",1778,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cex-2018.xsd",{"path":265,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":266,"sourceHtmlUrl":267},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cid-2016.xsd",1002,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cid-2016.xsd",{"path":269,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":270,"sourceHtmlUrl":271},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-sdtdatahash-2020.xsd",600,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-sdtdatahash-2020.xsd",{"path":273,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":274,"sourceHtmlUrl":275},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-symex-2015.xsd",745,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-symex-2015.xsd",{"path":277,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":278,"sourceHtmlUrl":279},"scripts\u002Foffice\u002Fsoffice.py",5301,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fsoffice.py",{"path":281,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":282,"sourceHtmlUrl":283},"scripts\u002Foffice\u002Funpack.py",4052,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Funpack.py",{"path":285,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":286,"sourceHtmlUrl":287},"scripts\u002Foffice\u002Fvalidate.py",3668,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fvalidate.py",{"path":289,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":290,"sourceHtmlUrl":291},"scripts\u002Foffice\u002Fvalidators\u002F__init__.py",336,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fvalidators\u002F__init__.py",{"path":293,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":294,"sourceHtmlUrl":295},"scripts\u002Foffice\u002Fvalidators\u002Fbase.py",32651,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fbase.py",{"path":297,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":298,"sourceHtmlUrl":299},"scripts\u002Foffice\u002Fvalidators\u002Fdocx.py",16376,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fdocx.py",{"path":301,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":302,"sourceHtmlUrl":303},"scripts\u002Foffice\u002Fvalidators\u002Fpptx.py",9824,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fpptx.py",{"path":305,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":306,"sourceHtmlUrl":307},"scripts\u002Foffice\u002Fvalidators\u002Fredlining.py",8918,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fredlining.py",{"path":309,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":310,"sourceHtmlUrl":311},"scripts\u002Frecalc.py",5782,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fxlsx\u002Fscripts\u002Frecalc.py",[313,341,368,401,436,460],{"skillNo":314,"name":315,"nameZh":6,"description":316,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":317,"categories":318,"keywords":324,"publishedAt":44},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[319],{"categoryNo":320,"categoryName":321,"taxonomyType":322,"taxonomyTypeDesc":323},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[325,326,327,328,329,25,330,331,32,23,332,27,333,334,335,336,337,338,339,340],"scoring","pool","wealthville pool scoring","liquidity","which","exit","now","reduce","record","track","verdict","evm","solana","how","public","look",{"skillNo":342,"name":343,"nameZh":6,"description":344,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":345,"categories":346,"keywords":348,"publishedAt":44},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[347],{"categoryNo":320,"categoryName":321,"taxonomyType":322,"taxonomyTypeDesc":323},[349,350,351,352,353,354,355,356,357,358,359,23,360,361,362,363,364,365,366,367],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":369,"name":370,"nameZh":6,"description":371,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":372,"categories":373,"keywords":383,"publishedAt":44},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[374,377,378],{"categoryNo":375,"categoryName":376,"taxonomyType":322,"taxonomyTypeDesc":323},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":320,"categoryName":321,"taxonomyType":322,"taxonomyTypeDesc":323},{"categoryNo":379,"categoryName":380,"taxonomyType":381,"taxonomyTypeDesc":382},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[384,385,386,387,388,389,390,25,391,392,393,394,395,396,397,32,398,399,23,400],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":402,"name":403,"nameZh":6,"description":404,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":405,"licenseFileUrl":406,"sourceHtmlUrl":407,"categories":408,"keywords":412,"publishedAt":44},"01M6AFY6F7CC2BBZP1QD6VTNVC","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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[409],{"categoryNo":410,"categoryName":411,"taxonomyType":322,"taxonomyTypeDesc":323},"01JBSEEDCAT000000000000009","前端开发",[413,414,415,416,417,418,419,420,421,422,423,424,425,426,427,428,429,430,431,432,433,434,25,435],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":437,"name":438,"nameZh":6,"description":439,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":405,"licenseFileUrl":440,"sourceHtmlUrl":441,"categories":442,"keywords":447,"publishedAt":44},"01M6AFWF33SFV9Z3SF4PEEE4BF","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.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[443,446],{"categoryNo":444,"categoryName":445,"taxonomyType":322,"taxonomyTypeDesc":323},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":410,"categoryName":411,"taxonomyType":322,"taxonomyTypeDesc":323},[448,449,450,451,452,414,453,423,424,454,455,456,457,25,458,27,459],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":461,"name":462,"nameZh":6,"description":463,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":405,"licenseFileUrl":464,"sourceHtmlUrl":465,"categories":466,"keywords":474,"publishedAt":44},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[467,470,471],{"categoryNo":468,"categoryName":469,"taxonomyType":322,"taxonomyTypeDesc":323},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":320,"categoryName":321,"taxonomyType":322,"taxonomyTypeDesc":323},{"categoryNo":472,"categoryName":473,"taxonomyType":381,"taxonomyTypeDesc":382},"01JBSEEDCAT000000000000036","内容创作者",[475,476,477,478,479,480,36,481,416,482,426,360,483,484,485,486,487,396,488,23,489,490,491,492,493,338,494],"discernment nudge","nudge","interpretation","help","run","reasoning","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]