[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ADW6MND5FMSFHS8857DAJ8":3,"skill-same:01M6ADW6MND5FMSFHS8857DAJ8":505},{"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":60,"commitSha":61,"skillDirectory":62,"forksCount":63,"repositoryHtmlUrl":64,"repositoryHomepageUrl":65,"ownerHtmlUrl":66,"ownerBlogUrl":67,"ownerDescription":68,"updatedAt":69,"install":70,"resources":83},"01M6ADW6MND5FMSFHS8857DAJ8","optimization-bitsandbytes",null,"Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33418,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-bitsandbytes\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],"Optimization","optimization bitsandbytes","Bitsandbytes","fit","when","accuracy","for","orchestra","formats","INT8","NF4","8-Bit","Memory Optimization","4-Bit","Accelerate","llms","bit","Transformers","HuggingFace","QLoRA","gpu","training","research","memory","inference","2026-11-10 10:12:30",false,"---\nname: optimization-bitsandbytes\ndescription: Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  author: Orchestra Research\n  tags: [Optimization, Bitsandbytes, Quantization, 8-Bit, 4-Bit, Memory Optimization, QLoRA, NF4, INT8, HuggingFace, Efficient Inference]\n  dependencies: [bitsandbytes, transformers, accelerate, torch]\n---\n\n# bitsandbytes - LLM Quantization\n\n## Quick start\n\nbitsandbytes reduces LLM memory by 50% (8-bit) or 75% (4-bit) with \u003C1% accuracy loss.\n\n**Installation**:\n```bash\npip install bitsandbytes transformers accelerate\n```\n\n**8-bit quantization** (50% memory reduction):\n```python\nfrom transformers import AutoModelForCausalLM, BitsAndBytesConfig\n\nconfig = BitsAndBytesConfig(load_in_8bit=True)\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-2-7b-hf\",\n    quantization_config=config,\n    device_map=\"auto\"\n)\n\n# Memory: 14GB → 7GB\n```\n\n**4-bit quantization** (75% memory reduction):\n```python\nconfig = BitsAndBytesConfig(\n    load_in_4bit=True,\n    bnb_4bit_compute_dtype=torch.float16\n)\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-2-7b-hf\",\n    quantization_config=config,\n    device_map=\"auto\"\n)\n\n# Memory: 14GB → 3.5GB\n```\n\n## Common workflows\n\n### Workflow 1: Load large model in limited GPU memory\n\nCopy this checklist:\n\n```\nQuantization Loading:\n- [ ] Step 1: Calculate memory requirements\n- [ ] Step 2: Choose quantization level (4-bit or 8-bit)\n- [ ] Step 3: Configure quantization\n- [ ] Step 4: Load and verify model\n```\n\n**Step 1: Calculate memory requirements**\n\nEstimate model memory:\n```\nFP16 memory (GB) = Parameters × 2 bytes \u002F 1e9\nINT8 memory (GB) = Parameters × 1 byte \u002F 1e9\nINT4 memory (GB) = Parameters × 0.5 bytes \u002F 1e9\n\nExample (Llama 2 7B):\nFP16: 7B × 2 \u002F 1e9 = 14 GB\nINT8: 7B × 1 \u002F 1e9 = 7 GB\nINT4: 7B × 0.5 \u002F 1e9 = 3.5 GB\n```\n\n**Step 2: Choose quantization level**\n\n| GPU VRAM | Model Size | Recommended |\n|----------|------------|-------------|\n| 8 GB | 3B | 4-bit |\n| 12 GB | 7B | 4-bit |\n| 16 GB | 7B | 8-bit or 4-bit |\n| 24 GB | 13B | 8-bit or 70B 4-bit |\n| 40+ GB | 70B | 8-bit |\n\n**Step 3: Configure quantization**\n\nFor 8-bit (better accuracy):\n```python\nfrom transformers import BitsAndBytesConfig\nimport torch\n\nconfig = BitsAndBytesConfig(\n    load_in_8bit=True,\n    llm_int8_threshold=6.0,  # Outlier threshold\n    llm_int8_has_fp16_weight=False\n)\n```\n\nFor 4-bit (maximum memory savings):\n```python\nconfig = BitsAndBytesConfig(\n    load_in_4bit=True,\n    bnb_4bit_compute_dtype=torch.float16,  # Compute in FP16\n    bnb_4bit_quant_type=\"nf4\",  # NormalFloat4 (recommended)\n    bnb_4bit_use_double_quant=True  # Nested quantization\n)\n```\n\n**Step 4: Load and verify model**\n\n```python\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-2-13b-hf\",\n    quantization_config=config,\n    device_map=\"auto\",  # Automatic device placement\n    torch_dtype=torch.float16\n)\n\ntokenizer = AutoTokenizer.from_pretrained(\"meta-llama\u002FLlama-2-13b-hf\")\n\n# Test inference\ninputs = tokenizer(\"Hello, how are you?\", return_tensors=\"pt\").to(\"cuda\")\noutputs = model.generate(**inputs, max_length=50)\nprint(tokenizer.decode(outputs[0]))\n\n# Check memory\nimport torch\nprint(f\"Memory allocated: {torch.cuda.memory_allocated()\u002F1e9:.2f}GB\")\n```\n\n### Workflow 2: Fine-tune with QLoRA (4-bit training)\n\nQLoRA enables fine-tuning large models on consumer GPUs.\n\nCopy this checklist:\n\n```\nQLoRA Fine-tuning:\n- [ ] Step 1: Install dependencies\n- [ ] Step 2: Configure 4-bit base model\n- [ ] Step 3: Add LoRA adapters\n- [ ] Step 4: Train with standard Trainer\n```\n\n**Step 1: Install dependencies**\n\n```bash\npip install bitsandbytes transformers peft accelerate datasets\n```\n\n**Step 2: Configure 4-bit base model**\n\n```python\nfrom transformers import AutoModelForCausalLM, BitsAndBytesConfig\nimport torch\n\nbnb_config = BitsAndBytesConfig(\n    load_in_4bit=True,\n    bnb_4bit_compute_dtype=torch.float16,\n    bnb_4bit_quant_type=\"nf4\",\n    bnb_4bit_use_double_quant=True\n)\n\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-2-7b-hf\",\n    quantization_config=bnb_config,\n    device_map=\"auto\"\n)\n```\n\n**Step 3: Add LoRA adapters**\n\n```python\nfrom peft import LoraConfig, get_peft_model, prepare_model_for_kbit_training\n\n# Prepare model for training\nmodel = prepare_model_for_kbit_training(model)\n\n# Configure LoRA\nlora_config = LoraConfig(\n    r=16,  # LoRA rank\n    lora_alpha=32,  # LoRA alpha\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\n# Add LoRA adapters\nmodel = get_peft_model(model, lora_config)\nmodel.print_trainable_parameters()\n# Output: trainable params: 4.2M || all params: 6.7B || trainable%: 0.06%\n```\n\n**Step 4: Train with standard Trainer**\n\n```python\nfrom transformers import Trainer, TrainingArguments\n\ntraining_args = TrainingArguments(\n    output_dir=\".\u002Fqlora-output\",\n    per_device_train_batch_size=4,\n    gradient_accumulation_steps=4,\n    num_train_epochs=3,\n    learning_rate=2e-4,\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    tokenizer=tokenizer\n)\n\ntrainer.train()\n\n# Save LoRA adapters (only ~20MB)\nmodel.save_pretrained(\".\u002Fqlora-adapters\")\n```\n\n### Workflow 3: 8-bit optimizer for memory-efficient training\n\nUse 8-bit Adam\u002FAdamW to reduce optimizer memory by 75%.\n\n```\n8-bit Optimizer Setup:\n- [ ] Step 1: Replace standard optimizer\n- [ ] Step 2: Configure training\n- [ ] Step 3: Monitor memory savings\n```\n\n**Step 1: Replace standard optimizer**\n\n```python\nimport bitsandbytes as bnb\nfrom transformers import Trainer, TrainingArguments\n\n# Instead of torch.optim.AdamW\nmodel = AutoModelForCausalLM.from_pretrained(\"model-name\")\n\ntraining_args = TrainingArguments(\n    output_dir=\".\u002Foutput\",\n    per_device_train_batch_size=8,\n    optim=\"paged_adamw_8bit\",  # 8-bit optimizer\n    learning_rate=5e-5\n)\n\ntrainer = Trainer(\n    model=model,\n    args=training_args,\n    train_dataset=train_dataset\n)\n\ntrainer.train()\n```\n\n**Manual optimizer usage**:\n```python\nimport bitsandbytes as bnb\n\noptimizer = bnb.optim.AdamW8bit(\n    model.parameters(),\n    lr=1e-4,\n    betas=(0.9, 0.999),\n    eps=1e-8\n)\n\n# Training loop\nfor batch in dataloader:\n    loss = model(**batch).loss\n    loss.backward()\n    optimizer.step()\n    optimizer.zero_grad()\n```\n\n**Step 2: Configure training**\n\nCompare memory:\n```\nStandard AdamW optimizer memory = model_params × 8 bytes (states)\n8-bit AdamW memory = model_params × 2 bytes\nSavings = 75% optimizer memory\n\nExample (Llama 2 7B):\nStandard: 7B × 8 = 56 GB\n8-bit: 7B × 2 = 14 GB\nSavings: 42 GB\n```\n\n**Step 3: Monitor memory savings**\n\n```python\nimport torch\n\nbefore = torch.cuda.memory_allocated()\n\n# Training step\noptimizer.step()\n\nafter = torch.cuda.memory_allocated()\nprint(f\"Memory used: {(after-before)\u002F1e9:.2f}GB\")\n```\n\n## When to use vs alternatives\n\n**Use bitsandbytes when:**\n- GPU memory limited (need to fit larger model)\n- Training with QLoRA (fine-tune 70B on single GPU)\n- Inference only (50-75% memory reduction)\n- Using HuggingFace Transformers\n- Acceptable 0-2% accuracy degradation\n\n**Use alternatives instead:**\n- **GPTQ\u002FAWQ**: Production serving (faster inference than bitsandbytes)\n- **GGUF**: CPU inference (llama.cpp)\n- **FP8**: H100 GPUs (hardware FP8 faster)\n- **Full precision**: Accuracy critical, memory not constrained\n\n## Common issues\n\n**Issue: CUDA error during loading**\n\nInstall matching CUDA version:\n```bash\n# Check CUDA version\nnvcc --version\n\n# Install matching bitsandbytes\npip install bitsandbytes --no-cache-dir\n```\n\n**Issue: Model loading slow**\n\nUse CPU offload for large models:\n```python\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"model-name\",\n    quantization_config=config,\n    device_map=\"auto\",\n    max_memory={0: \"20GB\", \"cpu\": \"30GB\"}  # Offload to CPU\n)\n```\n\n**Issue: Lower accuracy than expected**\n\nTry 8-bit instead of 4-bit:\n```python\nconfig = BitsAndBytesConfig(load_in_8bit=True)\n# 8-bit has \u003C0.5% accuracy loss vs 1-2% for 4-bit\n```\n\nOr use NF4 with double quantization:\n```python\nconfig = BitsAndBytesConfig(\n    load_in_4bit=True,\n    bnb_4bit_quant_type=\"nf4\",  # Better than fp4\n    bnb_4bit_use_double_quant=True  # Extra accuracy\n)\n```\n\n**Issue: OOM even with 4-bit**\n\nEnable CPU offload:\n```python\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"model-name\",\n    quantization_config=config,\n    device_map=\"auto\",\n    offload_folder=\"offload\",  # Disk offload\n    offload_state_dict=True\n)\n```\n\n## Advanced topics\n\n**QLoRA training guide**: See [references\u002Fqlora-training.md](references\u002Fqlora-training.md) for complete fine-tuning workflows, hyperparameter tuning, and multi-GPU training.\n\n**Quantization formats**: See [references\u002Fquantization-formats.md](references\u002Fquantization-formats.md) for INT8, NF4, FP4 comparison, double quantization, and custom quantization configs.\n\n**Memory optimization**: See [references\u002Fmemory-optimization.md](references\u002Fmemory-optimization.md) for CPU offloading strategies, gradient checkpointing, and memory profiling.\n\n## Hardware requirements\n\n- **GPU**: NVIDIA with compute capability 7.0+ (Turing, Ampere, Hopper)\n- **VRAM**: Depends on model and quantization\n  - 4-bit Llama 2 7B: 4GB\n  - 4-bit Llama 2 13B: 8GB\n  - 4-bit Llama 2 70B: 24GB\n- **CUDA**: 11.1+ (12.0+ recommended)\n- **PyTorch**: 2.0+\n\n**Supported platforms**: NVIDIA GPUs (primary), AMD ROCm, Intel GPUs (experimental)\n\n## Resources\n\n- GitHub: https:\u002F\u002Fgithub.com\u002Fbitsandbytes-foundation\u002Fbitsandbytes\n- HuggingFace docs: https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Ftransformers\u002Fquantization\u002Fbitsandbytes\n- QLoRA paper: \"QLoRA: Efficient Finetuning of Quantized LLMs\" (2023)\n- LLM.int8() paper: \"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale\" (2022)\n\n\n\n","# bitsandbytes - LLM Quantization\n\n## Quick start\n\nbitsandbytes reduces LLM memory by 50% (8-bit) or 75% (4-bit) with \u003C1% accuracy loss.\n\n**Installation**:\n```bash\npip install bitsandbytes transformers accelerate\n```\n\n**8-bit quantization** (50% memory reduction):\n```python\nfrom transformers import AutoModelForCausalLM, BitsAndBytesConfig\n\nconfig = BitsAndBytesConfig(load_in_8bit=True)\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-2-7b-hf\",\n    quantization_config=config,\n    device_map=\"auto\"\n)\n\n# Memory: 14GB → 7GB\n```\n\n**4-bit quantization** (75% memory reduction):\n```python\nconfig = BitsAndBytesConfig(\n    load_in_4bit=True,\n    bnb_4bit_compute_dtype=torch.float16\n)\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-2-7b-hf\",\n    quantization_config=config,\n    device_map=\"auto\"\n)\n\n# Memory: 14GB → 3.5GB\n```\n\n## Common workflows\n\n### Workflow 1: Load large model in limited GPU memory\n\nCopy this checklist:\n\n```\nQuantization Loading:\n- [ ] Step 1: Calculate memory requirements\n- [ ] Step 2: Choose quantization level (4-bit or 8-bit)\n- [ ] Step 3: Configure quantization\n- [ ] Step 4: Load and verify model\n```\n\n**Step 1: Calculate memory requirements**\n\nEstimate model memory:\n```\nFP16 memory (GB) = Parameters × 2 bytes \u002F 1e9\nINT8 memory (GB) = Parameters × 1 byte \u002F 1e9\nINT4 memory (GB) = Parameters × 0.5 bytes \u002F 1e9\n\nExample (Llama 2 7B):\nFP16: 7B × 2 \u002F 1e9 = 14 GB\nINT8: 7B × 1 \u002F 1e9 = 7 GB\nINT4: 7B × 0.5 \u002F 1e9 = 3.5 GB\n```\n\n**Step 2: Choose quantization level**\n\n| GPU VRAM | Model Size | Recommended |\n|----------|------------|-------------|\n| 8 GB | 3B | 4-bit |\n| 12 GB | 7B | 4-bit |\n| 16 GB | 7B | 8-bit or 4-bit |\n| 24 GB | 13B | 8-bit or 70B 4-bit |\n| 40+ GB | 70B | 8-bit |\n\n**Step 3: Configure quantization**\n\nFor 8-bit (better accuracy):\n```python\nfrom transformers import BitsAndBytesConfig\nimport torch\n\nconfig = BitsAndBytesConfig(\n    load_in_8bit=True,\n    llm_int8_threshold=6.0,  # Outlier threshold\n    llm_int8_has_fp16_weight=False\n)\n```\n\nFor 4-bit (maximum memory savings):\n```python\nconfig = BitsAndBytesConfig(\n    load_in_4bit=True,\n    bnb_4bit_compute_dtype=torch.float16,  # Compute in FP16\n    bnb_4bit_quant_type=\"nf4\",  # NormalFloat4 (recommended)\n    bnb_4bit_use_double_quant=True  # Nested quantization\n)\n```\n\n**Step 4: Load and verify model**\n\n```python\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-2-13b-hf\",\n    quantization_config=config,\n    device_map=\"auto\",  # Automatic device placement\n    torch_dtype=torch.float16\n)\n\ntokenizer = AutoTokenizer.from_pretrained(\"meta-llama\u002FLlama-2-13b-hf\")\n\n# Test inference\ninputs = tokenizer(\"Hello, how are you?\", return_tensors=\"pt\").to(\"cuda\")\noutputs = model.generate(**inputs, max_length=50)\nprint(tokenizer.decode(outputs[0]))\n\n# Check memory\nimport torch\nprint(f\"Memory allocated: {torch.cuda.memory_allocated()\u002F1e9:.2f}GB\")\n```\n\n### Workflow 2: Fine-tune with QLoRA (4-bit training)\n\nQLoRA enables fine-tuning large models on consumer GPUs.\n\nCopy this checklist:\n\n```\nQLoRA Fine-tuning:\n- [ ] Step 1: Install dependencies\n- [ ] Step 2: Configure 4-bit base model\n- [ ] Step 3: Add LoRA adapters\n- [ ] Step 4: Train with standard Trainer\n```\n\n**Step 1: Install dependencies**\n\n```bash\npip install bitsandbytes transformers peft accelerate datasets\n```\n\n**Step 2: Configure 4-bit base model**\n\n```python\nfrom transformers import AutoModelForCausalLM, BitsAndBytesConfig\nimport torch\n\nbnb_config = BitsAndBytesConfig(\n    load_in_4bit=True,\n    bnb_4bit_compute_dtype=torch.float16,\n    bnb_4bit_quant_type=\"nf4\",\n    bnb_4bit_use_double_quant=True\n)\n\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"meta-llama\u002FLlama-2-7b-hf\",\n    quantization_config=bnb_config,\n    device_map=\"auto\"\n)\n```\n\n**Step 3: Add LoRA adapters**\n\n```python\nfrom peft import LoraConfig, get_peft_model, prepare_model_for_kbit_training\n\n# Prepare model for training\nmodel = prepare_model_for_kbit_training(model)\n\n# Configure LoRA\nlora_config = LoraConfig(\n    r=16,  # LoRA rank\n    lora_alpha=32,  # LoRA alpha\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\n# Add LoRA adapters\nmodel = get_peft_model(model, lora_config)\nmodel.print_trainable_parameters()\n# Output: trainable params: 4.2M || all params: 6.7B || trainable%: 0.06%\n```\n\n**Step 4: Train with standard Trainer**\n\n```python\nfrom transformers import Trainer, TrainingArguments\n\ntraining_args = TrainingArguments(\n    output_dir=\".\u002Fqlora-output\",\n    per_device_train_batch_size=4,\n    gradient_accumulation_steps=4,\n    num_train_epochs=3,\n    learning_rate=2e-4,\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    tokenizer=tokenizer\n)\n\ntrainer.train()\n\n# Save LoRA adapters (only ~20MB)\nmodel.save_pretrained(\".\u002Fqlora-adapters\")\n```\n\n### Workflow 3: 8-bit optimizer for memory-efficient training\n\nUse 8-bit Adam\u002FAdamW to reduce optimizer memory by 75%.\n\n```\n8-bit Optimizer Setup:\n- [ ] Step 1: Replace standard optimizer\n- [ ] Step 2: Configure training\n- [ ] Step 3: Monitor memory savings\n```\n\n**Step 1: Replace standard optimizer**\n\n```python\nimport bitsandbytes as bnb\nfrom transformers import Trainer, TrainingArguments\n\n# Instead of torch.optim.AdamW\nmodel = AutoModelForCausalLM.from_pretrained(\"model-name\")\n\ntraining_args = TrainingArguments(\n    output_dir=\".\u002Foutput\",\n    per_device_train_batch_size=8,\n    optim=\"paged_adamw_8bit\",  # 8-bit optimizer\n    learning_rate=5e-5\n)\n\ntrainer = Trainer(\n    model=model,\n    args=training_args,\n    train_dataset=train_dataset\n)\n\ntrainer.train()\n```\n\n**Manual optimizer usage**:\n```python\nimport bitsandbytes as bnb\n\noptimizer = bnb.optim.AdamW8bit(\n    model.parameters(),\n    lr=1e-4,\n    betas=(0.9, 0.999),\n    eps=1e-8\n)\n\n# Training loop\nfor batch in dataloader:\n    loss = model(**batch).loss\n    loss.backward()\n    optimizer.step()\n    optimizer.zero_grad()\n```\n\n**Step 2: Configure training**\n\nCompare memory:\n```\nStandard AdamW optimizer memory = model_params × 8 bytes (states)\n8-bit AdamW memory = model_params × 2 bytes\nSavings = 75% optimizer memory\n\nExample (Llama 2 7B):\nStandard: 7B × 8 = 56 GB\n8-bit: 7B × 2 = 14 GB\nSavings: 42 GB\n```\n\n**Step 3: Monitor memory savings**\n\n```python\nimport torch\n\nbefore = torch.cuda.memory_allocated()\n\n# Training step\noptimizer.step()\n\nafter = torch.cuda.memory_allocated()\nprint(f\"Memory used: {(after-before)\u002F1e9:.2f}GB\")\n```\n\n## When to use vs alternatives\n\n**Use bitsandbytes when:**\n- GPU memory limited (need to fit larger model)\n- Training with QLoRA (fine-tune 70B on single GPU)\n- Inference only (50-75% memory reduction)\n- Using HuggingFace Transformers\n- Acceptable 0-2% accuracy degradation\n\n**Use alternatives instead:**\n- **GPTQ\u002FAWQ**: Production serving (faster inference than bitsandbytes)\n- **GGUF**: CPU inference (llama.cpp)\n- **FP8**: H100 GPUs (hardware FP8 faster)\n- **Full precision**: Accuracy critical, memory not constrained\n\n## Common issues\n\n**Issue: CUDA error during loading**\n\nInstall matching CUDA version:\n```bash\n# Check CUDA version\nnvcc --version\n\n# Install matching bitsandbytes\npip install bitsandbytes --no-cache-dir\n```\n\n**Issue: Model loading slow**\n\nUse CPU offload for large models:\n```python\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"model-name\",\n    quantization_config=config,\n    device_map=\"auto\",\n    max_memory={0: \"20GB\", \"cpu\": \"30GB\"}  # Offload to CPU\n)\n```\n\n**Issue: Lower accuracy than expected**\n\nTry 8-bit instead of 4-bit:\n```python\nconfig = BitsAndBytesConfig(load_in_8bit=True)\n# 8-bit has \u003C0.5% accuracy loss vs 1-2% for 4-bit\n```\n\nOr use NF4 with double quantization:\n```python\nconfig = BitsAndBytesConfig(\n    load_in_4bit=True,\n    bnb_4bit_quant_type=\"nf4\",  # Better than fp4\n    bnb_4bit_use_double_quant=True  # Extra accuracy\n)\n```\n\n**Issue: OOM even with 4-bit**\n\nEnable CPU offload:\n```python\nmodel = AutoModelForCausalLM.from_pretrained(\n    \"model-name\",\n    quantization_config=config,\n    device_map=\"auto\",\n    offload_folder=\"offload\",  # Disk offload\n    offload_state_dict=True\n)\n```\n\n## Advanced topics\n\n**QLoRA training guide**: See [references\u002Fqlora-training.md](references\u002Fqlora-training.md) for complete fine-tuning workflows, hyperparameter tuning, and multi-GPU training.\n\n**Quantization formats**: See [references\u002Fquantization-formats.md](references\u002Fquantization-formats.md) for INT8, NF4, FP4 comparison, double quantization, and custom quantization configs.\n\n**Memory optimization**: See [references\u002Fmemory-optimization.md](references\u002Fmemory-optimization.md) for CPU offloading strategies, gradient checkpointing, and memory profiling.\n\n## Hardware requirements\n\n- **GPU**: NVIDIA with compute capability 7.0+ (Turing, Ampere, Hopper)\n- **VRAM**: Depends on model and quantization\n  - 4-bit Llama 2 7B: 4GB\n  - 4-bit Llama 2 13B: 8GB\n  - 4-bit Llama 2 70B: 24GB\n- **CUDA**: 11.1+ (12.0+ recommended)\n- **PyTorch**: 2.0+\n\n**Supported platforms**: NVIDIA GPUs (primary), AMD ROCm, Intel GPUs (experimental)\n\n## Resources\n\n- GitHub: https:\u002F\u002Fgithub.com\u002Fbitsandbytes-foundation\u002Fbitsandbytes\n- HuggingFace docs: https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Ftransformers\u002Fquantization\u002Fbitsandbytes\n- QLoRA paper: \"QLoRA: Efficient Finetuning of Quantized LLMs\" (2023)\n- LLM.int8() paper: \"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale\" (2022)\n\n\n\n",{"name":5,"license":15,"metadata":49,"description":7},{"tags":50,"author":53,"version":54,"dependencies":55},[19,21,51,30,32,31,38,29,28,37,52],"Quantization","Efficient Inference","Orchestra Research","1.0.0",[56,57,58,59],"bitsandbytes","transformers","accelerate","torch","main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-bitsandbytes",3926,"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","2026-11-12 14:45:56",{"source":8,"skillName":5,"commands":71,"prompt":81,"zipAvailable":82},[72,75,78],{"tool":73,"command":74},"npx","npx skills add davila7\u002Fclaude-code-templates --skill optimization-bitsandbytes",{"tool":76,"command":77},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill optimization-bitsandbytes",{"tool":79,"command":80},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill optimization-bitsandbytes","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-bitsandbytes\u002FSKILL.md",true,[84,90,94,100,104,108,112,116,120,124,128,132,136,140,144,148,152,156,160,164,168,172,176,180,184,188,192,196,200,204,208,212,216,220,224,228,232,236,240,244,248,252,256,260,266,270,274,278,282,286,290,294,298,302,306,310,314,318,322,326,330,333,337,341,345,348,351,354,357,360,363,366,369,372,375,378,381,384,387,390,393,396,399,402,405,408,411,414,417,420,423,426,429,432,435,438,441,444,447,450,453,456,459,462,466,470,474,477,481,485,489,493,497,501],{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"editing.md","REFERENCE","参考文档",6885,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fediting.md",{"path":91,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":92,"sourceHtmlUrl":93},"html2pptx.md",19859,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fhtml2pptx.md",{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":98,"sourceHtmlUrl":99},"LICENSE.txt","LICENSE","许可证",1467,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002FLICENSE.txt",{"path":101,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":102,"sourceHtmlUrl":103},"ooxml.md",10388,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml.md",{"path":105,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":106,"sourceHtmlUrl":107},"ooxml\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-contentTypes.xsd",1963,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-contentTypes.xsd",{"path":109,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":110,"sourceHtmlUrl":111},"ooxml\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-coreProperties.xsd",2515,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-coreProperties.xsd",{"path":113,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":114,"sourceHtmlUrl":115},"ooxml\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-digSig.xsd",2856,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-digSig.xsd",{"path":117,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":118,"sourceHtmlUrl":119},"ooxml\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-relationships.xsd",1344,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-relationships.xsd",{"path":121,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":122,"sourceHtmlUrl":123},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chart.xsd",{"path":125,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":126,"sourceHtmlUrl":127},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chartDrawing.xsd",{"path":129,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":130,"sourceHtmlUrl":131},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-diagram.xsd",{"path":133,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":134,"sourceHtmlUrl":135},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-lockedCanvas.xsd",{"path":137,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":138,"sourceHtmlUrl":139},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-main.xsd",{"path":141,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":142,"sourceHtmlUrl":143},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-picture.xsd",{"path":145,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":146,"sourceHtmlUrl":147},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-spreadsheetDrawing.xsd",{"path":149,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":150,"sourceHtmlUrl":151},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-wordprocessingDrawing.xsd",{"path":153,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":154,"sourceHtmlUrl":155},"ooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fpml.xsd",83612,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fpml.xsd",{"path":157,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":158,"sourceHtmlUrl":159},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-additionalCharacteristics.xsd",{"path":161,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":162,"sourceHtmlUrl":163},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-bibliography.xsd",{"path":165,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":166,"sourceHtmlUrl":167},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-commonSimpleTypes.xsd",{"path":169,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":170,"sourceHtmlUrl":171},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlDataProperties.xsd",{"path":173,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":174,"sourceHtmlUrl":175},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlSchemaProperties.xsd",{"path":177,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":178,"sourceHtmlUrl":179},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesCustom.xsd",{"path":181,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":182,"sourceHtmlUrl":183},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesExtended.xsd",{"path":185,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":186,"sourceHtmlUrl":187},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesVariantTypes.xsd",{"path":189,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":190,"sourceHtmlUrl":191},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-math.xsd",{"path":193,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":194,"sourceHtmlUrl":195},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-relationshipReference.xsd",{"path":197,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":198,"sourceHtmlUrl":199},"ooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fsml.xsd",242277,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fsml.xsd",{"path":201,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":202,"sourceHtmlUrl":203},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-main.xsd",{"path":205,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":206,"sourceHtmlUrl":207},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-officeDrawing.xsd",{"path":209,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":210,"sourceHtmlUrl":211},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-presentationDrawing.xsd",{"path":213,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":214,"sourceHtmlUrl":215},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-spreadsheetDrawing.xsd",{"path":217,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":218,"sourceHtmlUrl":219},"ooxml\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\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-wordprocessingDrawing.xsd",{"path":221,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":222,"sourceHtmlUrl":223},"ooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fwml.xsd",171367,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fwml.xsd",{"path":225,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":226,"sourceHtmlUrl":227},"ooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fxml.xsd",4646,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fxml.xsd",{"path":229,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":230,"sourceHtmlUrl":231},"ooxml\u002Fschemas\u002Fmce\u002Fmc.xsd",3127,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002Fmce\u002Fmc.xsd",{"path":233,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":234,"sourceHtmlUrl":235},"ooxml\u002Fschemas\u002Fmicrosoft\u002Fwml-2010.xsd",26549,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002Fmicrosoft\u002Fwml-2010.xsd",{"path":237,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":238,"sourceHtmlUrl":239},"ooxml\u002Fschemas\u002Fmicrosoft\u002Fwml-2012.xsd",3745,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002Fmicrosoft\u002Fwml-2012.xsd",{"path":241,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":242,"sourceHtmlUrl":243},"ooxml\u002Fschemas\u002Fmicrosoft\u002Fwml-2018.xsd",901,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002Fmicrosoft\u002Fwml-2018.xsd",{"path":245,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":246,"sourceHtmlUrl":247},"ooxml\u002Fschemas\u002Fmicrosoft\u002Fwml-cex-2018.xsd",1778,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002Fmicrosoft\u002Fwml-cex-2018.xsd",{"path":249,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":250,"sourceHtmlUrl":251},"ooxml\u002Fschemas\u002Fmicrosoft\u002Fwml-cid-2016.xsd",1002,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002Fmicrosoft\u002Fwml-cid-2016.xsd",{"path":253,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":254,"sourceHtmlUrl":255},"ooxml\u002Fschemas\u002Fmicrosoft\u002Fwml-sdtdatahash-2020.xsd",600,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002Fmicrosoft\u002Fwml-sdtdatahash-2020.xsd",{"path":257,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":258,"sourceHtmlUrl":259},"ooxml\u002Fschemas\u002Fmicrosoft\u002Fwml-symex-2015.xsd",745,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fschemas\u002Fmicrosoft\u002Fwml-symex-2015.xsd",{"path":261,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":264,"sourceHtmlUrl":265},"ooxml\u002Fscripts\u002Fpack.py","SCRIPT","脚本",5596,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fscripts\u002Fpack.py",{"path":267,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":268,"sourceHtmlUrl":269},"ooxml\u002Fscripts\u002Funpack.py",1037,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fscripts\u002Funpack.py",{"path":271,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":272,"sourceHtmlUrl":273},"ooxml\u002Fscripts\u002Fvalidate.py",1959,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fscripts\u002Fvalidate.py",{"path":275,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":276,"sourceHtmlUrl":277},"ooxml\u002Fscripts\u002Fvalidation\u002F__init__.py",336,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fscripts\u002Fvalidation\u002F__init__.py",{"path":279,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":280,"sourceHtmlUrl":281},"ooxml\u002Fscripts\u002Fvalidation\u002Fbase.py",39892,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fscripts\u002Fvalidation\u002Fbase.py",{"path":283,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":284,"sourceHtmlUrl":285},"ooxml\u002Fscripts\u002Fvalidation\u002Fdocx.py",9996,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fscripts\u002Fvalidation\u002Fdocx.py",{"path":287,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":288,"sourceHtmlUrl":289},"ooxml\u002Fscripts\u002Fvalidation\u002Fpptx.py",12327,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fscripts\u002Fvalidation\u002Fpptx.py",{"path":291,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":292,"sourceHtmlUrl":293},"ooxml\u002Fscripts\u002Fvalidation\u002Fredlining.py",11179,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fooxml\u002Fscripts\u002Fvalidation\u002Fredlining.py",{"path":295,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":296,"sourceHtmlUrl":297},"pptxgenjs.md",12819,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fpptxgenjs.md",{"path":299,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":300,"sourceHtmlUrl":301},"references\u002Fmemory-optimization.md",12642,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-bitsandbytes\u002Freferences\u002Fmemory-optimization.md",{"path":303,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":304,"sourceHtmlUrl":305},"references\u002Fqlora-training.md",12015,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-bitsandbytes\u002Freferences\u002Fqlora-training.md",{"path":307,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":308,"sourceHtmlUrl":309},"references\u002Fquantization-formats.md",10258,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Foptimization-bitsandbytes\u002Freferences\u002Fquantization-formats.md",{"path":311,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":312,"sourceHtmlUrl":313},"scripts\u002F__init__.py",0,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002F__init__.py",{"path":315,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":316,"sourceHtmlUrl":317},"scripts\u002Fadd_slide.py",6872,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Fadd_slide.py",{"path":319,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":320,"sourceHtmlUrl":321},"scripts\u002Fclean.py",9583,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Fclean.py",{"path":323,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":324,"sourceHtmlUrl":325},"scripts\u002Fhtml2pptx.js",37795,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Fhtml2pptx.js",{"path":327,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":328,"sourceHtmlUrl":329},"scripts\u002Finventory.py",38126,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Finventory.py",{"path":331,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":312,"sourceHtmlUrl":332},"scripts\u002Foffice\u002Fhelpers\u002F__init__.py","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fhelpers\u002F__init__.py",{"path":334,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":335,"sourceHtmlUrl":336},"scripts\u002Foffice\u002Fhelpers\u002Fmerge_runs.py",5567,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fhelpers\u002Fmerge_runs.py",{"path":338,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":339,"sourceHtmlUrl":340},"scripts\u002Foffice\u002Fhelpers\u002Fsimplify_redlines.py",5754,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fhelpers\u002Fsimplify_redlines.py",{"path":342,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":343,"sourceHtmlUrl":344},"scripts\u002Foffice\u002Fpack.py",4991,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fpack.py",{"path":346,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":106,"sourceHtmlUrl":347},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-contentTypes.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-contentTypes.xsd",{"path":349,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":110,"sourceHtmlUrl":350},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-coreProperties.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-coreProperties.xsd",{"path":352,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":114,"sourceHtmlUrl":353},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-digSig.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-digSig.xsd",{"path":355,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":118,"sourceHtmlUrl":356},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-relationships.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-relationships.xsd",{"path":358,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":122,"sourceHtmlUrl":359},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chart.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chart.xsd",{"path":361,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":126,"sourceHtmlUrl":362},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chartDrawing.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chartDrawing.xsd",{"path":364,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":130,"sourceHtmlUrl":365},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-diagram.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-diagram.xsd",{"path":367,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":134,"sourceHtmlUrl":368},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-lockedCanvas.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-lockedCanvas.xsd",{"path":370,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":138,"sourceHtmlUrl":371},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-main.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-main.xsd",{"path":373,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":142,"sourceHtmlUrl":374},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-picture.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-picture.xsd",{"path":376,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":146,"sourceHtmlUrl":377},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-spreadsheetDrawing.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-spreadsheetDrawing.xsd",{"path":379,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":150,"sourceHtmlUrl":380},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-wordprocessingDrawing.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-wordprocessingDrawing.xsd",{"path":382,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":154,"sourceHtmlUrl":383},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fpml.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fpml.xsd",{"path":385,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":158,"sourceHtmlUrl":386},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-additionalCharacteristics.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-additionalCharacteristics.xsd",{"path":388,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":162,"sourceHtmlUrl":389},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-bibliography.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-bibliography.xsd",{"path":391,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":166,"sourceHtmlUrl":392},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-commonSimpleTypes.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-commonSimpleTypes.xsd",{"path":394,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":170,"sourceHtmlUrl":395},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlDataProperties.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlDataProperties.xsd",{"path":397,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":174,"sourceHtmlUrl":398},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlSchemaProperties.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlSchemaProperties.xsd",{"path":400,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":178,"sourceHtmlUrl":401},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesCustom.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesCustom.xsd",{"path":403,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":182,"sourceHtmlUrl":404},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesExtended.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesExtended.xsd",{"path":406,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":186,"sourceHtmlUrl":407},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesVariantTypes.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesVariantTypes.xsd",{"path":409,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":190,"sourceHtmlUrl":410},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-math.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-math.xsd",{"path":412,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":194,"sourceHtmlUrl":413},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-relationshipReference.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-relationshipReference.xsd",{"path":415,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":198,"sourceHtmlUrl":416},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fsml.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fsml.xsd",{"path":418,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":202,"sourceHtmlUrl":419},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-main.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-main.xsd",{"path":421,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":206,"sourceHtmlUrl":422},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-officeDrawing.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-officeDrawing.xsd",{"path":424,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":210,"sourceHtmlUrl":425},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-presentationDrawing.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-presentationDrawing.xsd",{"path":427,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":214,"sourceHtmlUrl":428},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-spreadsheetDrawing.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-spreadsheetDrawing.xsd",{"path":430,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":218,"sourceHtmlUrl":431},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-wordprocessingDrawing.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-wordprocessingDrawing.xsd",{"path":433,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":222,"sourceHtmlUrl":434},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fwml.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fwml.xsd",{"path":436,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":226,"sourceHtmlUrl":437},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fxml.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fxml.xsd",{"path":439,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":230,"sourceHtmlUrl":440},"scripts\u002Foffice\u002Fschemas\u002Fmce\u002Fmc.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmce\u002Fmc.xsd",{"path":442,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":234,"sourceHtmlUrl":443},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2010.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2010.xsd",{"path":445,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":238,"sourceHtmlUrl":446},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2012.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2012.xsd",{"path":448,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":242,"sourceHtmlUrl":449},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2018.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2018.xsd",{"path":451,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":246,"sourceHtmlUrl":452},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cex-2018.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cex-2018.xsd",{"path":454,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":250,"sourceHtmlUrl":455},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cid-2016.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cid-2016.xsd",{"path":457,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":254,"sourceHtmlUrl":458},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-sdtdatahash-2020.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-sdtdatahash-2020.xsd",{"path":460,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":258,"sourceHtmlUrl":461},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-symex-2015.xsd","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-symex-2015.xsd",{"path":463,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":464,"sourceHtmlUrl":465},"scripts\u002Foffice\u002Fsoffice.py",5301,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fsoffice.py",{"path":467,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":468,"sourceHtmlUrl":469},"scripts\u002Foffice\u002Funpack.py",4052,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Funpack.py",{"path":471,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":472,"sourceHtmlUrl":473},"scripts\u002Foffice\u002Fvalidate.py",3668,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fvalidate.py",{"path":475,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":276,"sourceHtmlUrl":476},"scripts\u002Foffice\u002Fvalidators\u002F__init__.py","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fvalidators\u002F__init__.py",{"path":478,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":479,"sourceHtmlUrl":480},"scripts\u002Foffice\u002Fvalidators\u002Fbase.py",32651,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fbase.py",{"path":482,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":483,"sourceHtmlUrl":484},"scripts\u002Foffice\u002Fvalidators\u002Fdocx.py",16376,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fdocx.py",{"path":486,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":487,"sourceHtmlUrl":488},"scripts\u002Foffice\u002Fvalidators\u002Fpptx.py",9824,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fpptx.py",{"path":490,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":491,"sourceHtmlUrl":492},"scripts\u002Foffice\u002Fvalidators\u002Fredlining.py",8918,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fredlining.py",{"path":494,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":495,"sourceHtmlUrl":496},"scripts\u002Frearrange.py",8514,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Frearrange.py",{"path":498,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":499,"sourceHtmlUrl":500},"scripts\u002Freplace.py",13594,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Freplace.py",{"path":502,"resourceType":262,"resourceTypeDesc":263,"sizeBytes":503,"sourceHtmlUrl":504},"scripts\u002Fthumbnail.py",8785,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdocument-processing\u002Fpptx\u002Fscripts\u002Fthumbnail.py",[506,536,563,596,631,655],{"skillNo":507,"name":508,"nameZh":6,"description":509,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":510,"categories":511,"keywords":517,"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",[512],{"categoryNo":513,"categoryName":514,"taxonomyType":515,"taxonomyTypeDesc":516},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[518,519,520,521,522,25,523,524,525,23,526,527,528,529,530,531,532,533,534,535],"scoring","pool","wealthville pool scoring","liquidity","which","exit","now","use","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":537,"name":538,"nameZh":6,"description":539,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":540,"categories":541,"keywords":543,"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",[542],{"categoryNo":513,"categoryName":514,"taxonomyType":515,"taxonomyTypeDesc":516},[544,545,546,547,548,549,550,551,552,553,554,23,555,556,557,558,559,560,561,562],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":564,"name":565,"nameZh":6,"description":566,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":567,"categories":568,"keywords":578,"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",[569,572,573],{"categoryNo":570,"categoryName":571,"taxonomyType":515,"taxonomyTypeDesc":516},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":513,"categoryName":514,"taxonomyType":515,"taxonomyTypeDesc":516},{"categoryNo":574,"categoryName":575,"taxonomyType":576,"taxonomyTypeDesc":577},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[579,580,581,582,583,584,585,25,586,587,588,589,590,591,592,525,593,594,23,595],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":597,"name":598,"nameZh":6,"description":599,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":600,"licenseFileUrl":601,"sourceHtmlUrl":602,"categories":603,"keywords":607,"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",[604],{"categoryNo":605,"categoryName":606,"taxonomyType":515,"taxonomyTypeDesc":516},"01JBSEEDCAT000000000000009","前端开发",[608,609,610,611,612,613,614,615,616,617,618,619,620,621,622,623,624,625,626,627,628,629,25,630],"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":632,"name":633,"nameZh":6,"description":634,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":600,"licenseFileUrl":635,"sourceHtmlUrl":636,"categories":637,"keywords":642,"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",[638,641],{"categoryNo":639,"categoryName":640,"taxonomyType":515,"taxonomyTypeDesc":516},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":605,"categoryName":606,"taxonomyType":515,"taxonomyTypeDesc":516},[643,644,645,646,647,609,648,618,619,649,650,651,652,25,653,527,654],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":656,"name":657,"nameZh":6,"description":658,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":600,"licenseFileUrl":659,"sourceHtmlUrl":660,"categories":661,"keywords":669,"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",[662,665,666],{"categoryNo":663,"categoryName":664,"taxonomyType":515,"taxonomyTypeDesc":516},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":513,"categoryName":514,"taxonomyType":515,"taxonomyTypeDesc":516},{"categoryNo":667,"categoryName":668,"taxonomyType":576,"taxonomyTypeDesc":577},"01JBSEEDCAT000000000000036","内容创作者",[670,671,672,673,674,675,676,677,611,678,621,555,679,680,681,682,683,591,684,23,685,686,687,688,689,533,690],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]