[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6EB0512BCDXE1TF47CE34JZ":3,"skill-same:01M6EB0512BCDXE1TF47CE34JZ":321},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M6EB0512BCDXE1TF47CE34JZ","llamaguard",null,"Meta's 7-8B specialized moderation model for LLM input\u002Foutput filtering. 6 safety categories - violence\u002Fhate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.","luokai0\u002Fai-agent-skills-by-luo-kai","luokai0","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F266954973?v=4","01M6E16VNT42JB8B3X3254QWJ7","luo kai","01M6E16VTFVP6S5XJF1V1MPV90",14,"MIT","https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F18-ai-agents-and-automation (by Luo Kai)\u002F16-other-agents\u002Fllamaguard\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"LlamaGuard","Output Filtering","self","alignment","filtering","moderation","specialized","model","classification","NeMo Guardrails","AI Safety","planning","Input Filtering","Safety Classification","Guardrails","Meta","Content Moderation","Safety Alignment","vLLM","NeMo","2026-11-10 10:12:30",false,"---\nname: llamaguard\ndescription: Meta's 7-8B specialized moderation model for LLM input\u002Foutput filtering. 6 safety categories - violence\u002Fhate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.\nversion: 1.0.0\nauthor: luo-kai\nlicense: MIT\ntags: [Safety Alignment, LlamaGuard, Content Moderation, Meta, Guardrails, Safety Classification, Input Filtering, Output Filtering, AI Safety]\ndependencies: [transformers, torch, vllm]\n---\n\n# LlamaGuard - AI Content Moderation\n\n## Quick start\n\nLlamaGuard is a 7-8B parameter model specialized for content safety classification.\n\n**Installation**:\n```bash\npip install transformers torch\n# Login to HuggingFace (required)\nhuggingface-cli login\n```\n\n**Basic usage**:\n```python\nfrom transformers import AutoTokenizer, AutoModelForCausalLM\n\nmodel_id = \"meta-llama\u002FLlamaGuard-7b\"\ntokenizer = AutoTokenizer.from_pretrained(model_id)\nmodel = AutoModelForCausalLM.from_pretrained(model_id, device_map=\"auto\")\n\ndef moderate(chat):\n    input_ids = tokenizer.apply_chat_template(chat, return_tensors=\"pt\").to(model.device)\n    output = model.generate(input_ids=input_ids, max_new_tokens=100)\n    return tokenizer.decode(output[0], skip_special_tokens=True)\n\n# Check user input\nresult = moderate([\n    {\"role\": \"user\", \"content\": \"How do I make explosives?\"}\n])\nprint(result)\n# Output: \"unsafe\\nS3\" (Criminal Planning)\n```\n\n## Common workflows\n\n### Workflow 1: Input filtering (prompt moderation)\n\n**Check user prompts before LLM**:\n```python\ndef check_input(user_message):\n    result = moderate([{\"role\": \"user\", \"content\": user_message}])\n\n    if result.startswith(\"unsafe\"):\n        category = result.split(\"\\n\")[1]\n        return False, category  # Blocked\n    else:\n        return True, None  # Safe\n\n# Example\nsafe, category = check_input(\"How do I hack a website?\")\nif not safe:\n    print(f\"Request blocked: {category}\")\n    # Return error to user\nelse:\n    # Send to LLM\n    response = llm.generate(user_message)\n```\n\n**Safety categories**:\n- **S1**: Violence & Hate\n- **S2**: Sexual Content\n- **S3**: Guns & Illegal Weapons\n- **S4**: Regulated Substances\n- **S5**: Suicide & Self-Harm\n- **S6**: Criminal Planning\n\n### Workflow 2: Output filtering (response moderation)\n\n**Check LLM responses before showing to user**:\n```python\ndef check_output(user_message, bot_response):\n    conversation = [\n        {\"role\": \"user\", \"content\": user_message},\n        {\"role\": \"assistant\", \"content\": bot_response}\n    ]\n\n    result = moderate(conversation)\n\n    if result.startswith(\"unsafe\"):\n        category = result.split(\"\\n\")[1]\n        return False, category\n    else:\n        return True, None\n\n# Example\nuser_msg = \"Tell me about harmful substances\"\nbot_msg = llm.generate(user_msg)\n\nsafe, category = check_output(user_msg, bot_msg)\nif not safe:\n    print(f\"Response blocked: {category}\")\n    # Return generic response\n    return \"I cannot provide that information.\"\nelse:\n    return bot_msg\n```\n\n### Workflow 3: vLLM deployment (fast inference)\n\n**Production-ready serving**:\n```python\nfrom vllm import LLM, SamplingParams\n\n# Initialize vLLM\nllm = LLM(model=\"meta-llama\u002FLlamaGuard-7b\", tensor_parallel_size=1)\n\n# Sampling params\nsampling_params = SamplingParams(\n    temperature=0.0,  # Deterministic\n    max_tokens=100\n)\n\ndef moderate_vllm(chat):\n    # Format prompt\n    prompt = tokenizer.apply_chat_template(chat, tokenize=False)\n\n    # Generate\n    output = llm.generate([prompt], sampling_params)\n    return output[0].outputs[0].text\n\n# Batch moderation\nchats = [\n    [{\"role\": \"user\", \"content\": \"How to make bombs?\"}],\n    [{\"role\": \"user\", \"content\": \"What's the weather?\"}],\n    [{\"role\": \"user\", \"content\": \"Tell me about drugs\"}]\n]\n\nprompts = [tokenizer.apply_chat_template(c, tokenize=False) for c in chats]\nresults = llm.generate(prompts, sampling_params)\n\nfor i, result in enumerate(results):\n    print(f\"Chat {i}: {result.outputs[0].text}\")\n```\n\n**Throughput**: ~50-100 requests\u002Fsec on single A100\n\n### Workflow 4: API endpoint (FastAPI)\n\n**Serve as moderation API**:\n```python\nfrom fastapi import FastAPI\nfrom pydantic import BaseModel\nfrom vllm import LLM, SamplingParams\n\napp = FastAPI()\nllm = LLM(model=\"meta-llama\u002FLlamaGuard-7b\")\nsampling_params = SamplingParams(temperature=0.0, max_tokens=100)\n\nclass ModerationRequest(BaseModel):\n    messages: list  # [{\"role\": \"user\", \"content\": \"...\"}]\n\n@app.post(\"\u002Fmoderate\")\ndef moderate_endpoint(request: ModerationRequest):\n    prompt = tokenizer.apply_chat_template(request.messages, tokenize=False)\n    output = llm.generate([prompt], sampling_params)[0]\n\n    result = output.outputs[0].text\n    is_safe = result.startswith(\"safe\")\n    category = None if is_safe else result.split(\"\\n\")[1] if \"\\n\" in result else None\n\n    return {\n        \"safe\": is_safe,\n        \"category\": category,\n        \"full_output\": result\n    }\n\n# Run: uvicorn api:app --host 0.0.0.0 --port 8000\n```\n\n**Usage**:\n```bash\ncurl -X POST http:\u002F\u002Flocalhost:8000\u002Fmoderate \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"messages\": [{\"role\": \"user\", \"content\": \"How to hack?\"}]}'\n\n# Response: {\"safe\": false, \"category\": \"S6\", \"full_output\": \"unsafe\\nS6\"}\n```\n\n### Workflow 5: NeMo Guardrails integration\n\n**Use with NVIDIA Guardrails**:\n```python\nfrom nemoguardrails import RailsConfig, LLMRails\nfrom nemoguardrails.integrations.llama_guard import LlamaGuard\n\n# Configure NeMo Guardrails\nconfig = RailsConfig.from_content(\"\"\"\nmodels:\n  - type: main\n    engine: openai\n    model: gpt-4\n\nrails:\n  input:\n    flows:\n      - llamaguard check input\n  output:\n    flows:\n      - llamaguard check output\n\"\"\")\n\n# Add LlamaGuard integration\nllama_guard = LlamaGuard(model_path=\"meta-llama\u002FLlamaGuard-7b\")\nrails = LLMRails(config)\nrails.register_action(llama_guard.check_input, name=\"llamaguard check input\")\nrails.register_action(llama_guard.check_output, name=\"llamaguard check output\")\n\n# Use with automatic moderation\nresponse = rails.generate(messages=[\n    {\"role\": \"user\", \"content\": \"How do I make weapons?\"}\n])\n# Automatically blocked by LlamaGuard\n```\n\n## When to use vs alternatives\n\n**Use LlamaGuard when**:\n- Need pre-trained moderation model\n- Want high accuracy (94-95%)\n- Have GPU resources (7-8B model)\n- Need detailed safety categories\n- Building production LLM apps\n\n**Model versions**:\n- **LlamaGuard 1** (7B): Original, 6 categories\n- **LlamaGuard 2** (8B): Improved, 6 categories\n- **LlamaGuard 3** (8B): Latest (2024), enhanced\n\n**Use alternatives instead**:\n- **OpenAI Moderation API**: Simpler, API-based, free\n- **Perspective API**: Google's toxicity detection\n- **NeMo Guardrails**: More comprehensive safety framework\n- **Constitutional AI**: Training-time safety\n\n## Common issues\n\n**Issue: Model access denied**\n\nLogin to HuggingFace:\n```bash\nhuggingface-cli login\n# Enter your token\n```\n\nAccept license on model page:\nhttps:\u002F\u002Fhuggingface.co\u002Fmeta-llama\u002FLlamaGuard-7b\n\n**Issue: High latency (>500ms)**\n\nUse vLLM for 10× speedup:\n```python\nfrom vllm import LLM\nllm = LLM(model=\"meta-llama\u002FLlamaGuard-7b\")\n# Latency: 500ms → 50ms\n```\n\nEnable tensor parallelism:\n```python\nllm = LLM(model=\"meta-llama\u002FLlamaGuard-7b\", tensor_parallel_size=2)\n# 2× faster on 2 GPUs\n```\n\n**Issue: False positives**\n\nUse threshold-based filtering:\n```python\n# Get probability of \"unsafe\" token\nlogits = model(..., return_dict_in_generate=True, output_scores=True)\nunsafe_prob = torch.softmax(logits.scores[0][0], dim=-1)[unsafe_token_id]\n\nif unsafe_prob > 0.9:  # High confidence threshold\n    return \"unsafe\"\nelse:\n    return \"safe\"\n```\n\n**Issue: OOM on GPU**\n\nUse 8-bit quantization:\n```python\nfrom transformers import BitsAndBytesConfig\n\nquantization_config = BitsAndBytesConfig(load_in_8bit=True)\nmodel = AutoModelForCausalLM.from_pretrained(\n    model_id,\n    quantization_config=quantization_config,\n    device_map=\"auto\"\n)\n# Memory: 14GB → 7GB\n```\n\n## Advanced topics\n\n**Custom categories**: See [references\u002Fcustom-categories.md](references\u002Fcustom-categories.md) for fine-tuning LlamaGuard with domain-specific safety categories.\n\n**Performance benchmarks**: See [references\u002Fbenchmarks.md](references\u002Fbenchmarks.md) for accuracy comparison with other moderation APIs and latency optimization.\n\n**Deployment guide**: See [references\u002Fdeployment.md](references\u002Fdeployment.md) for Sagemaker, Kubernetes, and scaling strategies.\n\n## Hardware requirements\n\n- **GPU**: NVIDIA T4\u002FA10\u002FA100\n- **VRAM**:\n  - FP16: 14GB (7B model)\n  - INT8: 7GB (quantized)\n  - INT4: 4GB (QLoRA)\n- **CPU**: Possible but slow (10× latency)\n- **Throughput**: 50-100 req\u002Fsec (A100)\n\n**Latency** (single GPU):\n- HuggingFace Transformers: 300-500ms\n- vLLM: 50-100ms\n- Batched (vLLM): 20-50ms per request\n\n## Resources\n\n- HuggingFace:\n  - V1: https:\u002F\u002Fhuggingface.co\u002Fmeta-llama\u002FLlamaGuard-7b\n  - V2: https:\u002F\u002Fhuggingface.co\u002Fmeta-llama\u002FMeta-Llama-Guard-2-8B\n  - V3: https:\u002F\u002Fhuggingface.co\u002Fmeta-llama\u002FMeta-Llama-Guard-3-8B\n- Paper: https:\u002F\u002Fai.meta.com\u002Fresearch\u002Fpublications\u002Fllama-guard-llm-based-input-output-safeguard-for-human-ai-conversations\u002F\n- Integration: vLLM, Sagemaker, NeMo Guardrails\n- Accuracy: 94.5% (prompts), 95.3% (responses)\n\n\n\n","# LlamaGuard - AI Content Moderation\n\n## Quick start\n\nLlamaGuard is a 7-8B parameter model specialized for content safety classification.\n\n**Installation**:\n```bash\npip install transformers torch\n# Login to HuggingFace (required)\nhuggingface-cli login\n```\n\n**Basic usage**:\n```python\nfrom transformers import AutoTokenizer, AutoModelForCausalLM\n\nmodel_id = \"meta-llama\u002FLlamaGuard-7b\"\ntokenizer = AutoTokenizer.from_pretrained(model_id)\nmodel = AutoModelForCausalLM.from_pretrained(model_id, device_map=\"auto\")\n\ndef moderate(chat):\n    input_ids = tokenizer.apply_chat_template(chat, return_tensors=\"pt\").to(model.device)\n    output = model.generate(input_ids=input_ids, max_new_tokens=100)\n    return tokenizer.decode(output[0], skip_special_tokens=True)\n\n# Check user input\nresult = moderate([\n    {\"role\": \"user\", \"content\": \"How do I make explosives?\"}\n])\nprint(result)\n# Output: \"unsafe\\nS3\" (Criminal Planning)\n```\n\n## Common workflows\n\n### Workflow 1: Input filtering (prompt moderation)\n\n**Check user prompts before LLM**:\n```python\ndef check_input(user_message):\n    result = moderate([{\"role\": \"user\", \"content\": user_message}])\n\n    if result.startswith(\"unsafe\"):\n        category = result.split(\"\\n\")[1]\n        return False, category  # Blocked\n    else:\n        return True, None  # Safe\n\n# Example\nsafe, category = check_input(\"How do I hack a website?\")\nif not safe:\n    print(f\"Request blocked: {category}\")\n    # Return error to user\nelse:\n    # Send to LLM\n    response = llm.generate(user_message)\n```\n\n**Safety categories**:\n- **S1**: Violence & Hate\n- **S2**: Sexual Content\n- **S3**: Guns & Illegal Weapons\n- **S4**: Regulated Substances\n- **S5**: Suicide & Self-Harm\n- **S6**: Criminal Planning\n\n### Workflow 2: Output filtering (response moderation)\n\n**Check LLM responses before showing to user**:\n```python\ndef check_output(user_message, bot_response):\n    conversation = [\n        {\"role\": \"user\", \"content\": user_message},\n        {\"role\": \"assistant\", \"content\": bot_response}\n    ]\n\n    result = moderate(conversation)\n\n    if result.startswith(\"unsafe\"):\n        category = result.split(\"\\n\")[1]\n        return False, category\n    else:\n        return True, None\n\n# Example\nuser_msg = \"Tell me about harmful substances\"\nbot_msg = llm.generate(user_msg)\n\nsafe, category = check_output(user_msg, bot_msg)\nif not safe:\n    print(f\"Response blocked: {category}\")\n    # Return generic response\n    return \"I cannot provide that information.\"\nelse:\n    return bot_msg\n```\n\n### Workflow 3: vLLM deployment (fast inference)\n\n**Production-ready serving**:\n```python\nfrom vllm import LLM, SamplingParams\n\n# Initialize vLLM\nllm = LLM(model=\"meta-llama\u002FLlamaGuard-7b\", tensor_parallel_size=1)\n\n# Sampling params\nsampling_params = SamplingParams(\n    temperature=0.0,  # Deterministic\n    max_tokens=100\n)\n\ndef moderate_vllm(chat):\n    # Format prompt\n    prompt = tokenizer.apply_chat_template(chat, tokenize=False)\n\n    # Generate\n    output = llm.generate([prompt], sampling_params)\n    return output[0].outputs[0].text\n\n# Batch moderation\nchats = [\n    [{\"role\": \"user\", \"content\": \"How to make bombs?\"}],\n    [{\"role\": \"user\", \"content\": \"What's the weather?\"}],\n    [{\"role\": \"user\", \"content\": \"Tell me about drugs\"}]\n]\n\nprompts = [tokenizer.apply_chat_template(c, tokenize=False) for c in chats]\nresults = llm.generate(prompts, sampling_params)\n\nfor i, result in enumerate(results):\n    print(f\"Chat {i}: {result.outputs[0].text}\")\n```\n\n**Throughput**: ~50-100 requests\u002Fsec on single A100\n\n### Workflow 4: API endpoint (FastAPI)\n\n**Serve as moderation API**:\n```python\nfrom fastapi import FastAPI\nfrom pydantic import BaseModel\nfrom vllm import LLM, SamplingParams\n\napp = FastAPI()\nllm = LLM(model=\"meta-llama\u002FLlamaGuard-7b\")\nsampling_params = SamplingParams(temperature=0.0, max_tokens=100)\n\nclass ModerationRequest(BaseModel):\n    messages: list  # [{\"role\": \"user\", \"content\": \"...\"}]\n\n@app.post(\"\u002Fmoderate\")\ndef moderate_endpoint(request: ModerationRequest):\n    prompt = tokenizer.apply_chat_template(request.messages, tokenize=False)\n    output = llm.generate([prompt], sampling_params)[0]\n\n    result = output.outputs[0].text\n    is_safe = result.startswith(\"safe\")\n    category = None if is_safe else result.split(\"\\n\")[1] if \"\\n\" in result else None\n\n    return {\n        \"safe\": is_safe,\n        \"category\": category,\n        \"full_output\": result\n    }\n\n# Run: uvicorn api:app --host 0.0.0.0 --port 8000\n```\n\n**Usage**:\n```bash\ncurl -X POST http:\u002F\u002Flocalhost:8000\u002Fmoderate \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"messages\": [{\"role\": \"user\", \"content\": \"How to hack?\"}]}'\n\n# Response: {\"safe\": false, \"category\": \"S6\", \"full_output\": \"unsafe\\nS6\"}\n```\n\n### Workflow 5: NeMo Guardrails integration\n\n**Use with NVIDIA Guardrails**:\n```python\nfrom nemoguardrails import RailsConfig, LLMRails\nfrom nemoguardrails.integrations.llama_guard import LlamaGuard\n\n# Configure NeMo Guardrails\nconfig = RailsConfig.from_content(\"\"\"\nmodels:\n  - type: main\n    engine: openai\n    model: gpt-4\n\nrails:\n  input:\n    flows:\n      - llamaguard check input\n  output:\n    flows:\n      - llamaguard check output\n\"\"\")\n\n# Add LlamaGuard integration\nllama_guard = LlamaGuard(model_path=\"meta-llama\u002FLlamaGuard-7b\")\nrails = LLMRails(config)\nrails.register_action(llama_guard.check_input, name=\"llamaguard check input\")\nrails.register_action(llama_guard.check_output, name=\"llamaguard check output\")\n\n# Use with automatic moderation\nresponse = rails.generate(messages=[\n    {\"role\": \"user\", \"content\": \"How do I make weapons?\"}\n])\n# Automatically blocked by LlamaGuard\n```\n\n## When to use vs alternatives\n\n**Use LlamaGuard when**:\n- Need pre-trained moderation model\n- Want high accuracy (94-95%)\n- Have GPU resources (7-8B model)\n- Need detailed safety categories\n- Building production LLM apps\n\n**Model versions**:\n- **LlamaGuard 1** (7B): Original, 6 categories\n- **LlamaGuard 2** (8B): Improved, 6 categories\n- **LlamaGuard 3** (8B): Latest (2024), enhanced\n\n**Use alternatives instead**:\n- **OpenAI Moderation API**: Simpler, API-based, free\n- **Perspective API**: Google's toxicity detection\n- **NeMo Guardrails**: More comprehensive safety framework\n- **Constitutional AI**: Training-time safety\n\n## Common issues\n\n**Issue: Model access denied**\n\nLogin to HuggingFace:\n```bash\nhuggingface-cli login\n# Enter your token\n```\n\nAccept license on model page:\nhttps:\u002F\u002Fhuggingface.co\u002Fmeta-llama\u002FLlamaGuard-7b\n\n**Issue: High latency (>500ms)**\n\nUse vLLM for 10× speedup:\n```python\nfrom vllm import LLM\nllm = LLM(model=\"meta-llama\u002FLlamaGuard-7b\")\n# Latency: 500ms → 50ms\n```\n\nEnable tensor parallelism:\n```python\nllm = LLM(model=\"meta-llama\u002FLlamaGuard-7b\", tensor_parallel_size=2)\n# 2× faster on 2 GPUs\n```\n\n**Issue: False positives**\n\nUse threshold-based filtering:\n```python\n# Get probability of \"unsafe\" token\nlogits = model(..., return_dict_in_generate=True, output_scores=True)\nunsafe_prob = torch.softmax(logits.scores[0][0], dim=-1)[unsafe_token_id]\n\nif unsafe_prob > 0.9:  # High confidence threshold\n    return \"unsafe\"\nelse:\n    return \"safe\"\n```\n\n**Issue: OOM on GPU**\n\nUse 8-bit quantization:\n```python\nfrom transformers import BitsAndBytesConfig\n\nquantization_config = BitsAndBytesConfig(load_in_8bit=True)\nmodel = AutoModelForCausalLM.from_pretrained(\n    model_id,\n    quantization_config=quantization_config,\n    device_map=\"auto\"\n)\n# Memory: 14GB → 7GB\n```\n\n## Advanced topics\n\n**Custom categories**: See [references\u002Fcustom-categories.md](references\u002Fcustom-categories.md) for fine-tuning LlamaGuard with domain-specific safety categories.\n\n**Performance benchmarks**: See [references\u002Fbenchmarks.md](references\u002Fbenchmarks.md) for accuracy comparison with other moderation APIs and latency optimization.\n\n**Deployment guide**: See [references\u002Fdeployment.md](references\u002Fdeployment.md) for Sagemaker, Kubernetes, and scaling strategies.\n\n## Hardware requirements\n\n- **GPU**: NVIDIA T4\u002FA10\u002FA100\n- **VRAM**:\n  - FP16: 14GB (7B model)\n  - INT8: 7GB (quantized)\n  - INT4: 4GB (QLoRA)\n- **CPU**: Possible but slow (10× latency)\n- **Throughput**: 50-100 req\u002Fsec (A100)\n\n**Latency** (single GPU):\n- HuggingFace Transformers: 300-500ms\n- vLLM: 50-100ms\n- Batched (vLLM): 20-50ms per request\n\n## Resources\n\n- HuggingFace:\n  - V1: https:\u002F\u002Fhuggingface.co\u002Fmeta-llama\u002FLlamaGuard-7b\n  - V2: https:\u002F\u002Fhuggingface.co\u002Fmeta-llama\u002FMeta-Llama-Guard-2-8B\n  - V3: https:\u002F\u002Fhuggingface.co\u002Fmeta-llama\u002FMeta-Llama-Guard-3-8B\n- Paper: https:\u002F\u002Fai.meta.com\u002Fresearch\u002Fpublications\u002Fllama-guard-llm-based-input-output-safeguard-for-human-ai-conversations\u002F\n- Integration: vLLM, Sagemaker, NeMo Guardrails\n- Accuracy: 94.5% (prompts), 95.3% (responses)\n\n\n\n",{"name":5,"tags":49,"author":50,"license":15,"version":51,"description":7,"dependencies":52},[41,24,40,39,38,37,36,25,34],"luo-kai","1.0.0",[53,54,55],"transformers","torch","vllm","main","4d2fb89cdfb75f3f6fd3c6c5ec9ad90ea129eb3c","ai-agent-skills\u002F18-ai-agents-and-automation (by Luo Kai)\u002F16-other-agents\u002Fllamaguard",1,"https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai","https:\u002F\u002Fgithub.com\u002Fluokai0","a solo builder.","2026-05-06 04:29:04",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add luokai0\u002Fai-agent-skills-by-luo-kai --skill llamaguard",{"tool":70,"command":71},"bunx","bunx skills add luokai0\u002Fai-agent-skills-by-luo-kai --skill llamaguard",{"tool":73,"command":74},"pnpm","pnpm dlx skills add luokai0\u002Fai-agent-skills-by-luo-kai --skill llamaguard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F18-ai-agents-and-automation (by Luo Kai)\u002F16-other-agents\u002Fllamaguard\u002FSKILL.md",true,[78,84,89,93,97,101,105,109,113,117,121,125,129,133,137,141,145,149,153,157,161,165,169,173,177,181,185,189,193,197,201,205,209,213,217,221,225,229,233,237,241,245,249,253,257,261,265,269,273,277,281,285,289,293,297,301,305,309,313,317],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"LICENSE.txt","LICENSE","许可证",1467,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002FLICENSE.txt",{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":59,"sourceHtmlUrl":88},"scripts\u002F__init__.py","SCRIPT","脚本","https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002F__init__.py",{"path":90,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Faccept_changes.py",4051,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Faccept_changes.py",{"path":94,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":95,"sourceHtmlUrl":96},"scripts\u002Fcomment.py",10694,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Fcomment.py",{"path":98,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":99,"sourceHtmlUrl":100},"scripts\u002Foffice\u002Fhelpers\u002F__init__.py",0,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fhelpers\u002F__init__.py",{"path":102,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":103,"sourceHtmlUrl":104},"scripts\u002Foffice\u002Fhelpers\u002Fmerge_runs.py",5567,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fhelpers\u002Fmerge_runs.py",{"path":106,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":107,"sourceHtmlUrl":108},"scripts\u002Foffice\u002Fhelpers\u002Fsimplify_redlines.py",5754,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fhelpers\u002Fsimplify_redlines.py",{"path":110,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":111,"sourceHtmlUrl":112},"scripts\u002Foffice\u002Fpack.py",4991,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fpack.py",{"path":114,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":115,"sourceHtmlUrl":116},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-contentTypes.xsd",1963,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-contentTypes.xsd",{"path":118,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":119,"sourceHtmlUrl":120},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-coreProperties.xsd",2515,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-coreProperties.xsd",{"path":122,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":123,"sourceHtmlUrl":124},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-digSig.xsd",2856,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-digSig.xsd",{"path":126,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":127,"sourceHtmlUrl":128},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-relationships.xsd",1344,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-relationships.xsd",{"path":130,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":131,"sourceHtmlUrl":132},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chart.xsd",74984,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chart.xsd",{"path":134,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":135,"sourceHtmlUrl":136},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chartDrawing.xsd",6956,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chartDrawing.xsd",{"path":138,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":139,"sourceHtmlUrl":140},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-diagram.xsd",51302,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-diagram.xsd",{"path":142,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":143,"sourceHtmlUrl":144},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-lockedCanvas.xsd",624,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-lockedCanvas.xsd",{"path":146,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":147,"sourceHtmlUrl":148},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-main.xsd",152039,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-main.xsd",{"path":150,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":151,"sourceHtmlUrl":152},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-picture.xsd",1231,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-picture.xsd",{"path":154,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":155,"sourceHtmlUrl":156},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-spreadsheetDrawing.xsd",8862,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-spreadsheetDrawing.xsd",{"path":158,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":159,"sourceHtmlUrl":160},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-wordprocessingDrawing.xsd",14795,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-wordprocessingDrawing.xsd",{"path":162,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":163,"sourceHtmlUrl":164},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fpml.xsd",83612,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fpml.xsd",{"path":166,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":167,"sourceHtmlUrl":168},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-additionalCharacteristics.xsd",1269,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-additionalCharacteristics.xsd",{"path":170,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":171,"sourceHtmlUrl":172},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-bibliography.xsd",7328,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-bibliography.xsd",{"path":174,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":175,"sourceHtmlUrl":176},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-commonSimpleTypes.xsd",6382,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-commonSimpleTypes.xsd",{"path":178,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":179,"sourceHtmlUrl":180},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlDataProperties.xsd",1248,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlDataProperties.xsd",{"path":182,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":183,"sourceHtmlUrl":184},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlSchemaProperties.xsd",880,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlSchemaProperties.xsd",{"path":186,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":187,"sourceHtmlUrl":188},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesCustom.xsd",2608,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesCustom.xsd",{"path":190,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":191,"sourceHtmlUrl":192},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesExtended.xsd",3507,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesExtended.xsd",{"path":194,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":195,"sourceHtmlUrl":196},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesVariantTypes.xsd",7507,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesVariantTypes.xsd",{"path":198,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":199,"sourceHtmlUrl":200},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-math.xsd",23313,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-math.xsd",{"path":202,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":203,"sourceHtmlUrl":204},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-relationshipReference.xsd",1367,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-relationshipReference.xsd",{"path":206,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":207,"sourceHtmlUrl":208},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fsml.xsd",242277,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fsml.xsd",{"path":210,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":211,"sourceHtmlUrl":212},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-main.xsd",26148,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-main.xsd",{"path":214,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":215,"sourceHtmlUrl":216},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-officeDrawing.xsd",25279,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-officeDrawing.xsd",{"path":218,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":219,"sourceHtmlUrl":220},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-presentationDrawing.xsd",535,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-presentationDrawing.xsd",{"path":222,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":223,"sourceHtmlUrl":224},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-spreadsheetDrawing.xsd",5712,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-spreadsheetDrawing.xsd",{"path":226,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":227,"sourceHtmlUrl":228},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-wordprocessingDrawing.xsd",4010,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-wordprocessingDrawing.xsd",{"path":230,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":231,"sourceHtmlUrl":232},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fwml.xsd",171367,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fwml.xsd",{"path":234,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":235,"sourceHtmlUrl":236},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fxml.xsd",4646,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fxml.xsd",{"path":238,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":239,"sourceHtmlUrl":240},"scripts\u002Foffice\u002Fschemas\u002Fmce\u002Fmc.xsd",3127,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmce\u002Fmc.xsd",{"path":242,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":243,"sourceHtmlUrl":244},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2010.xsd",26549,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2010.xsd",{"path":246,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":247,"sourceHtmlUrl":248},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2012.xsd",3745,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2012.xsd",{"path":250,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":251,"sourceHtmlUrl":252},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2018.xsd",901,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2018.xsd",{"path":254,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":255,"sourceHtmlUrl":256},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cex-2018.xsd",1778,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cex-2018.xsd",{"path":258,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":259,"sourceHtmlUrl":260},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cid-2016.xsd",1002,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cid-2016.xsd",{"path":262,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":263,"sourceHtmlUrl":264},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-sdtdatahash-2020.xsd",600,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-sdtdatahash-2020.xsd",{"path":266,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":267,"sourceHtmlUrl":268},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-symex-2015.xsd",745,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-symex-2015.xsd",{"path":270,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":271,"sourceHtmlUrl":272},"scripts\u002Foffice\u002Fsoffice.py",5301,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fsoffice.py",{"path":274,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":275,"sourceHtmlUrl":276},"scripts\u002Foffice\u002Funpack.py",4052,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Funpack.py",{"path":278,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":279,"sourceHtmlUrl":280},"scripts\u002Foffice\u002Fvalidate.py",3668,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fvalidate.py",{"path":282,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":283,"sourceHtmlUrl":284},"scripts\u002Foffice\u002Fvalidators\u002F__init__.py",336,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fvalidators\u002F__init__.py",{"path":286,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":287,"sourceHtmlUrl":288},"scripts\u002Foffice\u002Fvalidators\u002Fbase.py",32651,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fbase.py",{"path":290,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":291,"sourceHtmlUrl":292},"scripts\u002Foffice\u002Fvalidators\u002Fdocx.py",16376,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fdocx.py",{"path":294,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":295,"sourceHtmlUrl":296},"scripts\u002Foffice\u002Fvalidators\u002Fpptx.py",9824,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fpptx.py",{"path":298,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":299,"sourceHtmlUrl":300},"scripts\u002Foffice\u002Fvalidators\u002Fredlining.py",8918,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fredlining.py",{"path":302,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":303,"sourceHtmlUrl":304},"scripts\u002Ftemplates\u002Fcomments.xml",2603,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Ftemplates\u002Fcomments.xml",{"path":306,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":307,"sourceHtmlUrl":308},"scripts\u002Ftemplates\u002FcommentsExtended.xml",2611,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Ftemplates\u002FcommentsExtended.xml",{"path":310,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":311,"sourceHtmlUrl":312},"scripts\u002Ftemplates\u002FcommentsExtensible.xml",2707,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Ftemplates\u002FcommentsExtensible.xml",{"path":314,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":315,"sourceHtmlUrl":316},"scripts\u002Ftemplates\u002FcommentsIds.xml",2619,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Ftemplates\u002FcommentsIds.xml",{"path":318,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":319,"sourceHtmlUrl":320},"scripts\u002Ftemplates\u002Fpeople.xml",115,"https:\u002F\u002Fgithub.com\u002Fa1627418541\u002F-\u002Fblob\u002Fmain\u002F.mux\u002Fskills\u002Fdocx\u002Fscripts\u002Ftemplates\u002Fpeople.xml",[322,348,365,395,428,463],{"skillNo":323,"name":324,"nameZh":6,"description":325,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":326,"categories":327,"keywords":328,"publishedAt":44},"01M6F2SKTE208174C7S7JJCZC7","write-contracts","Generates secure Aptos Move V2 smart contracts with Object model, Digital Asset integration, security patterns, and storage type guidance. Includes comprehensive storage decision framework for optimal data structure selection. Triggers on: 'write contract', 'create NFT collection', 'build marketplace', 'implement minting', 'generate Move module', 'create token contract', 'build DAO', 'implement staking'. Ask storage questions when: 'store', 'track', 'registry', 'mapping', 'list', 'collection'.","https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F22-clawhub-skills\u002Fwrite-contracts\u002FSKILL.md",[],[329,330,331,332,333,334,335,336,31,337,338,339,340,341,342,343,344,345,346,347],"write","contracts","write contracts","storage","secure","create","generate","collection","decision","ask","smart-contracts","selection","objects","structure","nft","token","aptos","critical","move",{"skillNo":349,"name":350,"nameZh":6,"description":351,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":352,"categories":353,"keywords":354,"publishedAt":44},"01M6F2RFXJ6T9MKW0A7N7GM45B","web-search","通用网络搜索技能，支持多引擎搜索（百度、必应、DuckDuckGo），无需API密钥即可获取实时信息","https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F22-clawhub-skills\u002Fweb-search-ex-skill\u002FSKILL.md",[],[355,356,357,358,359,360,361,362,363,364],"web","search","web search","搜索","baidu","bing","duckduckgo","百度","多引擎","internet",{"skillNo":366,"name":367,"nameZh":6,"description":368,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":369,"categories":370,"keywords":376,"publishedAt":44},"01M6F2K968G1FZEZFPW2E6B222","solo-build","Execute implementation plan tasks with TDD workflow, auto-commit, and phase gates. Use when user says \"build it\", \"start building\", \"execute plan\", \"implement tasks\", \"ship it\", or references a track ID. Do NOT use for planning (use \u002Fplan) or scaffolding (use \u002Fscaffold).","https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F22-clawhub-skills\u002Fsolo-build\u002FSKILL.md",[371],{"categoryNo":372,"categoryName":373,"taxonomyType":374,"taxonomyTypeDesc":375},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[377,378,379,380,381,382,383,384,356,385,386,387,329,388,389,390,391,392,393,394],"build","solo","solo build","MCP","workflow","commit","tasks","code","Bash","plan","read","auto","references","context7","query","scaffolding","ship it","project",{"skillNo":396,"name":397,"nameZh":6,"description":398,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":399,"categories":400,"keywords":407,"publishedAt":44},"01M6F2GKN39SGHSPWYB3662YC8","react-email","Use when building HTML email templates with React components, adding a visual email editor to an application using the React Email visual editor, rendering emails to HTML, or sending emails with Resend. Covers welcome emails, password resets, notifications, order confirmations, newsletters, transactional emails, and the embeddable email editor component.","https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F22-clawhub-skills\u002Freact-email-skills\u002FSKILL.md",[401,404],{"categoryNo":402,"categoryName":403,"taxonomyType":374,"taxonomyTypeDesc":375},"01JBSEEDCAT000000000000005","邮件与沟通",{"categoryNo":405,"categoryName":406,"taxonomyType":374,"taxonomyTypeDesc":375},"01JBSEEDCAT000000000000009","前端开发",[408,409,410,411,412,413,414,415,416,417,418,419,420,421,422,423,424,425,426,427],"react","email","react email","github","editor","components","react components","component","welcome","https","notifications","password","node","use","html","resend","visual","emails","rendering","with",{"skillNo":429,"name":430,"nameZh":6,"description":431,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":432,"categories":433,"keywords":444,"publishedAt":44},"01M6F2FBVGVDFSG8SSFJGXA40C","APITester Agent-Driven API Testing","Test API endpoints and document responses. Define tests in plain English, run them, get formatted results. Agent-driven Postman alternative.","https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F22-clawhub-skills\u002Fopenclaw-api-tester\u002FSKILL.md",[434,437,440,441],{"categoryNo":435,"categoryName":436,"taxonomyType":374,"taxonomyTypeDesc":375},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":438,"categoryName":439,"taxonomyType":374,"taxonomyTypeDesc":375},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":372,"categoryName":373,"taxonomyType":374,"taxonomyTypeDesc":375},{"categoryNo":442,"categoryName":443,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师",[445,446,447,448,449,450,451,452,453,454,455,456,457,458,459,460,461,462],"testing","api","api testing","driven","APITester Agent Driven API Testing","test","run","postman","results","plain english","tester","endpoints","document","get","define","tests","english","api-tester",{"skillNo":464,"name":465,"nameZh":6,"description":466,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":467,"categories":468,"keywords":469,"publishedAt":44},"01M6F273Y3NGAPVJZ608BC0G9G","hubspot-implementation-plan","Generate a phased implementation plan from a HubSpot audit report. Creates prioritized, sequenced cleanup processes with effort estimates, dependencies, and automation feasibility. Use after running \u002Fhubspot-audit.","https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F22-clawhub-skills\u002Fhubspot-implementation-plan\u002FSKILL.md",[],[386,470,471,472,473,474,475,335,35,476,477,478,479,421,480,481,427,482],"implementation","hubspot","hubspot implementation plan","automation","feasibility","cleanup","report","audit","audit report","phased implementation","dependencies","processes","hubspot audit"]