[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ADZ8459C9HYVQ61T87H2P2":3,"skill-same:01M6ADZ8459C9HYVQ61T87H2P2":109},{"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":28,"publishedAt":55,"linkOnly":56,"markdownContent":57,"markdownBody":58,"frontMatter":59,"refName":67,"commitSha":68,"skillDirectory":69,"forksCount":70,"repositoryHtmlUrl":71,"repositoryHomepageUrl":72,"ownerHtmlUrl":73,"ownerBlogUrl":74,"ownerDescription":75,"updatedAt":76,"install":77,"resources":90},"01M6ADZ8459C9HYVQ61T87H2P2","safety-alignment-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.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fsafety-alignment-llamaguard\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54],"alignment","Safety","safety alignment llamaguard","Safety Classification","categories","input","self","specialized","model","NeMo Guardrails","AI Safety","Output Filtering","Input Filtering","research","Guardrails","Meta","Content Moderation","LlamaGuard","Safety Alignment","Transformers","vLLM","HuggingFace","NeMo","content","planning","deploy","2026-11-10 10:12:30",false,"---\nname: safety-alignment-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: Orchestra Research\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":60,"author":61,"license":15,"version":62,"description":7,"dependencies":63},[47,46,45,44,43,32,41,40,39],"Orchestra Research","1.0.0",[64,65,66],"transformers","torch","vllm","main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fsafety-alignment-llamaguard",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":78,"prompt":88,"zipAvailable":89},[79,82,85],{"tool":80,"command":81},"npx","npx skills add davila7\u002Fclaude-code-templates --skill safety-alignment-llamaguard",{"tool":83,"command":84},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill safety-alignment-llamaguard",{"tool":86,"command":87},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill safety-alignment-llamaguard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fsafety-alignment-llamaguard\u002FSKILL.md",true,[91,97,103],{"path":92,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":95,"sourceHtmlUrl":96},"assets\u002Fexample_asset.txt","ASSET","资产文件",865,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fenterprise-communication\u002Fquality-manager-qmr\u002Fassets\u002Fexample_asset.txt",{"path":98,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":101,"sourceHtmlUrl":102},"references\u002Fapi_reference.md","REFERENCE","参考文档",970,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fenterprise-communication\u002Fquality-manager-qmr\u002Freferences\u002Fapi_reference.md",{"path":104,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":107,"sourceHtmlUrl":108},"scripts\u002Fexample.py","SCRIPT","脚本",597,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fenterprise-communication\u002Fquality-manager-qmr\u002Fscripts\u002Fexample.py",[110,138,165,196,231,255],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":117,"publishedAt":55},"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",[116],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137],"scoring","pool","wealthville pool scoring","liquidity","which","for","exit","now","use","when","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":145,"publishedAt":55},"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",[144],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[146,147,148,149,150,151,152,153,154,155,156,127,157,158,159,160,161,162,163,164],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":178,"publishedAt":55},"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",[171,174,175],{"categoryNo":172,"categoryName":173,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":176,"categoryName":177,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000033","数据分析师",[179,180,181,182,183,184,185,123,186,187,188,189,190,191,192,126,193,194,127,195],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":200,"licenseFileUrl":201,"sourceHtmlUrl":202,"categories":203,"keywords":207,"publishedAt":55},"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",[204],{"categoryNo":205,"categoryName":206,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,123,230],"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":232,"name":233,"nameZh":6,"description":234,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":200,"licenseFileUrl":235,"sourceHtmlUrl":236,"categories":237,"keywords":242,"publishedAt":55},"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",[238,241],{"categoryNo":239,"categoryName":240,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":205,"categoryName":206,"taxonomyType":21,"taxonomyTypeDesc":22},[243,244,245,246,247,209,248,218,219,249,250,251,252,123,253,129,254],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":256,"name":257,"nameZh":6,"description":258,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":200,"licenseFileUrl":259,"sourceHtmlUrl":260,"categories":261,"keywords":267,"publishedAt":55},"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",[262,265,266],{"categoryNo":263,"categoryName":264,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[268,269,270,271,272,273,274,275,211,276,221,157,52,277,278,279,280,191,281,127,282,283,284,285,286,135,287],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]