[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DTPH78H0A2Z59YT0RV8PSG":3,"skill-same:01M6DTPH78H0A2Z59YT0RV8PSG":86},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":59,"commitSha":60,"skillDirectory":61,"forksCount":62,"repositoryHtmlUrl":63,"repositoryHomepageUrl":6,"ownerHtmlUrl":64,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":65,"install":66,"resources":79},"01M6DTPH78H0A2Z59YT0RV8PSG","tsx-code-order",null,"规范 TSX\u002FReact 函数组件内部的代码书写顺序。\nUse when: 用户说「整理组件顺序」「代码顺序乱了」「按规范排列 hooks」「tsx 代码排序」「梳理一下组件结构」，\n或在写新组件 \u002F review 已有组件时需要对齐代码顺序规范。","sudoprivacy\u002Fsudowork","sudoprivacy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F115790070?v=4","01M6DTPA1KMM1JSSJBNE9FGG5Q","01M6DTPA5PQ2F3S9CVXH1TQ4RT",10,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fsudoprivacy\u002Fsudowork\u002Fblob\u002Fdev\u002F.claude\u002Fskills\u002Ftsx-code-order\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[23,24,25,26,27,28,29,30,31],"code","tsx","tsx code order","review","react","use","hooks","整理","when","2026-11-10 10:12:30",false,"---\nname: llava\ndescription: Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna\u002FLLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.\nversion: 1.0.0\nauthor: Orchestra Research\nlicense: MIT\ndependencies: [transformers, torch, pillow]\nmetadata:\n  hermes:\n    tags: [LLaVA, Vision-Language, Multimodal, Visual Question Answering, Image Chat, CLIP, Vicuna, Conversational AI, Instruction Tuning, VQA]\n\n---\n\n# LLaVA - Large Language and Vision Assistant\n\nOpen-source vision-language model for conversational image understanding.\n\n## When to use LLaVA\n\n**Use when:**\n- Building vision-language chatbots\n- Visual question answering (VQA)\n- Image description and captioning\n- Multi-turn image conversations\n- Visual instruction following\n- Document understanding with images\n\n**Metrics**:\n- **23,000+ GitHub stars**\n- GPT-4V level capabilities (targeted)\n- Apache 2.0 License\n- Multiple model sizes (7B-34B params)\n\n**Use alternatives instead**:\n- **GPT-4V**: Highest quality, API-based\n- **CLIP**: Simple zero-shot classification\n- **BLIP-2**: Better for captioning only\n- **Flamingo**: Research, not open-source\n\n## Quick start\n\n### Installation\n\n```bash\n# Clone repository\ngit clone https:\u002F\u002Fgithub.com\u002Fhaotian-liu\u002FLLaVA\ncd LLaVA\n\n# Install\npip install -e .\n```\n\n### Basic usage\n\n```python\nfrom llava.model.builder import load_pretrained_model\nfrom llava.mm_utils import get_model_name_from_path, process_images, tokenizer_image_token\nfrom llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN\nfrom llava.conversation import conv_templates\nfrom PIL import Image\nimport torch\n\n# Load model\nmodel_path = \"liuhaotian\u002Fllava-v1.5-7b\"\ntokenizer, model, image_processor, context_len = load_pretrained_model(\n    model_path=model_path,\n    model_base=None,\n    model_name=get_model_name_from_path(model_path)\n)\n\n# Load image\nimage = Image.open(\"image.jpg\")\nimage_tensor = process_images([image], image_processor, model.config)\nimage_tensor = image_tensor.to(model.device, dtype=torch.float16)\n\n# Create conversation\nconv = conv_templates[\"llava_v1\"].copy()\nconv.append_message(conv.roles[0], DEFAULT_IMAGE_TOKEN + \"\\nWhat is in this image?\")\nconv.append_message(conv.roles[1], None)\nprompt = conv.get_prompt()\n\n# Generate response\ninput_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).to(model.device)\n\nwith torch.inference_mode():\n    output_ids = model.generate(\n        input_ids,\n        images=image_tensor,\n        do_sample=True,\n        temperature=0.2,\n        max_new_tokens=512\n    )\n\nresponse = tokenizer.decode(output_ids[0], skip_special_tokens=True).strip()\nprint(response)\n```\n\n## Available models\n\n| Model | Parameters | VRAM | Quality |\n|-------|------------|------|---------|\n| LLaVA-v1.5-7B | 7B | ~14 GB | Good |\n| LLaVA-v1.5-13B | 13B | ~28 GB | Better |\n| LLaVA-v1.6-34B | 34B | ~70 GB | Best |\n\n```python\n# Load different models\nmodel_7b = \"liuhaotian\u002Fllava-v1.5-7b\"\nmodel_13b = \"liuhaotian\u002Fllava-v1.5-13b\"\nmodel_34b = \"liuhaotian\u002Fllava-v1.6-34b\"\n\n# 4-bit quantization for lower VRAM\nload_4bit = True  # Reduces VRAM by ~4×\n```\n\n## CLI usage\n\n```bash\n# Single image query\npython -m llava.serve.cli \\\n    --model-path liuhaotian\u002Fllava-v1.5-7b \\\n    --image-file image.jpg \\\n    --query \"What is in this image?\"\n\n# Multi-turn conversation\npython -m llava.serve.cli \\\n    --model-path liuhaotian\u002Fllava-v1.5-7b \\\n    --image-file image.jpg\n# Then type questions interactively\n```\n\n## Web UI (Gradio)\n\n```bash\n# Launch Gradio interface\npython -m llava.serve.gradio_web_server \\\n    --model-path liuhaotian\u002Fllava-v1.5-7b \\\n    --load-4bit  # Optional: reduce VRAM\n\n# Access at http:\u002F\u002Flocalhost:7860\n```\n\n## Multi-turn conversations\n\n```python\n# Initialize conversation\nconv = conv_templates[\"llava_v1\"].copy()\n\n# Turn 1\nconv.append_message(conv.roles[0], DEFAULT_IMAGE_TOKEN + \"\\nWhat is in this image?\")\nconv.append_message(conv.roles[1], None)\nresponse1 = generate(conv, model, image)  # \"A dog playing in a park\"\n\n# Turn 2\nconv.messages[-1][1] = response1  # Add previous response\nconv.append_message(conv.roles[0], \"What breed is the dog?\")\nconv.append_message(conv.roles[1], None)\nresponse2 = generate(conv, model, image)  # \"Golden Retriever\"\n\n# Turn 3\nconv.messages[-1][1] = response2\nconv.append_message(conv.roles[0], \"What time of day is it?\")\nconv.append_message(conv.roles[1], None)\nresponse3 = generate(conv, model, image)\n```\n\n## Common tasks\n\n### Image captioning\n\n```python\nquestion = \"Describe this image in detail.\"\nresponse = ask(model, image, question)\n```\n\n### Visual question answering\n\n```python\nquestion = \"How many people are in the image?\"\nresponse = ask(model, image, question)\n```\n\n### Object detection (textual)\n\n```python\nquestion = \"List all the objects you can see in this image.\"\nresponse = ask(model, image, question)\n```\n\n### Scene understanding\n\n```python\nquestion = \"What is happening in this scene?\"\nresponse = ask(model, image, question)\n```\n\n### Document understanding\n\n```python\nquestion = \"What is the main topic of this document?\"\nresponse = ask(model, document_image, question)\n```\n\n## Training custom model\n\n```bash\n# Stage 1: Feature alignment (558K image-caption pairs)\nbash scripts\u002Fv1_5\u002Fpretrain.sh\n\n# Stage 2: Visual instruction tuning (150K instruction data)\nbash scripts\u002Fv1_5\u002Ffinetune.sh\n```\n\n## Quantization (reduce VRAM)\n\n```python\n# 4-bit quantization\ntokenizer, model, image_processor, context_len = load_pretrained_model(\n    model_path=\"liuhaotian\u002Fllava-v1.5-13b\",\n    model_base=None,\n    model_name=get_model_name_from_path(\"liuhaotian\u002Fllava-v1.5-13b\"),\n    load_4bit=True  # Reduces VRAM ~4×\n)\n\n# 8-bit quantization\nload_8bit=True  # Reduces VRAM ~2×\n```\n\n## Best practices\n\n1. **Start with 7B model** - Good quality, manageable VRAM\n2. **Use 4-bit quantization** - Reduces VRAM significantly\n3. **GPU required** - CPU inference extremely slow\n4. **Clear prompts** - Specific questions get better answers\n5. **Multi-turn conversations** - Maintain conversation context\n6. **Temperature 0.2-0.7** - Balance creativity\u002Fconsistency\n7. **max_new_tokens 512-1024** - For detailed responses\n8. **Batch processing** - Process multiple images sequentially\n\n## Performance\n\n| Model | VRAM (FP16) | VRAM (4-bit) | Speed (tokens\u002Fs) |\n|-------|-------------|--------------|------------------|\n| 7B | ~14 GB | ~4 GB | ~20 |\n| 13B | ~28 GB | ~8 GB | ~12 |\n| 34B | ~70 GB | ~18 GB | ~5 |\n\n*On A100 GPU*\n\n## Benchmarks\n\nLLaVA achieves competitive scores on:\n- **VQAv2**: 78.5%\n- **GQA**: 62.0%\n- **MM-Vet**: 35.4%\n- **MMBench**: 64.3%\n\n## Limitations\n\n1. **Hallucinations** - May describe things not in image\n2. **Spatial reasoning** - Struggles with precise locations\n3. **Small text** - Difficulty reading fine print\n4. **Object counting** - Imprecise for many objects\n5. **VRAM requirements** - Need powerful GPU\n6. **Inference speed** - Slower than CLIP\n\n## Integration with frameworks\n\n### LangChain\n\n```python\nfrom langchain.llms.base import LLM\n\nclass LLaVALLM(LLM):\n    def _call(self, prompt, stop=None):\n        # Custom LLaVA inference\n        return response\n\nllm = LLaVALLM()\n```\n\n### Gradio App\n\n```python\nimport gradio as gr\n\ndef chat(image, text, history):\n    response = ask_llava(model, image, text)\n    return response\n\ndemo = gr.ChatInterface(\n    chat,\n    additional_inputs=[gr.Image(type=\"pil\")],\n    title=\"LLaVA Chat\"\n)\ndemo.launch()\n```\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fhaotian-liu\u002FLLaVA ⭐ 23,000+\n- **Paper**: https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.08485\n- **Demo**: https:\u002F\u002Fllava.hliu.cc\n- **Models**: https:\u002F\u002Fhuggingface.co\u002Fliuhaotian\n- **License**: Apache 2.0\n\n\n","# LLaVA - Large Language and Vision Assistant\n\nOpen-source vision-language model for conversational image understanding.\n\n## When to use LLaVA\n\n**Use when:**\n- Building vision-language chatbots\n- Visual question answering (VQA)\n- Image description and captioning\n- Multi-turn image conversations\n- Visual instruction following\n- Document understanding with images\n\n**Metrics**:\n- **23,000+ GitHub stars**\n- GPT-4V level capabilities (targeted)\n- Apache 2.0 License\n- Multiple model sizes (7B-34B params)\n\n**Use alternatives instead**:\n- **GPT-4V**: Highest quality, API-based\n- **CLIP**: Simple zero-shot classification\n- **BLIP-2**: Better for captioning only\n- **Flamingo**: Research, not open-source\n\n## Quick start\n\n### Installation\n\n```bash\n# Clone repository\ngit clone https:\u002F\u002Fgithub.com\u002Fhaotian-liu\u002FLLaVA\ncd LLaVA\n\n# Install\npip install -e .\n```\n\n### Basic usage\n\n```python\nfrom llava.model.builder import load_pretrained_model\nfrom llava.mm_utils import get_model_name_from_path, process_images, tokenizer_image_token\nfrom llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN\nfrom llava.conversation import conv_templates\nfrom PIL import Image\nimport torch\n\n# Load model\nmodel_path = \"liuhaotian\u002Fllava-v1.5-7b\"\ntokenizer, model, image_processor, context_len = load_pretrained_model(\n    model_path=model_path,\n    model_base=None,\n    model_name=get_model_name_from_path(model_path)\n)\n\n# Load image\nimage = Image.open(\"image.jpg\")\nimage_tensor = process_images([image], image_processor, model.config)\nimage_tensor = image_tensor.to(model.device, dtype=torch.float16)\n\n# Create conversation\nconv = conv_templates[\"llava_v1\"].copy()\nconv.append_message(conv.roles[0], DEFAULT_IMAGE_TOKEN + \"\\nWhat is in this image?\")\nconv.append_message(conv.roles[1], None)\nprompt = conv.get_prompt()\n\n# Generate response\ninput_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).to(model.device)\n\nwith torch.inference_mode():\n    output_ids = model.generate(\n        input_ids,\n        images=image_tensor,\n        do_sample=True,\n        temperature=0.2,\n        max_new_tokens=512\n    )\n\nresponse = tokenizer.decode(output_ids[0], skip_special_tokens=True).strip()\nprint(response)\n```\n\n## Available models\n\n| Model | Parameters | VRAM | Quality |\n|-------|------------|------|---------|\n| LLaVA-v1.5-7B | 7B | ~14 GB | Good |\n| LLaVA-v1.5-13B | 13B | ~28 GB | Better |\n| LLaVA-v1.6-34B | 34B | ~70 GB | Best |\n\n```python\n# Load different models\nmodel_7b = \"liuhaotian\u002Fllava-v1.5-7b\"\nmodel_13b = \"liuhaotian\u002Fllava-v1.5-13b\"\nmodel_34b = \"liuhaotian\u002Fllava-v1.6-34b\"\n\n# 4-bit quantization for lower VRAM\nload_4bit = True  # Reduces VRAM by ~4×\n```\n\n## CLI usage\n\n```bash\n# Single image query\npython -m llava.serve.cli \\\n    --model-path liuhaotian\u002Fllava-v1.5-7b \\\n    --image-file image.jpg \\\n    --query \"What is in this image?\"\n\n# Multi-turn conversation\npython -m llava.serve.cli \\\n    --model-path liuhaotian\u002Fllava-v1.5-7b \\\n    --image-file image.jpg\n# Then type questions interactively\n```\n\n## Web UI (Gradio)\n\n```bash\n# Launch Gradio interface\npython -m llava.serve.gradio_web_server \\\n    --model-path liuhaotian\u002Fllava-v1.5-7b \\\n    --load-4bit  # Optional: reduce VRAM\n\n# Access at http:\u002F\u002Flocalhost:7860\n```\n\n## Multi-turn conversations\n\n```python\n# Initialize conversation\nconv = conv_templates[\"llava_v1\"].copy()\n\n# Turn 1\nconv.append_message(conv.roles[0], DEFAULT_IMAGE_TOKEN + \"\\nWhat is in this image?\")\nconv.append_message(conv.roles[1], None)\nresponse1 = generate(conv, model, image)  # \"A dog playing in a park\"\n\n# Turn 2\nconv.messages[-1][1] = response1  # Add previous response\nconv.append_message(conv.roles[0], \"What breed is the dog?\")\nconv.append_message(conv.roles[1], None)\nresponse2 = generate(conv, model, image)  # \"Golden Retriever\"\n\n# Turn 3\nconv.messages[-1][1] = response2\nconv.append_message(conv.roles[0], \"What time of day is it?\")\nconv.append_message(conv.roles[1], None)\nresponse3 = generate(conv, model, image)\n```\n\n## Common tasks\n\n### Image captioning\n\n```python\nquestion = \"Describe this image in detail.\"\nresponse = ask(model, image, question)\n```\n\n### Visual question answering\n\n```python\nquestion = \"How many people are in the image?\"\nresponse = ask(model, image, question)\n```\n\n### Object detection (textual)\n\n```python\nquestion = \"List all the objects you can see in this image.\"\nresponse = ask(model, image, question)\n```\n\n### Scene understanding\n\n```python\nquestion = \"What is happening in this scene?\"\nresponse = ask(model, image, question)\n```\n\n### Document understanding\n\n```python\nquestion = \"What is the main topic of this document?\"\nresponse = ask(model, document_image, question)\n```\n\n## Training custom model\n\n```bash\n# Stage 1: Feature alignment (558K image-caption pairs)\nbash scripts\u002Fv1_5\u002Fpretrain.sh\n\n# Stage 2: Visual instruction tuning (150K instruction data)\nbash scripts\u002Fv1_5\u002Ffinetune.sh\n```\n\n## Quantization (reduce VRAM)\n\n```python\n# 4-bit quantization\ntokenizer, model, image_processor, context_len = load_pretrained_model(\n    model_path=\"liuhaotian\u002Fllava-v1.5-13b\",\n    model_base=None,\n    model_name=get_model_name_from_path(\"liuhaotian\u002Fllava-v1.5-13b\"),\n    load_4bit=True  # Reduces VRAM ~4×\n)\n\n# 8-bit quantization\nload_8bit=True  # Reduces VRAM ~2×\n```\n\n## Best practices\n\n1. **Start with 7B model** - Good quality, manageable VRAM\n2. **Use 4-bit quantization** - Reduces VRAM significantly\n3. **GPU required** - CPU inference extremely slow\n4. **Clear prompts** - Specific questions get better answers\n5. **Multi-turn conversations** - Maintain conversation context\n6. **Temperature 0.2-0.7** - Balance creativity\u002Fconsistency\n7. **max_new_tokens 512-1024** - For detailed responses\n8. **Batch processing** - Process multiple images sequentially\n\n## Performance\n\n| Model | VRAM (FP16) | VRAM (4-bit) | Speed (tokens\u002Fs) |\n|-------|-------------|--------------|------------------|\n| 7B | ~14 GB | ~4 GB | ~20 |\n| 13B | ~28 GB | ~8 GB | ~12 |\n| 34B | ~70 GB | ~18 GB | ~5 |\n\n*On A100 GPU*\n\n## Benchmarks\n\nLLaVA achieves competitive scores on:\n- **VQAv2**: 78.5%\n- **GQA**: 62.0%\n- **MM-Vet**: 35.4%\n- **MMBench**: 64.3%\n\n## Limitations\n\n1. **Hallucinations** - May describe things not in image\n2. **Spatial reasoning** - Struggles with precise locations\n3. **Small text** - Difficulty reading fine print\n4. **Object counting** - Imprecise for many objects\n5. **VRAM requirements** - Need powerful GPU\n6. **Inference speed** - Slower than CLIP\n\n## Integration with frameworks\n\n### LangChain\n\n```python\nfrom langchain.llms.base import LLM\n\nclass LLaVALLM(LLM):\n    def _call(self, prompt, stop=None):\n        # Custom LLaVA inference\n        return response\n\nllm = LLaVALLM()\n```\n\n### Gradio App\n\n```python\nimport gradio as gr\n\ndef chat(image, text, history):\n    response = ask_llava(model, image, text)\n    return response\n\ndemo = gr.ChatInterface(\n    chat,\n    additional_inputs=[gr.Image(type=\"pil\")],\n    title=\"LLaVA Chat\"\n)\ndemo.launch()\n```\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fhaotian-liu\u002FLLaVA ⭐ 23,000+\n- **Paper**: https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.08485\n- **Demo**: https:\u002F\u002Fllava.hliu.cc\n- **Models**: https:\u002F\u002Fhuggingface.co\u002Fliuhaotian\n- **License**: Apache 2.0\n\n\n",{"name":37,"author":38,"license":39,"version":40,"metadata":41,"description":54,"dependencies":55},"llava","Orchestra Research","MIT","1.0.0",{"hermes":42},{"tags":43},[44,45,46,47,48,49,50,51,52,53],"LLaVA","Vision-Language","Multimodal","Visual Question Answering","Image Chat","CLIP","Vicuna","Conversational AI","Instruction Tuning","VQA","Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna\u002FLLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.",[56,57,58],"transformers","torch","pillow","main","42ccd02cbf5e8e47839dc3eab6fc754dc6b339cf",".claude\u002Fskills\u002Ftsx-code-order",2,"https:\u002F\u002Fgithub.com\u002Fsudoprivacy\u002Fsudowork","https:\u002F\u002Fgithub.com\u002Fsudoprivacy","2026-11-11 10:56:31",{"source":8,"skillName":37,"commands":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add sudoprivacy\u002Fsudowork --skill llava",{"tool":72,"command":73},"bunx","bunx skills add sudoprivacy\u002Fsudowork --skill llava",{"tool":75,"command":76},"pnpm","pnpm dlx skills add sudoprivacy\u002Fsudowork --skill llava","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsudoprivacy\u002Fsudowork\u002Fblob\u002Fdev\u002F.claude\u002Fskills\u002Ftsx-code-order\u002FSKILL.md",true,[80],{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Ftraining.md","REFERENCE","参考文档",4738,"https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fllava\u002Freferences\u002Ftraining.md",[87,109,149,176,202,230],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":102,"publishedAt":32},"01M6DTQM16M8ZCQSVW6GYYB9GM","skill-creator","创建或更新 Sudowork 自定义技能，同时保留核心 skill creation \u002F skill-design 最佳实践。用于用户要求创建新技能、优化已有技能、打包导入 Sudowork，或让技能展示在我的技能自定义技能中。","https:\u002F\u002Fgithub.com\u002Fsudoprivacy\u002Fsudowork\u002Fblob\u002Fdev\u002Fapps\u002Fdesktop\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsudoprivacy\u002Fsudowork\u002Fblob\u002Fdev\u002Fapps\u002Fdesktop\u002Fskills\u002Fskill-creator\u002FSKILL.md",[94,99],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":100,"categoryName":101,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000023","Skill与智能体开发",[103,104,105,106,107,108],"skill creator","creator","design","creation","skill-design","skill creation",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":39,"licenseFileUrl":113,"sourceHtmlUrl":114,"categories":115,"keywords":125,"publishedAt":32},"01M6DTQEH8DMDYG9ET2PSB381S","shareone","Host HTML\u002FMarkdown pages and share PDF, Word, or PowerPoint docs as ShareOne short links. Use when publishing pages\u002Fdocs, adding passwords\u002Fwatermarks, comments, downloads, or updates.","https:\u002F\u002Fgithub.com\u002Fsudoprivacy\u002Fsudowork\u002Fblob\u002Fdev\u002Fapps\u002Fdesktop\u002Fskills\u002Fshareone\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fsudoprivacy\u002Fsudowork\u002Fblob\u002Fdev\u002Fapps\u002Fdesktop\u002Fskills\u002Fshareone\u002FSKILL.md",[116,119,122],{"categoryNo":117,"categoryName":118,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000002","文档处理",{"categoryNo":120,"categoryName":121,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":123,"categoryName":124,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000009","前端开发",[111,126,127,128,129,130,131,132,133,134,135,136,28,137,138,139,140,141,142,143,144,145,146,147,148,31],"PDF","pptx","docs","powerpoint","share","downloads","publish","sharing","markdown","Word","short","html","publishing","hosting","upload","pages","as","host","with","comments","links","passwords","updates",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":158,"publishedAt":32},"01M6DTQB7MRE9C1ETCRF8KCMY4","image-generation","Generate new images or edit existing images using AI. Use this skill when the user wants to create, generate, draw, design, or produce an image from a text description, OR when they want to modify, edit, alter, or transform an existing image (e.g. 'generate a picture of...', 'create an image', 'draw me a...', 'edit this image', 'change the background', 'modify the above picture', '生成图片', '画一张', '修改图片', '编辑上面的图').","https:\u002F\u002Fgithub.com\u002Fsudoprivacy\u002Fsudowork\u002Fblob\u002Fdev\u002Fapps\u002Fdesktop\u002Fskills\u002Fimage-generation\u002FSKILL.md",[155],{"categoryNo":156,"categoryName":157,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000016","图像与多媒体",[159,160,161,105,162,163,164,165,166,167,168,169,28,170,171,172,173,174,31,175],"image","Image Generation","generation","change","create","generate","produce","生成","text","edit","user","images","draw","me","transform","Existing","new",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":183,"publishedAt":32},"01M6DTQ7Y4CZRXENW8272CNFGD","image-analysis","Analyze, describe, or answer questions about image content using vision AI. Use this skill when the user asks anything about an image — what it shows, what's in it, reading text\u002Fdiagrams, identifying objects, or any question referencing a previous image (e.g. 'what is in this image', 'read the text in this screenshot', 'explain this diagram', 'tell me about the image above', '识别图片', '分析图片内容').","https:\u002F\u002Fgithub.com\u002Fsudoprivacy\u002Fsudowork\u002Fblob\u002Fdev\u002Fapps\u002Fdesktop\u002Fskills\u002Fimage-analysis\u002FSKILL.md",[182],{"categoryNo":156,"categoryName":157,"taxonomyType":97,"taxonomyTypeDesc":98},[159,184,185,186,187,188,189,167,190,191,192,169,28,193,194,195,196,172,197,198,199,200,201,31],"analysis","image analysis","diagram","screenshot","content","analyze","explain","question","read","vision","diagrams","vision ai","objects","about","questions","reading","answer","describe",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":208,"publishedAt":32},"01M6DTQ4MFX1843KSW940WHB3R","auto-login","Log in to a website automatically using credentials saved in the local key store. Use when the user wants unattended\u002Frepeat login to a site (no re-scanning QR, no re-typing passwords), e.g. '帮我自动登录这个网站', 'set up auto-login for X', '记住这个网站的登录'. The plaintext password is NEVER seen by you — the user fills it in 秘钥管理 and sudowork fills the form itself.","https:\u002F\u002Fgithub.com\u002Fsudoprivacy\u002Fsudowork\u002Fblob\u002Fdev\u002Fapps\u002Fdesktop\u002Fskills\u002Fauto-login\u002FSKILL.md",[],[209,210,211,212,213,214,215,216,169,28,217,218,219,220,221,222,223,224,225,226,147,227,228,229,31],"auto","auto login","login","website","SET","credentials","password","site","never","scanning","up","log","local","form","typing","you","re","qr","saved","for","log in",{"skillNo":231,"name":232,"nameZh":6,"description":233,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":234,"categories":235,"keywords":237,"publishedAt":32},"01M6DTQ1TAD7RHXQ65RRKW468N","video-subtitles","Generate timed subtitles from video or audio, translate their text, and burn subtitles into a new video. Use for captions, SRT, video subtitles, or adding translated subtitles in Sudowork desktop or WebUI cloud conversations.","https:\u002F\u002Fgithub.com\u002Fsudoprivacy\u002Fsudowork\u002Fblob\u002Fdev\u002Fapps\u002Fdesktop\u002Fskills\u002F_builtin\u002Fvideo-subtitles\u002FSKILL.md",[236],{"categoryNo":156,"categoryName":157,"taxonomyType":97,"taxonomyTypeDesc":98},[238,239,240,241,164,242,243,244,245,167,28,246,247,248,249,228,175],"subtitles","Video","video subtitles","translate","desktop","cloud","Audio","Captions","webui","burn","conversations","srt"]