[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F0K7NCJ4XBMVYRE7HTNR30":3,"skill-same:01M7F0K7NCJ4XBMVYRE7HTNR30":52},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M7F0K7NCJ4XBMVYRE7HTNR30","hf-mcp",null,"Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fhf-mcp\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: hf-mcp\ndescription: Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.\nrisk: critical\nsource: https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fskills\u002Ftree\u002Fmain\u002Fhf-mcp\u002Fskills\u002Fhf-mcp\nsource_repo: huggingface\u002Fskills\nsource_type: official\ndate_added: 2026-07-01\nlicense: Apache-2.0\nlicense_source: https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fskills\u002Fblob\u002Fmain\u002FLICENSE\n---\n\n# Hugging Face MCP Server\n## When to Use\n\nUse this skill when you need use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.\n\n\nConnect AI assistants to the Hugging Face Hub. Setup: https:\u002F\u002Fhuggingface.co\u002Fsettings\u002Fmcp\n\n## Use Cases & Examples\n\n### Find the Best Model for a Task\n\n```\nUser: \"Find the best model for code generation\"\n\n1. model_search(task=\"text-generation\", query=\"code\", sort=\"trendingScore\", limit=10)\n2. hub_repo_details(repo_ids=[\"top-result-id\"], include_readme=true)\n```\n\n### Compare Models from Different Providers\n\n```\nUser: \"Compare Llama vs Qwen for text generation\"\n\n1. model_search(author=\"meta-llama\", task=\"text-generation\", sort=\"downloads\", limit=5)\n2. model_search(author=\"Qwen\", task=\"text-generation\", sort=\"downloads\", limit=5)\n3. hub_repo_details(repo_ids=[\"meta-llama\u002FLlama-3.2-1B\", \"Qwen\u002FQwen3-8B\"], include_readme=true)\n```\n\n### Find Training Datasets\n\n```\nUser: \"Find datasets for sentiment analysis in English\"\n\n1. dataset_search(query=\"sentiment\", tags=[\"language:en\", \"task_categories:text-classification\"], sort=\"downloads\")\n2. hub_repo_details(repo_ids=[\"top-dataset-id\"], repo_type=\"dataset\", include_readme=true)\n```\n\n### Discover AI Tools (MCP Spaces)\n\n```\nUser: \"Find a tool that can remove image backgrounds\"\n\n1. space_search(query=\"background removal\", mcp=true)\n2. dynamic_space(operation=\"view_parameters\", space_name=\"result-space-id\")\n3. dynamic_space(operation=\"invoke\", space_name=\"result-space-id\", parameters=\"{...}\")\n```\n\n### Generate Images\n\n```\nUser: \"Create an image of a robot reading a book\"\n\n1. dynamic_space(operation=\"discover\")  # See available tasks\n2. gr1_flux1_schnell_infer(prompt=\"a robot sitting in a library reading a book, warm lighting, detailed\")\n```\n\n### Research a Topic\n\n```\nUser: \"What are the latest papers on RLHF?\"\n\n1. paper_search(query=\"reinforcement learning from human feedback\", results_limit=10)\n2. hub_repo_details(repo_ids=[\"paper-linked-model\"], include_readme=true)  # If paper links to models\n```\n\n### Learn How to Use a Library\n\n```\nUser: \"How do I fine-tune with LoRA using PEFT?\"\n\n1. hf_doc_search(query=\"LoRA fine-tuning\", product=\"peft\")\n2. hf_doc_fetch(doc_url=\"https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fpeft\u002F...\")\n```\n\n### Run a Quick GPU Job\n\n```\nUser: \"Run this Python script on a GPU\"\n\nhf_jobs(operation=\"uv\", args={\n  \"script\": \"# \u002F\u002F\u002F script\\n# dependencies = [\\\"torch\\\"]\\n# \u002F\u002F\u002F\\nimport torch\\nprint(torch.cuda.is_available())\",\n  \"flavor\": \"t4-small\"\n})\n```\n\n### Train a Model on Cloud GPU\n\n```\nUser: \"Run my training script on an A10G\"\n\nhf_jobs(operation=\"run\", args={\n  \"image\": \"pytorch\u002Fpytorch:2.5.1-cuda12.4-cudnn9-runtime\",\n  \"command\": [\"\u002Fbin\u002Fsh\", \"-lc\", \"pip install transformers trl && python train.py\"],\n  \"flavor\": \"a10g-small\",\n  \"secrets\": {\"HF_TOKEN\": \"$HF_TOKEN\"}\n})\n```\n\n### Check Job Status\n\n```\nUser: \"What's happening with my training job?\"\n\n1. hf_jobs(operation=\"ps\")\n2. hf_jobs(operation=\"logs\", args={\"job_id\": \"job-xxxxx\"})\n```\n\n### Explore What's Trending\n\n```\nUser: \"What models are trending right now?\"\n\nmodel_search(sort=\"trendingScore\", limit=20)\n```\n\n### Get Model Card Details\n\n```\nUser: \"Tell me about Mistral-7B\"\n\nhub_repo_details(repo_ids=[\"mistralai\u002FMistral-7B-v0.1\"], include_readme=true)\n```\n\n### Find Quantized Models\n\n```\nUser: \"Find GGUF versions of Llama 3\"\n\nmodel_search(query=\"Llama 3 GGUF\", sort=\"downloads\", limit=10)\n```\n\n### Use a Gradio Space as a Tool\n\n```\nUser: \"Transcribe this audio file\"\n\n1. space_search(query=\"speech to text transcription\", mcp=true)\n2. dynamic_space(operation=\"view_parameters\", space_name=\"openai\u002Fwhisper\")\n3. dynamic_space(operation=\"invoke\", space_name=\"openai\u002Fwhisper\", parameters=\"{\\\"audio\\\": \\\"...\\\"}\")\n```\n\n### Schedule Recurring Jobs\n\n```\nUser: \"Run this data sync every day at midnight\"\n\nhf_jobs(operation=\"scheduled uv\", args={\n  \"script\": \"...\",\n  \"cron\": \"0 0 * * *\",\n  \"flavor\": \"cpu-basic\"\n})\n```\n\n## Tool Selection Guide\n\n| Goal | Tool |\n|------|------|\n| Find models | `model_search` |\n| Find datasets | `dataset_search` |\n| Find Spaces\u002Fapps | `space_search` |\n| Find papers | `paper_search` |\n| Get repo README\u002Fdetails | `hub_repo_details` |\n| Learn library usage | `hf_doc_search` → `hf_doc_fetch` |\n| Run code on GPU\u002FCPU | `hf_jobs` |\n| Use Gradio apps as tools | `dynamic_space` |\n| Generate images | `gr1_flux1_schnell_infer` or `dynamic_space` |\n| Check auth | `hf_whoami` |\n\n## Tips\n\n- Use `sort=\"trendingScore\"` to find what's popular now\n- Use `sort=\"downloads\"` to find battle-tested options\n- Set `mcp=true` in `space_search` to find Spaces usable as tools\n- Use `include_readme=true` in `hub_repo_details` for full model\u002Fdataset documentation\n- For jobs accessing private repos, always include `secrets: {\"HF_TOKEN\": \"$HF_TOKEN\"}`\n- Use `dynamic_space(operation=\"discover\")` to see all available Space-based tasks\n\n## Limitations\n\n- Use this skill only when the task clearly matches its upstream product or API scope.\n- Verify commands, API behavior, pricing, quotas, credentials, and deployment effects against current official documentation before making changes.\n- Do not treat generated examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.\n","# Hugging Face MCP Server\n## When to Use\n\nUse this skill when you need use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.\n\n\nConnect AI assistants to the Hugging Face Hub. Setup: https:\u002F\u002Fhuggingface.co\u002Fsettings\u002Fmcp\n\n## Use Cases & Examples\n\n### Find the Best Model for a Task\n\n```\nUser: \"Find the best model for code generation\"\n\n1. model_search(task=\"text-generation\", query=\"code\", sort=\"trendingScore\", limit=10)\n2. hub_repo_details(repo_ids=[\"top-result-id\"], include_readme=true)\n```\n\n### Compare Models from Different Providers\n\n```\nUser: \"Compare Llama vs Qwen for text generation\"\n\n1. model_search(author=\"meta-llama\", task=\"text-generation\", sort=\"downloads\", limit=5)\n2. model_search(author=\"Qwen\", task=\"text-generation\", sort=\"downloads\", limit=5)\n3. hub_repo_details(repo_ids=[\"meta-llama\u002FLlama-3.2-1B\", \"Qwen\u002FQwen3-8B\"], include_readme=true)\n```\n\n### Find Training Datasets\n\n```\nUser: \"Find datasets for sentiment analysis in English\"\n\n1. dataset_search(query=\"sentiment\", tags=[\"language:en\", \"task_categories:text-classification\"], sort=\"downloads\")\n2. hub_repo_details(repo_ids=[\"top-dataset-id\"], repo_type=\"dataset\", include_readme=true)\n```\n\n### Discover AI Tools (MCP Spaces)\n\n```\nUser: \"Find a tool that can remove image backgrounds\"\n\n1. space_search(query=\"background removal\", mcp=true)\n2. dynamic_space(operation=\"view_parameters\", space_name=\"result-space-id\")\n3. dynamic_space(operation=\"invoke\", space_name=\"result-space-id\", parameters=\"{...}\")\n```\n\n### Generate Images\n\n```\nUser: \"Create an image of a robot reading a book\"\n\n1. dynamic_space(operation=\"discover\")  # See available tasks\n2. gr1_flux1_schnell_infer(prompt=\"a robot sitting in a library reading a book, warm lighting, detailed\")\n```\n\n### Research a Topic\n\n```\nUser: \"What are the latest papers on RLHF?\"\n\n1. paper_search(query=\"reinforcement learning from human feedback\", results_limit=10)\n2. hub_repo_details(repo_ids=[\"paper-linked-model\"], include_readme=true)  # If paper links to models\n```\n\n### Learn How to Use a Library\n\n```\nUser: \"How do I fine-tune with LoRA using PEFT?\"\n\n1. hf_doc_search(query=\"LoRA fine-tuning\", product=\"peft\")\n2. hf_doc_fetch(doc_url=\"https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fpeft\u002F...\")\n```\n\n### Run a Quick GPU Job\n\n```\nUser: \"Run this Python script on a GPU\"\n\nhf_jobs(operation=\"uv\", args={\n  \"script\": \"# \u002F\u002F\u002F script\\n# dependencies = [\\\"torch\\\"]\\n# \u002F\u002F\u002F\\nimport torch\\nprint(torch.cuda.is_available())\",\n  \"flavor\": \"t4-small\"\n})\n```\n\n### Train a Model on Cloud GPU\n\n```\nUser: \"Run my training script on an A10G\"\n\nhf_jobs(operation=\"run\", args={\n  \"image\": \"pytorch\u002Fpytorch:2.5.1-cuda12.4-cudnn9-runtime\",\n  \"command\": [\"\u002Fbin\u002Fsh\", \"-lc\", \"pip install transformers trl && python train.py\"],\n  \"flavor\": \"a10g-small\",\n  \"secrets\": {\"HF_TOKEN\": \"$HF_TOKEN\"}\n})\n```\n\n### Check Job Status\n\n```\nUser: \"What's happening with my training job?\"\n\n1. hf_jobs(operation=\"ps\")\n2. hf_jobs(operation=\"logs\", args={\"job_id\": \"job-xxxxx\"})\n```\n\n### Explore What's Trending\n\n```\nUser: \"What models are trending right now?\"\n\nmodel_search(sort=\"trendingScore\", limit=20)\n```\n\n### Get Model Card Details\n\n```\nUser: \"Tell me about Mistral-7B\"\n\nhub_repo_details(repo_ids=[\"mistralai\u002FMistral-7B-v0.1\"], include_readme=true)\n```\n\n### Find Quantized Models\n\n```\nUser: \"Find GGUF versions of Llama 3\"\n\nmodel_search(query=\"Llama 3 GGUF\", sort=\"downloads\", limit=10)\n```\n\n### Use a Gradio Space as a Tool\n\n```\nUser: \"Transcribe this audio file\"\n\n1. space_search(query=\"speech to text transcription\", mcp=true)\n2. dynamic_space(operation=\"view_parameters\", space_name=\"openai\u002Fwhisper\")\n3. dynamic_space(operation=\"invoke\", space_name=\"openai\u002Fwhisper\", parameters=\"{\\\"audio\\\": \\\"...\\\"}\")\n```\n\n### Schedule Recurring Jobs\n\n```\nUser: \"Run this data sync every day at midnight\"\n\nhf_jobs(operation=\"scheduled uv\", args={\n  \"script\": \"...\",\n  \"cron\": \"0 0 * * *\",\n  \"flavor\": \"cpu-basic\"\n})\n```\n\n## Tool Selection Guide\n\n| Goal | Tool |\n|------|------|\n| Find models | `model_search` |\n| Find datasets | `dataset_search` |\n| Find Spaces\u002Fapps | `space_search` |\n| Find papers | `paper_search` |\n| Get repo README\u002Fdetails | `hub_repo_details` |\n| Learn library usage | `hf_doc_search` → `hf_doc_fetch` |\n| Run code on GPU\u002FCPU | `hf_jobs` |\n| Use Gradio apps as tools | `dynamic_space` |\n| Generate images | `gr1_flux1_schnell_infer` or `dynamic_space` |\n| Check auth | `hf_whoami` |\n\n## Tips\n\n- Use `sort=\"trendingScore\"` to find what's popular now\n- Use `sort=\"downloads\"` to find battle-tested options\n- Set `mcp=true` in `space_search` to find Spaces usable as tools\n- Use `include_readme=true` in `hub_repo_details` for full model\u002Fdataset documentation\n- For jobs accessing private repos, always include `secrets: {\"HF_TOKEN\": \"$HF_TOKEN\"}`\n- Use `dynamic_space(operation=\"discover\")` to see all available Space-based tasks\n\n## Limitations\n\n- Use this skill only when the task clearly matches its upstream product or API scope.\n- Verify commands, API behavior, pricing, quotas, credentials, and deployment effects against current official documentation before making changes.\n- Do not treat generated examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.\n",{"name":5,"risk":24,"source":25,"license":15,"date_added":26,"description":7,"source_repo":27,"source_type":28,"license_source":29},"critical","https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fskills\u002Ftree\u002Fmain\u002Fhf-mcp\u002Fskills\u002Fhf-mcp",1782864000000,"huggingface\u002Fskills","official","https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fskills\u002Fblob\u002Fmain\u002FLICENSE","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fhf-mcp",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill hf-mcp",{"tool":44,"command":45},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill hf-mcp",{"tool":47,"command":48},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill hf-mcp","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fhf-mcp\u002FSKILL.md",true,[],[53,61,66,73,80,87],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":57,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":62,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":57,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":57,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":57,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":57,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":57,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]