[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D7N6CE71VCBXK8W1YM3PKY":3,"skill-same:01M7D7N6CE71VCBXK8W1YM3PKY":58},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":5,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7D7N6CE71VCBXK8W1YM3PKY","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.","tangyixiao\u002Ftangyixiao-skills","tangyixiao","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F115929632?v=4","01M7D582YK6A4M63CAK4CSY4EW","Tang Yixiao","01M7D582Z64DMRSYR872SR34SA",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fhf-mcp\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fhf-mcp\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: hf-mcp\ndescription: Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces,\n  papers. Get repo details, fetch documentation, run compute jobs, and use Gradio\n  Spaces as AI tools. Available when connected to the HF MCP server.\n---\n\n# Hugging Face MCP Server\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","# Hugging Face MCP Server\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",{"name":5,"description":7},"main","2a870f189175a48c39f5f7e26a6d93b0be9cd13b",0,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills","https:\u002F\u002Ftangyixiao.github.io\u002Ftangyixiao-skills\u002F","https:\u002F\u002Fgithub.com\u002Ftangyixiao","http:\u002F\u002Fwww.sxyz.net\u002F","I am Tang Yixiao, a student in Shaoxing No.1 High School. I am eager to learn on GitHub and contribute my part to this community.","2026-11-11 15:45:59",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add tangyixiao\u002Ftangyixiao-skills --skill hf-mcp",{"tool":40,"command":41},"bunx","bunx skills add tangyixiao\u002Ftangyixiao-skills --skill hf-mcp",{"tool":43,"command":44},"pnpm","pnpm dlx skills add tangyixiao\u002Ftangyixiao-skills --skill hf-mcp","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fhf-mcp\u002FSKILL.md",true,[48,54],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"INSTALL-SOURCE.json","REFERENCE","参考文档",484,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fhf-mcp\u002FINSTALL-SOURCE.json",{"path":55,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":16},"LICENSE","许可证",11357,[59,67,76,84,92,100],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":63,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":20},"01M7D8JK8FYBFNNAJXWD89CFH7","xlsx","Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fxlsx\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fxlsx\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":71,"licenseFileUrl":72,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":20},"01M7D8JG8ERGGQQAMX0DWCG9GR","writing-shape","Writing, exploit: shape raw material into an article, paragraph by paragraph.","MIT","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-shape\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-shape\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":71,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":20},"01M7D8JE672GW3EHSE8EF185M4","writing-fragments","Writing, explore: mine raw fragments, no structure yet.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-fragments\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-fragments\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":71,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":20},"01M7D8JBK572YDFMND8Q6CEYJW","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":71,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":20},"01M7D8J5QPWEXX61EGBKYH73R8","writing-clearly-and-concisely","Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-clearly-and-concisely\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-clearly-and-concisely\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":71,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":20},"01M7D8J36YWC8WZS5DK5AH03CD","writing-beats","Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-beats\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-beats\u002FSKILL.md",[],[]]