[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-huggingface-huggingface-gradio-zh-CN":3,"guides-for-huggingface-huggingface-gradio":733,"similar-k1738z37awwqt5ngyf19jvq0dn86n4zs-zh-CN":734},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":242,"isFallback":239,"parentExtension":247,"providers":280,"relations":284,"repo":285,"tags":731,"workflow":732},1778690773482.4875,"k1738z37awwqt5ngyf19jvq0dn86n4zs",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.",{"claudeCode":12},"huggingface/skills","huggingface-gradio","https://github.com/huggingface/skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":223,"workflow":240},1778691303537.7722,"kn74j835wj5ge2s7fvra0mk74s86m22j","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"targetMarket":216,"tier":217,"useCases":218},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,113,116,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of building Gradio web UIs and demos in Python and identifies specific use cases like creating apps, components, and chatbots.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill provides specific guidance and examples for using the Gradio library, going beyond generic Python UI development to address the nuances of Gradio's components and patterns.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill covers the core Gradio API, components, and patterns with detailed guides and examples, enabling users to build and manage Gradio applications comprehensively.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill is focused on Gradio web UI development in Python, adhering to a single domain without extending into unrelated areas.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description is concise, accurate, and clearly reflects the skill's purpose of building Gradio web UIs and demos in Python.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill does not expose specific tools or commands; it provides guidance and examples for using the Gradio library programmatically.",{"category":45,"check":46,"severity":24,"summary":47},"Documentation","Configuration & parameter reference","The SKILL.md file provides detailed signatures for key Gradio components, outlining their parameters and expected usage.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","This skill does not expose explicit tools or commands, so tool naming is not applicable.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","This skill does not expose specific tools or commands, so I/O surface is not applicable.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The extension is licensed under the Apache-2.0 license, as indicated by the bundled LICENSE file.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The last commit was on 2026-05-12, which is within the last 3 months.",{"category":59,"check":63,"severity":42,"summary":64},"Dependency Management","The skill itself does not appear to introduce external Python dependencies beyond the Gradio library, which is assumed to be installed by the user.",{"category":66,"check":67,"severity":42,"summary":68},"Security","Secret Management","The skill does not handle any secrets.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill provides guidance on using the Gradio library and does not involve loading or executing third-party data or code in a way that could lead to injection vulnerabilities.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill primarily guides the use of the Gradio library and does not involve fetching external content at runtime.",{"category":66,"check":76,"severity":42,"summary":77},"Sandbox Isolation","The skill is instructional and does not perform file system operations or interact with the OS in a way that requires sandbox isolation.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No detached-process spawns or deny-retry loops were detected, as the skill is purely instructional.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill does not contain any instructions to read or submit confidential data to a third party.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content is free of hidden-steering tricks, and all descriptions are clean printable ASCII.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The skill's content is plain, readable Python code and Markdown, with no obfuscation detected.",{"category":92,"check":93,"severity":42,"summary":94},"Portability","Structural Assumption","The skill does not make structural assumptions about the user's project organization outside of needing Python and Gradio installed.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","4 open issues and 6 closed issues in the last 90 days indicate active maintenance with a reasonable closure rate.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The repository is actively maintained with recent commits, indicating a versioning signal through commit history.",{"category":104,"check":105,"severity":42,"summary":106},"Code Execution","Validation","This skill provides instructional content and code examples, rather than executable tools with input arguments that require schema validation.",{"category":66,"check":108,"severity":42,"summary":109},"Unguarded Destructive Operations","The skill is instructional and does not contain any destructive operations.",{"category":104,"check":111,"severity":42,"summary":112},"Error Handling","The skill provides guidance and examples, not executable code that generates user-facing errors. The Gradio library itself handles error handling within applications built using this skill.",{"category":104,"check":114,"severity":42,"summary":115},"Logging","As this skill is purely instructional and does not perform actions, logging is not applicable.",{"category":117,"check":118,"severity":42,"summary":119},"Compliance","GDPR","The skill does not operate on personal data.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The skill is focused on Python and Gradio, with no regional or jurisdictional limitations, making it globally applicable.",{"category":92,"check":124,"severity":42,"summary":125},"Runtime stability","The skill is instructional and does not assume a specific runtime environment beyond Python and the Gradio library.",{"category":45,"check":127,"severity":24,"summary":128},"README","The README.md file clearly explains what Hugging Face Skills are and how to install and use them, including this Gradio skill.",{"category":33,"check":130,"severity":42,"summary":131},"Tool surface size","This skill does not expose tools or commands, so tool surface size is not applicable.",{"category":40,"check":133,"severity":42,"summary":134},"Overlapping near-synonym tools","This skill does not expose tools or commands, so overlapping synonyms are not applicable.",{"category":45,"check":136,"severity":24,"summary":137},"Phantom features","All features advertised in the README and SKILL.md, such as building Gradio apps and using components, have corresponding implementations and documentation within the Gradio library as referenced by the skill.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","The README provides clear installation instructions for various agent platforms (Claude Code, Codex, Gemini CLI, Cursor) and includes copy-pasteable commands.",{"category":143,"check":144,"severity":42,"summary":145},"Errors","Actionable error messages","As this skill is purely instructional, it does not generate user-facing errors. The Gradio library itself would handle error messages for applications built using this skill.",{"category":147,"check":148,"severity":42,"summary":149},"Execution","Pinned dependencies","The skill itself does not bundle scripts with dependencies; it relies on the user's Python environment and the Gradio library, which should be managed by the user.",{"category":33,"check":151,"severity":42,"summary":152},"Dry-run preview","The skill is instructional and does not involve state-changing operations or outbound data sending that would require a dry-run mode.",{"category":154,"check":155,"severity":42,"summary":156},"Protocol","Idempotent retry & timeouts","This skill is instructional and does not involve remote calls or state-changing operations that require idempotency or timeouts.",{"category":117,"check":158,"severity":42,"summary":159},"Telemetry opt-in","The skill does not emit any telemetry.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill's purpose is precisely defined, stating it's for building Gradio web UIs and demos in Python, and specifying use cases like creating apps, components, and chatbots.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter is concise and clearly states the skill's name and purpose within the character limit.",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md body is well-structured with guides, core patterns, component signatures, and custom component examples, staying within a reasonable length and delegating detail to linked guides.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md outlines core patterns and links to external Gradio guides for more in-depth information, demonstrating progressive disclosure.",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","This skill is instructional and does not involve deep exploration or code review that would necessitate a forked context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The skill includes numerous end-to-end examples in `examples.md`, covering various Gradio features like Blocks, Interface, ChatInterface, and custom components.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The Gradio documentation, linked by the skill, covers various component configurations and usage patterns that implicitly address edge cases and limitations of building UIs.",{"category":104,"check":183,"severity":42,"summary":184},"Tool Fallback","This skill does not rely on external MCP servers or tools and therefore has no fallback requirement.",{"category":186,"check":187,"severity":42,"summary":188},"Safety","Halt on unexpected state","As an instructional skill, it does not involve state-changing operations or preconditions that would need to be checked for unexpected state.",{"category":92,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill is self-contained and focuses solely on Gradio, without implicit reliance on other skills.",1778691303430,"This skill provides comprehensive guidance and examples for using the Gradio Python library to build interactive web UIs, demos, and chatbots. It covers core patterns like `Interface` and `Blocks`, key component signatures, custom component creation, and event listeners.",[195,196,197,198,199],"Build Gradio web UIs","Create Gradio apps and components","Implement event listeners and layouts","Develop Gradio chatbots","Utilize core Gradio patterns (Interface, Blocks, ChatInterface)",[201,202,203],"Developing general Python web applications outside of Gradio","Detailed explanation of underlying web technologies (HTML, CSS, JavaScript) beyond their use within Gradio components","Deployment strategies for Gradio applications beyond basic `launch()`","3.0.0","4.4.0","Build Gradio web UIs and demos in Python with clear guidance on components, layouts, and interactivity.","The skill is well-documented, provides extensive examples, and covers its domain comprehensively. It meets all criteria for a verified tier, with no significant findings.",98,"Excellent skill for building Gradio web UIs and demos in Python.",[211,212,213,214,215],"python","web-ui","gradio","demo-building","machine-learning","global","verified",[219,220,221,222],"When creating or editing Gradio apps","When defining Gradio components and their interactions","When structuring the layout of a Gradio application","When building chatbot interfaces with Gradio",{"codeQuality":224,"collectedAt":226,"documentation":227,"maintenance":230,"security":236,"testCoverage":238},{"hasLockfile":225},false,1778691285470,{"descriptionLength":228,"readmeSize":229},134,9821,{"closedIssues90d":231,"forks":232,"hasChangelog":225,"openIssues90d":233,"pushedAt":234,"stars":235},6,663,4,1778593131000,10482,{"hasNpmPackage":225,"license":237,"smitheryVerified":225},"Apache-2.0",{"hasCi":239,"hasTests":225},true,{"updatedAt":241},1778691303545,{"basePath":243,"githubOwner":244,"githubRepo":245,"locale":18,"slug":13,"type":246},"skills/huggingface-gradio","huggingface","skills","skill",{"_creationTime":248,"_id":249,"community":250,"display":251,"identity":256,"parentExtension":259,"providers":260,"relations":274,"tags":276,"workflow":277},1778690773482.486,"k175g1spb5757qt4tnj9cktcn986mshy",{"reviewCount":8},{"description":252,"installMethods":253,"name":255,"sourceUrl":14},"Agent Skills for AI/ML tasks including dataset creation, model training, evaluation, and research paper publishing on Hugging Face Hub",{"claudeCode":254},"huggingface-skills","Hugging Face Skills",{"basePath":257,"githubOwner":244,"githubRepo":245,"locale":18,"slug":245,"type":258},"","plugin",null,{"evaluate":261,"extract":269},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":262,"targetMarket":216,"tier":217},[244,263,264,265,266,267,268,211],"ai","ml","datasets","models","training","cli",{"commitSha":270,"license":237,"plugin":271},"HEAD",{"mcpCount":8,"provider":272,"skillCount":273},"classify",14,{"repoId":275},"kd72xwt5xnc0ktc4p7smzfcp3986m959",[263,268,265,244,264,266,211,267],{"evaluatedAt":278,"extractAt":279,"updatedAt":278},1778691185872,1778690773482,{"evaluate":281,"extract":283},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":282,"targetMarket":216,"tier":217},[211,212,213,214,215],{"commitSha":270},{"parentExtensionId":249,"repoId":275},{"_creationTime":286,"_id":275,"identity":287,"providers":288,"workflow":727},1778689536128.5474,{"githubOwner":244,"githubRepo":245,"sourceUrl":14},{"classify":289,"discover":720,"github":723},{"commitSha":270,"extensions":290},[291,305,314,322,330,338,346,354,362,370,378,386,391,399,407,415,458,466,472,478,495,501,508,550,561,580,586,606,618,642,700],{"basePath":257,"description":252,"displayName":254,"installMethods":292,"rationale":293,"selectedPaths":294,"source":303,"sourceLanguage":18,"type":304},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[295,298,300],{"path":296,"priority":297},".claude-plugin/marketplace.json","mandatory",{"path":299,"priority":297},"README.md",{"path":301,"priority":302},"LICENSE","high","rule","marketplace",{"basePath":306,"description":307,"displayName":308,"installMethods":309,"rationale":310,"selectedPaths":311,"source":303,"sourceLanguage":18,"type":258},"skills/huggingface-llm-trainer","Train or fine-tune language models using TRL on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes hardware selection, cost estimation, Trackio monitoring, and Hub persistence.","huggingface-llm-trainer",{"claudeCode":308},"inline plugin source from marketplace.json at skills/huggingface-llm-trainer",[312],{"path":313,"priority":302},"SKILL.md",{"basePath":315,"description":316,"displayName":317,"installMethods":318,"rationale":319,"selectedPaths":320,"source":303,"sourceLanguage":18,"type":258},"skills/huggingface-local-models","Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.","huggingface-local-models",{"claudeCode":317},"inline plugin source from marketplace.json at skills/huggingface-local-models",[321],{"path":313,"priority":302},{"basePath":323,"description":324,"displayName":325,"installMethods":326,"rationale":327,"selectedPaths":328,"source":303,"sourceLanguage":18,"type":258},"skills/huggingface-paper-publisher","Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.","huggingface-paper-publisher",{"claudeCode":325},"inline plugin source from marketplace.json at skills/huggingface-paper-publisher",[329],{"path":313,"priority":302},{"basePath":331,"description":332,"displayName":333,"installMethods":334,"rationale":335,"selectedPaths":336,"source":303,"sourceLanguage":18,"type":258},"skills/huggingface-papers","Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata like authors, linked models, datasets, Spaces, and media URLs when needed.","huggingface-papers",{"claudeCode":333},"inline plugin source from marketplace.json at skills/huggingface-papers",[337],{"path":313,"priority":302},{"basePath":339,"description":340,"displayName":341,"installMethods":342,"rationale":343,"selectedPaths":344,"source":303,"sourceLanguage":18,"type":258},"skills/huggingface-community-evals","Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom evaluations with vLLM/lighteval.","huggingface-community-evals",{"claudeCode":341},"inline plugin source from marketplace.json at skills/huggingface-community-evals",[345],{"path":313,"priority":302},{"basePath":347,"description":348,"displayName":349,"installMethods":350,"rationale":351,"selectedPaths":352,"source":303,"sourceLanguage":18,"type":258},"skills/huggingface-best","Find the best AI model for any task by querying Hugging Face leaderboards and benchmarks. Recommends top models based on task type, hardware constraints, and benchmark scores.","huggingface-best",{"claudeCode":349},"inline plugin source from marketplace.json at skills/huggingface-best",[353],{"path":313,"priority":302},{"basePath":355,"description":356,"displayName":357,"installMethods":358,"rationale":359,"selectedPaths":360,"source":303,"sourceLanguage":18,"type":258},"skills/hf-cli","Execute Hugging Face Hub operations using the hf CLI. Download models/datasets, upload files, manage repos, and run cloud compute jobs.","hf-cli",{"claudeCode":357},"inline plugin source from marketplace.json at skills/hf-cli",[361],{"path":313,"priority":302},{"basePath":363,"description":364,"displayName":365,"installMethods":366,"rationale":367,"selectedPaths":368,"source":303,"sourceLanguage":18,"type":258},"skills/huggingface-trackio","Track and visualize ML training experiments with Trackio. Log metrics via Python API and retrieve them via CLI. Supports real-time dashboards synced to HF Spaces.","huggingface-trackio",{"claudeCode":365},"inline plugin source from marketplace.json at skills/huggingface-trackio",[369],{"path":313,"priority":302},{"basePath":371,"description":372,"displayName":373,"installMethods":374,"rationale":375,"selectedPaths":376,"source":303,"sourceLanguage":18,"type":258},"skills/huggingface-datasets","Explore, query, and extract data from any Hugging Face dataset using the Dataset Viewer REST API and npx tooling. Zero Python dependencies — covers split/config discovery, row pagination, text search, filtering, SQL via parquetlens, and dataset upload via CLI.","huggingface-datasets",{"claudeCode":373},"inline plugin source from marketplace.json at skills/huggingface-datasets",[377],{"path":313,"priority":302},{"basePath":379,"description":380,"displayName":381,"installMethods":382,"rationale":383,"selectedPaths":384,"source":303,"sourceLanguage":18,"type":258},"skills/huggingface-tool-builder","Build reusable scripts for Hugging Face Hub and API workflows. Useful for chaining API calls, enriching Hub metadata, or automating repeated tasks.","huggingface-tool-builder",{"claudeCode":381},"inline plugin source from marketplace.json at skills/huggingface-tool-builder",[385],{"path":313,"priority":302},{"basePath":243,"description":10,"displayName":13,"installMethods":387,"rationale":388,"selectedPaths":389,"source":303,"sourceLanguage":18,"type":258},{"claudeCode":13},"inline plugin source from marketplace.json at skills/huggingface-gradio",[390],{"path":313,"priority":302},{"basePath":392,"description":393,"displayName":394,"installMethods":395,"rationale":396,"selectedPaths":397,"source":303,"sourceLanguage":18,"type":258},"skills/transformers-js","Run state-of-the-art machine learning models directly in JavaScript/TypeScript for NLP, computer vision, audio processing, and multimodal tasks. Works in Node.js and browsers with WebGPU/WASM using Hugging Face models.","transformers-js",{"claudeCode":394},"inline plugin source from marketplace.json at skills/transformers-js",[398],{"path":313,"priority":302},{"basePath":400,"description":401,"displayName":402,"installMethods":403,"rationale":404,"selectedPaths":405,"source":303,"sourceLanguage":18,"type":258},"skills/huggingface-vision-trainer","Train and fine-tune object detection models (RTDETRv2, YOLOS, DETR and others) and image classification models (timm and transformers models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3) using Transformers Trainer API on Hugging Face Jobs infrastructure or locally. Includes COCO dataset format support, Albumentations augmentation, mAP/mAR metrics, trackio tracking, hardware selection, and Hub persistence.","huggingface-vision-trainer",{"claudeCode":402},"inline plugin source from marketplace.json at skills/huggingface-vision-trainer",[406],{"path":313,"priority":302},{"basePath":408,"description":409,"displayName":410,"installMethods":411,"rationale":412,"selectedPaths":413,"source":303,"sourceLanguage":18,"type":258},"skills/train-sentence-transformers","Train or fine-tune sentence-transformers models across all three architectures: SentenceTransformer (bi-encoder embeddings), CrossEncoder (rerankers), and SparseEncoder (SPLADE). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing.","train-sentence-transformers",{"claudeCode":410},"inline plugin source from marketplace.json at skills/train-sentence-transformers",[414],{"path":313,"priority":302},{"basePath":257,"description":252,"displayName":254,"installMethods":416,"license":237,"rationale":417,"selectedPaths":418,"source":303,"sourceLanguage":18,"type":258},{"claudeCode":254},"plugin manifest at .claude-plugin/plugin.json",[419,421,422,423,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456],{"path":420,"priority":297},".claude-plugin/plugin.json",{"path":299,"priority":297},{"path":301,"priority":302},{"path":424,"priority":425},"skills/hf-cli/SKILL.md","medium",{"path":427,"priority":425},"skills/huggingface-best/SKILL.md",{"path":429,"priority":425},"skills/huggingface-community-evals/SKILL.md",{"path":431,"priority":425},"skills/huggingface-datasets/SKILL.md",{"path":433,"priority":425},"skills/huggingface-gradio/SKILL.md",{"path":435,"priority":425},"skills/huggingface-llm-trainer/SKILL.md",{"path":437,"priority":425},"skills/huggingface-local-models/SKILL.md",{"path":439,"priority":425},"skills/huggingface-paper-publisher/SKILL.md",{"path":441,"priority":425},"skills/huggingface-papers/SKILL.md",{"path":443,"priority":425},"skills/huggingface-tool-builder/SKILL.md",{"path":445,"priority":425},"skills/huggingface-trackio/SKILL.md",{"path":447,"priority":425},"skills/huggingface-vision-trainer/SKILL.md",{"path":449,"priority":425},"skills/train-sentence-transformers/SKILL.md",{"path":451,"priority":425},"skills/transformers-js/SKILL.md",{"path":453,"priority":297},".mcp.json",{"path":455,"priority":302},"agents/AGENTS.md",{"path":457,"priority":302},".cursor-plugin/plugin.json",{"basePath":459,"description":460,"displayName":461,"installMethods":462,"rationale":463,"selectedPaths":464,"source":303,"sourceLanguage":18,"type":246},"hf-mcp/skills/hf-mcp","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.","hf-mcp",{"claudeCode":12},"SKILL.md frontmatter at hf-mcp/skills/hf-mcp/SKILL.md",[465],{"path":313,"priority":297},{"basePath":355,"description":467,"displayName":357,"installMethods":468,"rationale":469,"selectedPaths":470,"source":303,"sourceLanguage":18,"type":246},"Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`.",{"claudeCode":12},"SKILL.md frontmatter at skills/hf-cli/SKILL.md",[471],{"path":313,"priority":297},{"basePath":347,"description":473,"displayName":349,"installMethods":474,"rationale":475,"selectedPaths":476,"source":303,"sourceLanguage":18,"type":246},"Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: \"best model for X\", \"what model should I use for\", \"top models for [task]\", \"which model runs on my laptop/machine/device\", \"recommend a model for\", \"what LLM should I use for\", \"compare models for\", \"what's state of the art for\", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks.\n",{"claudeCode":12},"SKILL.md frontmatter at skills/huggingface-best/SKILL.md",[477],{"path":313,"priority":297},{"basePath":339,"description":479,"displayName":341,"installMethods":480,"rationale":481,"selectedPaths":482,"source":303,"sourceLanguage":18,"type":246},"Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.",{"claudeCode":12},"SKILL.md frontmatter at skills/huggingface-community-evals/SKILL.md",[483,484,487,489,491,493],{"path":313,"priority":297},{"path":485,"priority":486},"examples/.env.example","low",{"path":488,"priority":486},"examples/USAGE_EXAMPLES.md",{"path":490,"priority":486},"scripts/inspect_eval_uv.py",{"path":492,"priority":486},"scripts/inspect_vllm_uv.py",{"path":494,"priority":486},"scripts/lighteval_vllm_uv.py",{"basePath":371,"description":496,"displayName":373,"installMethods":497,"rationale":498,"selectedPaths":499,"source":303,"sourceLanguage":18,"type":246},"Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.\r",{"claudeCode":12},"SKILL.md frontmatter at skills/huggingface-datasets/SKILL.md",[500],{"path":313,"priority":297},{"basePath":243,"description":10,"displayName":13,"installMethods":502,"rationale":503,"selectedPaths":504,"source":303,"sourceLanguage":18,"type":246},{"claudeCode":12},"SKILL.md frontmatter at skills/huggingface-gradio/SKILL.md",[505,506],{"path":313,"priority":297},{"path":507,"priority":425},"examples.md",{"basePath":306,"description":509,"displayName":308,"installMethods":510,"rationale":511,"selectedPaths":512,"source":303,"sourceLanguage":18,"type":246},"Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.",{"claudeCode":12},"SKILL.md frontmatter at skills/huggingface-llm-trainer/SKILL.md",[513,514,516,518,520,522,524,526,528,530,532,534,536,538,540,542,544,546,548],{"path":313,"priority":297},{"path":515,"priority":425},"references/gguf_conversion.md",{"path":517,"priority":425},"references/hardware_guide.md",{"path":519,"priority":425},"references/hub_saving.md",{"path":521,"priority":425},"references/local_training_macos.md",{"path":523,"priority":425},"references/reliability_principles.md",{"path":525,"priority":425},"references/trackio_guide.md",{"path":527,"priority":425},"references/training_methods.md",{"path":529,"priority":425},"references/training_patterns.md",{"path":531,"priority":425},"references/troubleshooting.md",{"path":533,"priority":425},"references/unsloth.md",{"path":535,"priority":486},"scripts/convert_to_gguf.py",{"path":537,"priority":486},"scripts/dataset_inspector.py",{"path":539,"priority":486},"scripts/estimate_cost.py",{"path":541,"priority":486},"scripts/hf_benchmarks.py",{"path":543,"priority":486},"scripts/train_dpo_example.py",{"path":545,"priority":486},"scripts/train_grpo_example.py",{"path":547,"priority":486},"scripts/train_sft_example.py",{"path":549,"priority":486},"scripts/unsloth_sft_example.py",{"basePath":315,"description":316,"displayName":317,"installMethods":551,"rationale":552,"selectedPaths":553,"source":303,"sourceLanguage":18,"type":246},{"claudeCode":12},"SKILL.md frontmatter at skills/huggingface-local-models/SKILL.md",[554,555,557,559],{"path":313,"priority":297},{"path":556,"priority":425},"references/hardware.md",{"path":558,"priority":425},"references/hub-discovery.md",{"path":560,"priority":425},"references/quantization.md",{"basePath":323,"description":324,"displayName":325,"installMethods":562,"rationale":563,"selectedPaths":564,"source":303,"sourceLanguage":18,"type":246},{"claudeCode":12},"SKILL.md frontmatter at skills/huggingface-paper-publisher/SKILL.md",[565,566,568,570,572,574,576,578],{"path":313,"priority":297},{"path":567,"priority":486},"examples/example_usage.md",{"path":569,"priority":425},"references/quick_reference.md",{"path":571,"priority":486},"scripts/paper_manager.py",{"path":573,"priority":486},"templates/arxiv.md",{"path":575,"priority":486},"templates/ml-report.md",{"path":577,"priority":486},"templates/modern.md",{"path":579,"priority":486},"templates/standard.md",{"basePath":331,"description":581,"displayName":333,"installMethods":582,"rationale":583,"selectedPaths":584,"source":303,"sourceLanguage":18,"type":246},"Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.",{"claudeCode":12},"SKILL.md frontmatter at skills/huggingface-papers/SKILL.md",[585],{"path":313,"priority":297},{"basePath":379,"description":587,"displayName":381,"installMethods":588,"rationale":589,"selectedPaths":590,"source":303,"sourceLanguage":18,"type":246},"Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.",{"claudeCode":12},"SKILL.md frontmatter at skills/huggingface-tool-builder/SKILL.md",[591,592,594,596,598,600,602,604],{"path":313,"priority":297},{"path":593,"priority":425},"references/baseline_hf_api.py",{"path":595,"priority":425},"references/baseline_hf_api.sh",{"path":597,"priority":425},"references/baseline_hf_api.tsx",{"path":599,"priority":425},"references/find_models_by_paper.sh",{"path":601,"priority":425},"references/hf_enrich_models.sh",{"path":603,"priority":425},"references/hf_model_card_frontmatter.sh",{"path":605,"priority":425},"references/hf_model_papers_auth.sh",{"basePath":363,"description":607,"displayName":365,"installMethods":608,"rationale":609,"selectedPaths":610,"source":303,"sourceLanguage":18,"type":246},"Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.",{"claudeCode":12},"SKILL.md frontmatter at skills/huggingface-trackio/SKILL.md",[611,612,614,616],{"path":313,"priority":297},{"path":613,"priority":425},"references/alerts.md",{"path":615,"priority":425},"references/logging_metrics.md",{"path":617,"priority":425},"references/retrieving_metrics.md",{"basePath":400,"description":619,"displayName":402,"installMethods":620,"rationale":621,"selectedPaths":622,"source":303,"sourceLanguage":18,"type":246},"Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.",{"claudeCode":12},"SKILL.md frontmatter at skills/huggingface-vision-trainer/SKILL.md",[623,624,626,627,629,631,632,634,635,636,638,640],{"path":313,"priority":297},{"path":625,"priority":425},"references/finetune_sam2_trainer.md",{"path":519,"priority":425},{"path":628,"priority":425},"references/image_classification_training_notebook.md",{"path":630,"priority":425},"references/object_detection_training_notebook.md",{"path":523,"priority":425},{"path":633,"priority":425},"references/timm_trainer.md",{"path":537,"priority":486},{"path":539,"priority":486},{"path":637,"priority":486},"scripts/image_classification_training.py",{"path":639,"priority":486},"scripts/object_detection_training.py",{"path":641,"priority":486},"scripts/sam_segmentation_training.py",{"basePath":408,"description":643,"displayName":410,"installMethods":644,"rationale":645,"selectedPaths":646,"source":303,"sourceLanguage":18,"type":246},"Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval / pair classification), and `SparseEncoder` (SPLADE, sparse embedding model; for learned-sparse retrieval). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.",{"claudeCode":12},"SKILL.md frontmatter at skills/train-sentence-transformers/SKILL.md",[647,648,650,652,654,656,658,659,661,663,665,667,669,671,673,674,676,678,680,682,684,686,688,690,692,694,696,698],{"path":313,"priority":297},{"path":649,"priority":425},"references/base_model_selection.md",{"path":651,"priority":425},"references/dataset_formats.md",{"path":653,"priority":425},"references/evaluators_cross_encoder.md",{"path":655,"priority":425},"references/evaluators_sentence_transformer.md",{"path":657,"priority":425},"references/evaluators_sparse_encoder.md",{"path":517,"priority":425},{"path":660,"priority":425},"references/hf_jobs_execution.md",{"path":662,"priority":425},"references/losses_cross_encoder.md",{"path":664,"priority":425},"references/losses_sentence_transformer.md",{"path":666,"priority":425},"references/losses_sparse_encoder.md",{"path":668,"priority":425},"references/model_architectures.md",{"path":670,"priority":425},"references/prompts_and_instructions.md",{"path":672,"priority":425},"references/training_args.md",{"path":531,"priority":425},{"path":675,"priority":486},"scripts/mine_hard_negatives.py",{"path":677,"priority":486},"scripts/train_cross_encoder_distillation_example.py",{"path":679,"priority":486},"scripts/train_cross_encoder_example.py",{"path":681,"priority":486},"scripts/train_cross_encoder_listwise_example.py",{"path":683,"priority":486},"scripts/train_sentence_transformer_distillation_example.py",{"path":685,"priority":486},"scripts/train_sentence_transformer_example.py",{"path":687,"priority":486},"scripts/train_sentence_transformer_make_multilingual_example.py",{"path":689,"priority":486},"scripts/train_sentence_transformer_matryoshka_example.py",{"path":691,"priority":486},"scripts/train_sentence_transformer_multi_dataset_example.py",{"path":693,"priority":486},"scripts/train_sentence_transformer_static_embedding_example.py",{"path":695,"priority":486},"scripts/train_sentence_transformer_with_lora_example.py",{"path":697,"priority":486},"scripts/train_sparse_encoder_distillation_example.py",{"path":699,"priority":486},"scripts/train_sparse_encoder_example.py",{"basePath":392,"description":701,"displayName":394,"installMethods":702,"rationale":703,"selectedPaths":704,"source":303,"sourceLanguage":18,"type":246},"Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.",{"claudeCode":12},"SKILL.md frontmatter at skills/transformers-js/SKILL.md",[705,706,708,710,712,714,716,718],{"path":313,"priority":297},{"path":707,"priority":425},"references/CACHE.md",{"path":709,"priority":425},"references/CONFIGURATION.md",{"path":711,"priority":425},"references/EXAMPLES.md",{"path":713,"priority":425},"references/MODEL_ARCHITECTURES.md",{"path":715,"priority":425},"references/MODEL_REGISTRY.md",{"path":717,"priority":425},"references/PIPELINE_OPTIONS.md",{"path":719,"priority":425},"references/TEXT_GENERATION.md",{"sources":721},[722],"manual",{"closedIssues90d":231,"description":724,"forks":232,"homepage":725,"license":237,"openIssues90d":233,"pushedAt":234,"readmeSize":229,"stars":235,"topics":726},"Give your agents the power of the Hugging Face ecosystem","https://huggingface.co",[],{"classifiedAt":728,"discoverAt":729,"extractAt":730,"githubAt":730,"updatedAt":728},1778690772996,1778689536128,1778690770714,[214,213,215,211,212],{"evaluatedAt":241,"extractAt":279,"updatedAt":241},[],[735,767,789,811,841,875],{"_creationTime":736,"_id":737,"community":738,"display":739,"identity":745,"providers":750,"relations":761,"tags":763,"workflow":764},1778691799740.4976,"k1719vgzsxtv8exr684y5ww47s86mzqh",{"reviewCount":8},{"description":740,"installMethods":741,"name":743,"sourceUrl":744},"Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.",{"claudeCode":742},"K-Dense-AI/claude-scientific-skills","TimesFM Forecasting","https://github.com/K-Dense-AI/claude-scientific-skills",{"basePath":746,"githubOwner":747,"githubRepo":748,"locale":18,"slug":749,"type":246},"scientific-skills/timesfm-forecasting","K-Dense-AI","claude-scientific-skills","timesfm-forecasting",{"evaluate":751,"extract":759},{"promptVersionExtension":204,"promptVersionScoring":205,"score":752,"tags":753,"targetMarket":216,"tier":217},100,[754,755,756,757,758,215,211],"time-series","forecasting","univariate","foundation-model","timesfm",{"commitSha":270,"license":760},"MIT",{"repoId":762},"kd79rphh5gexy91xmpxc05h5mh86mm9r",[755,757,215,211,754,758,756],{"evaluatedAt":765,"extractAt":766,"updatedAt":765},1778694590335,1778691799740,{"_creationTime":768,"_id":769,"community":770,"display":771,"identity":775,"providers":778,"relations":785,"tags":786,"workflow":787},1778691799740.4958,"k17f4newyw03c3a37jjmvy576s86mgrc",{"reviewCount":8},{"description":772,"installMethods":773,"name":774,"sourceUrl":744},"Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.",{"claudeCode":742},"SHAP Model Interpretability",{"basePath":776,"githubOwner":747,"githubRepo":748,"locale":18,"slug":777,"type":246},"scientific-skills/shap","shap",{"evaluate":779,"extract":784},{"promptVersionExtension":204,"promptVersionScoring":205,"score":752,"tags":780,"targetMarket":216,"tier":217},[215,781,782,777,783,211],"explainable-ai","model-interpretability","data-science",{"commitSha":270,"license":760},{"repoId":762},[783,781,215,782,211,777],{"evaluatedAt":788,"extractAt":766,"updatedAt":788},1778694453287,{"_creationTime":790,"_id":791,"community":792,"display":793,"identity":797,"providers":800,"relations":807,"tags":808,"workflow":809},1778691799740.4905,"k17c27dcgjsqmxeggb19stv4xn86mf1z",{"reviewCount":8},{"description":794,"installMethods":795,"name":796,"sourceUrl":744},"Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.",{"claudeCode":742},"PyTorch Lightning",{"basePath":798,"githubOwner":747,"githubRepo":748,"locale":18,"slug":799,"type":246},"scientific-skills/pytorch-lightning","pytorch-lightning",{"evaluate":801,"extract":806},{"promptVersionExtension":204,"promptVersionScoring":205,"score":752,"tags":802,"targetMarket":216,"tier":217},[803,804,215,211,805],"pytorch","deep-learning","framework",{"commitSha":270,"license":237},{"repoId":762},[804,805,215,211,803],{"evaluatedAt":810,"extractAt":766,"updatedAt":810},1778693958717,{"_creationTime":812,"_id":813,"community":814,"display":815,"identity":821,"providers":825,"relations":834,"tags":837,"workflow":838},1778699018122.8064,"k178yxvt3g9djb8ph907q3tv1186n8ex",{"reviewCount":8},{"description":816,"installMethods":817,"name":819,"sourceUrl":820},"Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.",{"claudeCode":818},"wshobson/agents","embedding-strategies","https://github.com/wshobson/agents",{"basePath":822,"githubOwner":823,"githubRepo":824,"locale":18,"slug":819,"type":246},"plugins/llm-application-dev/skills/embedding-strategies","wshobson","agents",{"evaluate":826,"extract":833},{"promptVersionExtension":204,"promptVersionScoring":205,"score":752,"tags":827,"targetMarket":216,"tier":217},[828,829,830,831,832,211],"embeddings","rag","semantic-search","vector-databases","llm-applications",{"commitSha":270},{"parentExtensionId":835,"repoId":836},"k1719fyk9jrke6aq23wbyf8ej586n3af","kd74de64zj0axtg5b8t7eqqe2x86nske",[828,832,211,829,830,831],{"evaluatedAt":839,"extractAt":840,"updatedAt":839},1778701750946,1778699018122,{"_creationTime":842,"_id":843,"community":844,"display":845,"identity":851,"providers":856,"relations":866,"tags":870,"workflow":871},1778699887554.4724,"k171fhjffw07a0a511s1v1hqsh86m9gz",{"reviewCount":8},{"description":846,"installMethods":847,"name":849,"sourceUrl":850},"AWS Cloud Development Kit (CDK) 专家，用于使用 TypeScript/Python 构建云基础设施。在创建 CDK 堆栈、定义 CDK 构造、实现基础设施即代码，或当用户提及 CDK、CloudFormation、IaC、cdk synth、cdk deploy，或希望以编程方式定义 AWS 基础设施时使用。涵盖 CDK 应用结构、构造模式、堆栈组合和部署工作流。",{"claudeCode":848},"zxkane/aws-skills","aws-cdk-development","https://github.com/zxkane/aws-skills",{"basePath":852,"githubOwner":853,"githubRepo":854,"locale":855,"slug":849,"type":246},"plugins/aws-cdk/skills/aws-cdk-development","zxkane","aws-skills","zh-CN",{"evaluate":857,"extract":865},{"promptVersionExtension":204,"promptVersionScoring":205,"score":752,"tags":858,"targetMarket":216,"tier":217},[859,860,861,211,862,863,864],"aws","cdk","typescript","iac","cloudformation","infrastructure",{"commitSha":270},{"parentExtensionId":867,"repoId":868,"translatedFrom":869},"k177paz2fgaa1r1kfhgb2esr1n86my7m","kd7708aervxaq6vqq9tdf93s2586mcqy","k174bzyyax9v1t5bm0m98bfqyh86m8v8",[859,860,863,862,864,211,861],{"evaluatedAt":872,"extractAt":873,"updatedAt":874},1778699774404,1778699647844,1778699887554,{"_creationTime":876,"_id":877,"community":878,"display":879,"identity":885,"providers":889,"relations":897,"tags":900,"workflow":901},1778695548458.3613,"k17dx6tyy2yb3z5pp1vgmg46ad86nm18",{"reviewCount":8},{"description":880,"installMethods":881,"name":883,"sourceUrl":884},"Fit cognitive drift-diffusion models (Ratcliff DDM) to reaction time and accuracy data with parameter estimation (drift rate, boundary separation, non-decision time), model comparison, and parameter recovery validation. Use when modeling binary decision-making with reaction time data, estimating cognitive parameters from experimental data, comparing sequential sampling model variants, or decomposing speed-accuracy tradeoff effects into latent cognitive components.\n",{"claudeCode":882},"pjt222/agent-almanac","fit-drift-diffusion-model","https://github.com/pjt222/agent-almanac",{"basePath":886,"githubOwner":887,"githubRepo":888,"locale":18,"slug":883,"type":246},"skills/fit-drift-diffusion-model","pjt222","agent-almanac",{"evaluate":890,"extract":896},{"promptVersionExtension":204,"promptVersionScoring":205,"score":752,"tags":891,"targetMarket":216,"tier":217},[892,893,894,211,895],"cognitive-science","modeling","statistics","data-analysis",{"commitSha":270},{"parentExtensionId":898,"repoId":899},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[892,895,893,211,894],{"evaluatedAt":902,"extractAt":903,"updatedAt":902},1778698191612,1778695548458]