[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-plugin-huggingface-huggingface-local-models-de":3,"guides-for-huggingface-huggingface-local-models":744,"similar-k172w5kkdn7117xpqyyhcqsww186n17b-de":745},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":14,"identity":252,"isFallback":249,"parentExtension":256,"providers":291,"relations":295,"repo":296,"tags":742,"workflow":743},1778690773482.483,"k172w5kkdn7117xpqyyhcqsww186n17b",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13},"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.",{"claudeCode":12},"huggingface-local-models","https://github.com/huggingface/skills",{"_creationTime":15,"_id":16,"extensionId":5,"locale":17,"result":18,"trustSignals":233,"workflow":250},1778690852474.3076,"kn7f5q22cbcmv5kpcrsry773bh86nk3m","en",{"checks":19,"evaluatedAt":202,"extensionSummary":203,"features":204,"nonGoals":210,"promptVersionExtension":214,"promptVersionScoring":215,"purpose":216,"rationale":217,"score":218,"summary":219,"tags":220,"targetMarket":227,"tier":228,"useCases":229},[20,25,28,31,35,38,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,116,120,123,126,129,132,135,138,142,144,148,151,155,158,161,164,167,169,172,175,178,181,184,188,191,194,198],{"category":21,"check":22,"severity":23,"summary":24},"Practical Utility","Problem relevance","pass","The description clearly states the problem of selecting and running local LLMs with llama.cpp and GGUF, covering various hardware accelerators and file lookup/conversion tasks.",{"category":21,"check":26,"severity":23,"summary":27},"Unique selling proposition","This skill provides a focused workflow and specific guidance for integrating local LLMs with llama.cpp, going beyond generic LLM usage by addressing GGUF selection, conversion, and serving specifics.",{"category":21,"check":29,"severity":23,"summary":30},"Production readiness","The skill covers the complete lifecycle of selecting, downloading, converting (if necessary), and running local GGUF models, with clear instructions and examples for various scenarios.",{"category":32,"check":33,"severity":23,"summary":34},"Scope","Single responsibility principle","The skill focuses solely on the selection, configuration, and execution of local models using llama.cpp and GGUF, without encroaching on unrelated domains.",{"category":32,"check":36,"severity":23,"summary":37},"Description quality","The displayed description accurately reflects the skill's capabilities as detailed in the README and SKILL.md, covering model selection, hardware acceleration, and serving.",{"category":39,"check":40,"severity":41,"summary":42},"Invocation","Scoped tools","not_applicable","This extension is a plugin, not a skill with tools. Its functionality is described in SKILL.md and leveraged by the host agent.",{"category":44,"check":45,"severity":23,"summary":46},"Documentation","Configuration & parameter reference","The SKILL.md provides detailed guidance on quant selection, conversion, and running servers, including explicit file paths and commands, effectively serving as parameter reference.",{"category":32,"check":48,"severity":41,"summary":49},"Tool naming","This extension does not expose individual tools or commands; its functionality is described within the SKILL.md and invoked by the host agent.",{"category":32,"check":51,"severity":41,"summary":52},"Minimal I/O surface","This extension is a plugin and does not expose tools with specific input/output schemas that can be evaluated for minimal surface area.",{"category":54,"check":55,"severity":23,"summary":56},"License","License usability","The LICENSE file is Apache-2.0, a permissive open-source license, and is correctly detected.",{"category":58,"check":59,"severity":23,"summary":60},"Maintenance","Commit recency","The last commit was on May 12, 2026, which is recent (within 3 months).",{"category":58,"check":62,"severity":23,"summary":63},"Dependency Management","The README and SKILL.md mention external dependencies like llama.cpp and Hugging Face Hub tools, and the instructions imply standard installation methods (brew, winget, git clone), suggesting proper dependency handling.",{"category":65,"check":66,"severity":23,"summary":67},"Security","Secret Management","The skill mentions `hf auth login` for gated repos but does not itself handle or expose secrets; it relies on the user's CLI authentication.",{"category":65,"check":69,"severity":23,"summary":70},"Injection","The skill focuses on providing commands and guidance for local model execution, not on loading or executing untrusted third-party data as instructions.",{"category":65,"check":72,"severity":23,"summary":73},"Transitive Supply-Chain Grenades","The skill relies on user-installed tools like llama.cpp and Hugging Face Hub CLI, with clear instructions provided, rather than fetching and executing arbitrary remote content.",{"category":65,"check":75,"severity":23,"summary":76},"Sandbox Isolation","The skill provides instructions for commands like `llama-cli` and `llama-server` which are assumed to run within their own sandboxed environments or user-managed contexts.",{"category":65,"check":78,"severity":23,"summary":79},"Sandbox escape primitives","No detached process spawns or deny-retry loops were observed in the provided SKILL.md instructions.",{"category":65,"check":81,"severity":23,"summary":82},"Data Exfiltration","The skill focuses on local model execution and does not instruct the agent to read or submit confidential data to third parties.",{"category":65,"check":84,"severity":23,"summary":85},"Hidden Text Tricks","The bundled content and README are free of hidden steering tricks, invisible Unicode characters, or other obfuscation methods.",{"category":87,"check":88,"severity":23,"summary":89},"Hooks","Opaque code execution","The skill documentation provides clear, readable bash commands and Python script calls, with no evidence of obfuscated code, base64 payloads, or runtime fetches for execution.",{"category":91,"check":92,"severity":23,"summary":93},"Portability","Structural Assumption","The skill provides clear instructions for commands and file paths, relying on standard user environments and tool installations, rather than making assumptions about specific project layouts.",{"category":95,"check":96,"severity":23,"summary":97},"Trust","Issues Attention","The repository has 4 open issues and 6 closed issues in the last 90 days, indicating active maintenance and a reasonable closure rate.",{"category":99,"check":100,"severity":23,"summary":101},"Versioning","Release Management","The repository has a recent push date and a clear project structure, suggesting versioning is managed through the commit history and standard GitHub release practices.",{"category":103,"check":104,"severity":41,"summary":105},"Code Execution","Validation","This plugin primarily provides instructions and guidance, not executable tools with input schemas that require validation via a library.",{"category":65,"check":107,"severity":23,"summary":108},"Unguarded Destructive Operations","The skill focuses on model selection and serving, which are not destructive operations. Any file operations (like conversion) are user-initiated and documented.",{"category":110,"check":111,"severity":23,"summary":112},"Errors","Actionable error messages","The SKILL.md provides clear instructions and expected outputs for commands, implying that standard tool error messages will be provided, with guidance on how to resolve issues like incorrect quant selection or missing dependencies.",{"category":103,"check":114,"severity":41,"summary":115},"Logging","The skill itself does not perform destructive actions or outbound calls that would require local audit logging; it relies on the host agent for execution context.",{"category":117,"check":118,"severity":41,"summary":119},"Compliance","GDPR","The skill operates on local model files and does not handle personal data, thus no GDPR considerations apply.",{"category":117,"check":121,"severity":23,"summary":122},"Target market","The skill is globally applicable for users running local LLMs and does not have any regional restrictions.",{"category":91,"check":124,"severity":23,"summary":125},"Runtime stability","The instructions for `llama.cpp` and `hf auth login` are cross-platform and rely on standard tools, suggesting good runtime stability.",{"category":44,"check":127,"severity":23,"summary":128},"README","The README provides a clear overview of the Hugging Face Skills repository and directs users to specific skills like this one.",{"category":32,"check":130,"severity":41,"summary":131},"Tool surface size","This is a plugin with a SKILL.md, not a collection of discrete tools. The scope is defined by the SKILL.md's guidance.",{"category":39,"check":133,"severity":41,"summary":134},"Overlapping near-synonym tools","This plugin does not expose distinct tools that could have overlapping synonyms.",{"category":44,"check":136,"severity":23,"summary":137},"Phantom features","All features described in the README and SKILL.md, such as finding GGUFs, quant selection, and running servers, have corresponding implementation guidance and external tool references.",{"category":139,"check":140,"severity":23,"summary":141},"Install","Installation instruction","The README provides clear installation instructions for Claude Code, Codex, Gemini CLI, and Cursor, including copy-pasteable commands and links to further documentation.",{"category":110,"check":111,"severity":23,"summary":143},"The SKILL.md provides clear instructions and guidance, and the referenced external tools (llama.cpp, hf-cli) are expected to provide actionable error messages.",{"category":145,"check":146,"severity":23,"summary":147},"Execution","Pinned dependencies","The skill instructs users to install external tools like `llama.cpp` via standard package managers (brew, winget) or cloning from a specific GitHub repository, implying pinned versions are used.",{"category":32,"check":149,"severity":41,"summary":150},"Dry-run preview","This plugin provides guidance on using existing tools; it does not perform state-changing operations directly that would require a dry-run feature.",{"category":152,"check":153,"severity":41,"summary":154},"Protocol","Idempotent retry & timeouts","This plugin does not manage remote calls or state-changing operations that would require idempotency or timeouts. It relies on the host agent and external tools.",{"category":117,"check":156,"severity":23,"summary":157},"Telemetry opt-in","The skill does not emit telemetry; it relies on the user's local tools and Hugging Face Hub interactions.",{"category":39,"check":159,"severity":41,"summary":160},"Name collisions","This is a single plugin extension, so there are no bundled extensions to check for name collisions.",{"category":39,"check":162,"severity":41,"summary":163},"Hooks-off mechanism","This extension does not appear to use hooks that would require a specific hooks-off mechanism.",{"category":39,"check":165,"severity":41,"summary":166},"Hook matcher tightness","No hooks are defined for this plugin.",{"category":65,"check":168,"severity":41,"summary":166},"Hook security",{"category":87,"check":170,"severity":41,"summary":171},"Silent prompt rewriting","This plugin does not implement a UserPromptSubmit hook.",{"category":65,"check":173,"severity":41,"summary":174},"Permission Hook","This plugin does not implement a PermissionRequest hook.",{"category":117,"check":176,"severity":41,"summary":177},"Hook privacy","No hooks are defined for this plugin, thus no data is sent via network from hooks.",{"category":103,"check":179,"severity":41,"summary":180},"Hook dependency","This plugin does not contain any hooks.",{"category":44,"check":182,"severity":23,"summary":183},"Feature Transparency","The README and SKILL.md clearly describe the functionality related to local model execution with llama.cpp and GGUF.",{"category":185,"check":186,"severity":23,"summary":187},"Convention","Layout convention adherence","The repository structure adheres to typical plugin conventions, with a clear SKILL.md and documentation for installation and usage.",{"category":185,"check":189,"severity":41,"summary":190},"Plugin state","This plugin does not appear to manage persistent state under CLAUDE_PLUGIN_DATA; it relies on external tool installations.",{"category":65,"check":192,"severity":41,"summary":193},"Keychain-stored secrets","The plugin does not consume secrets directly; it relies on the user's authentication configured for the Hugging Face Hub CLI.",{"category":195,"check":196,"severity":23,"summary":197},"Dependencies","Tagged release sourcing","The skill directs users to install `llama.cpp` from its official GitHub repository and use Hugging Face Hub's `hf-cli`, which typically rely on tagged releases or specific branches.",{"category":199,"check":200,"severity":23,"summary":201},"Installation","Clean uninstall","The plugin itself does not install background daemons or services; it relies on the host agent and user-installed external tools, which are managed separately.",1778690852346,"This plugin provides guidance and instructions for selecting, configuring, and running local language models using llama.cpp and GGUF format on various hardware accelerators. It covers finding models, choosing quantizations, and setting up local serving.",[205,206,207,208,209],"Select local LLMs with llama.cpp and GGUF","Support for CPU, Mac Metal, CUDA, and ROCm","Find and select appropriate GGUF models and quantizations","Run local LLM servers and CLI interfaces","Convert models when GGUF is not directly available",[211,212,213],"Providing a managed cloud LLM service.","Acting as a general-purpose LLM API wrapper.","Abstracting away the underlying llama.cpp or Hugging Face Hub tooling entirely.","3.0.0","4.4.0","To enable users to easily run large language models locally on their own hardware, leveraging optimized tools like llama.cpp and Hugging Face's model repository.","The plugin demonstrates excellent adherence to documentation, security, and functional requirements, with no significant findings. Its only non-applicable checks are due to its nature as a guidance-focused plugin rather than a tool-executing skill.",99,"High-quality plugin for local LLM execution with excellent documentation and security.",[221,222,223,224,225,226],"llm","local-models","llama-cpp","gguf","huggingface","ml-ops","global","verified",[230,231,232],"Running LLMs locally for privacy or cost savings.","Experimenting with different local LLM configurations and hardware.","Developing applications that require a local inference backend.",{"codeQuality":234,"collectedAt":236,"documentation":237,"maintenance":240,"security":246,"testCoverage":248},{"hasLockfile":235},false,1778690836965,{"descriptionLength":238,"readmeSize":239},222,9821,{"closedIssues90d":241,"forks":242,"hasChangelog":235,"openIssues90d":243,"pushedAt":244,"stars":245},6,663,4,1778593131000,10482,{"hasNpmPackage":235,"license":247,"smitheryVerified":235},"Apache-2.0",{"hasCi":249,"hasTests":235},true,{"updatedAt":251},1778690852474,{"basePath":253,"githubOwner":225,"githubRepo":254,"locale":17,"slug":12,"type":255},"skills/huggingface-local-models","skills","plugin",{"_creationTime":257,"_id":258,"community":259,"display":260,"identity":265,"parentExtension":268,"providers":269,"relations":285,"tags":287,"workflow":288},1778690773482.4824,"k17es3r8wd37t5rrwqcpp5kwrh86mxx8",{"reviewCount":8},{"description":261,"installMethods":262,"name":264,"sourceUrl":13},"Agent Skills for AI/ML tasks including dataset creation, model training, evaluation, and research paper publishing on Hugging Face Hub",{"claudeCode":263},"huggingface/skills","huggingface-skills",{"basePath":266,"githubOwner":225,"githubRepo":254,"locale":17,"slug":254,"type":267},"","marketplace",null,{"evaluate":270,"extract":279},{"promptVersionExtension":271,"promptVersionScoring":215,"score":272,"tags":273,"targetMarket":227,"tier":228},"3.1.0",95,[274,225,275,276,277,278],"ai-ml","datasets","models","research","developer-tools",{"commitSha":280,"marketplace":281,"plugin":283},"HEAD",{"name":264,"pluginCount":282},14,{"mcpCount":8,"provider":284,"skillCount":8},"classify",{"repoId":286},"kd72xwt5xnc0ktc4p7smzfcp3986m959",[274,275,278,225,276,277],{"evaluatedAt":289,"extractAt":290,"updatedAt":289},1778690814090,1778690773482,{"evaluate":292,"extract":294},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":293,"targetMarket":227,"tier":228},[221,222,223,224,225,226],{"commitSha":280},{"parentExtensionId":258,"repoId":286},{"_creationTime":297,"_id":286,"identity":298,"providers":299,"workflow":738},1778689536128.5474,{"githubOwner":225,"githubRepo":254,"sourceUrl":13},{"classify":300,"discover":731,"github":734},{"commitSha":280,"extensions":301},[302,315,324,329,337,345,353,361,369,377,385,393,401,409,417,425,468,477,483,489,506,512,519,561,572,591,597,617,629,653,711],{"basePath":266,"description":261,"displayName":264,"installMethods":303,"rationale":304,"selectedPaths":305,"source":314,"sourceLanguage":17,"type":267},{"claudeCode":263},"marketplace.json at .claude-plugin/marketplace.json",[306,309,311],{"path":307,"priority":308},".claude-plugin/marketplace.json","mandatory",{"path":310,"priority":308},"README.md",{"path":312,"priority":313},"LICENSE","high","rule",{"basePath":316,"description":317,"displayName":318,"installMethods":319,"rationale":320,"selectedPaths":321,"source":314,"sourceLanguage":17,"type":255},"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":318},"inline plugin source from marketplace.json at skills/huggingface-llm-trainer",[322],{"path":323,"priority":313},"SKILL.md",{"basePath":253,"description":10,"displayName":12,"installMethods":325,"rationale":326,"selectedPaths":327,"source":314,"sourceLanguage":17,"type":255},{"claudeCode":12},"inline plugin source from marketplace.json at skills/huggingface-local-models",[328],{"path":323,"priority":313},{"basePath":330,"description":331,"displayName":332,"installMethods":333,"rationale":334,"selectedPaths":335,"source":314,"sourceLanguage":17,"type":255},"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":332},"inline plugin source from marketplace.json at skills/huggingface-paper-publisher",[336],{"path":323,"priority":313},{"basePath":338,"description":339,"displayName":340,"installMethods":341,"rationale":342,"selectedPaths":343,"source":314,"sourceLanguage":17,"type":255},"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":340},"inline plugin source from marketplace.json at skills/huggingface-papers",[344],{"path":323,"priority":313},{"basePath":346,"description":347,"displayName":348,"installMethods":349,"rationale":350,"selectedPaths":351,"source":314,"sourceLanguage":17,"type":255},"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":348},"inline plugin source from marketplace.json at skills/huggingface-community-evals",[352],{"path":323,"priority":313},{"basePath":354,"description":355,"displayName":356,"installMethods":357,"rationale":358,"selectedPaths":359,"source":314,"sourceLanguage":17,"type":255},"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":356},"inline plugin source from marketplace.json at skills/huggingface-best",[360],{"path":323,"priority":313},{"basePath":362,"description":363,"displayName":364,"installMethods":365,"rationale":366,"selectedPaths":367,"source":314,"sourceLanguage":17,"type":255},"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":364},"inline plugin source from marketplace.json at skills/hf-cli",[368],{"path":323,"priority":313},{"basePath":370,"description":371,"displayName":372,"installMethods":373,"rationale":374,"selectedPaths":375,"source":314,"sourceLanguage":17,"type":255},"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":372},"inline plugin source from marketplace.json at skills/huggingface-trackio",[376],{"path":323,"priority":313},{"basePath":378,"description":379,"displayName":380,"installMethods":381,"rationale":382,"selectedPaths":383,"source":314,"sourceLanguage":17,"type":255},"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":380},"inline plugin source from marketplace.json at skills/huggingface-datasets",[384],{"path":323,"priority":313},{"basePath":386,"description":387,"displayName":388,"installMethods":389,"rationale":390,"selectedPaths":391,"source":314,"sourceLanguage":17,"type":255},"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":388},"inline plugin source from marketplace.json at skills/huggingface-tool-builder",[392],{"path":323,"priority":313},{"basePath":394,"description":395,"displayName":396,"installMethods":397,"rationale":398,"selectedPaths":399,"source":314,"sourceLanguage":17,"type":255},"skills/huggingface-gradio","Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.","huggingface-gradio",{"claudeCode":396},"inline plugin source from marketplace.json at skills/huggingface-gradio",[400],{"path":323,"priority":313},{"basePath":402,"description":403,"displayName":404,"installMethods":405,"rationale":406,"selectedPaths":407,"source":314,"sourceLanguage":17,"type":255},"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":404},"inline plugin source from marketplace.json at skills/transformers-js",[408],{"path":323,"priority":313},{"basePath":410,"description":411,"displayName":412,"installMethods":413,"rationale":414,"selectedPaths":415,"source":314,"sourceLanguage":17,"type":255},"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":412},"inline plugin source from marketplace.json at skills/huggingface-vision-trainer",[416],{"path":323,"priority":313},{"basePath":418,"description":419,"displayName":420,"installMethods":421,"rationale":422,"selectedPaths":423,"source":314,"sourceLanguage":17,"type":255},"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":420},"inline plugin source from marketplace.json at skills/train-sentence-transformers",[424],{"path":323,"priority":313},{"basePath":266,"description":261,"displayName":264,"installMethods":426,"license":247,"rationale":427,"selectedPaths":428,"source":314,"sourceLanguage":17,"type":255},{"claudeCode":264},"plugin manifest at .claude-plugin/plugin.json",[429,431,432,433,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466],{"path":430,"priority":308},".claude-plugin/plugin.json",{"path":310,"priority":308},{"path":312,"priority":313},{"path":434,"priority":435},"skills/hf-cli/SKILL.md","medium",{"path":437,"priority":435},"skills/huggingface-best/SKILL.md",{"path":439,"priority":435},"skills/huggingface-community-evals/SKILL.md",{"path":441,"priority":435},"skills/huggingface-datasets/SKILL.md",{"path":443,"priority":435},"skills/huggingface-gradio/SKILL.md",{"path":445,"priority":435},"skills/huggingface-llm-trainer/SKILL.md",{"path":447,"priority":435},"skills/huggingface-local-models/SKILL.md",{"path":449,"priority":435},"skills/huggingface-paper-publisher/SKILL.md",{"path":451,"priority":435},"skills/huggingface-papers/SKILL.md",{"path":453,"priority":435},"skills/huggingface-tool-builder/SKILL.md",{"path":455,"priority":435},"skills/huggingface-trackio/SKILL.md",{"path":457,"priority":435},"skills/huggingface-vision-trainer/SKILL.md",{"path":459,"priority":435},"skills/train-sentence-transformers/SKILL.md",{"path":461,"priority":435},"skills/transformers-js/SKILL.md",{"path":463,"priority":308},".mcp.json",{"path":465,"priority":313},"agents/AGENTS.md",{"path":467,"priority":313},".cursor-plugin/plugin.json",{"basePath":469,"description":470,"displayName":471,"installMethods":472,"rationale":473,"selectedPaths":474,"source":314,"sourceLanguage":17,"type":476},"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":263},"SKILL.md frontmatter at hf-mcp/skills/hf-mcp/SKILL.md",[475],{"path":323,"priority":308},"skill",{"basePath":362,"description":478,"displayName":364,"installMethods":479,"rationale":480,"selectedPaths":481,"source":314,"sourceLanguage":17,"type":476},"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":263},"SKILL.md frontmatter at skills/hf-cli/SKILL.md",[482],{"path":323,"priority":308},{"basePath":354,"description":484,"displayName":356,"installMethods":485,"rationale":486,"selectedPaths":487,"source":314,"sourceLanguage":17,"type":476},"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":263},"SKILL.md frontmatter at skills/huggingface-best/SKILL.md",[488],{"path":323,"priority":308},{"basePath":346,"description":490,"displayName":348,"installMethods":491,"rationale":492,"selectedPaths":493,"source":314,"sourceLanguage":17,"type":476},"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":263},"SKILL.md frontmatter at skills/huggingface-community-evals/SKILL.md",[494,495,498,500,502,504],{"path":323,"priority":308},{"path":496,"priority":497},"examples/.env.example","low",{"path":499,"priority":497},"examples/USAGE_EXAMPLES.md",{"path":501,"priority":497},"scripts/inspect_eval_uv.py",{"path":503,"priority":497},"scripts/inspect_vllm_uv.py",{"path":505,"priority":497},"scripts/lighteval_vllm_uv.py",{"basePath":378,"description":507,"displayName":380,"installMethods":508,"rationale":509,"selectedPaths":510,"source":314,"sourceLanguage":17,"type":476},"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":263},"SKILL.md frontmatter at skills/huggingface-datasets/SKILL.md",[511],{"path":323,"priority":308},{"basePath":394,"description":395,"displayName":396,"installMethods":513,"rationale":514,"selectedPaths":515,"source":314,"sourceLanguage":17,"type":476},{"claudeCode":263},"SKILL.md frontmatter at skills/huggingface-gradio/SKILL.md",[516,517],{"path":323,"priority":308},{"path":518,"priority":435},"examples.md",{"basePath":316,"description":520,"displayName":318,"installMethods":521,"rationale":522,"selectedPaths":523,"source":314,"sourceLanguage":17,"type":476},"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":263},"SKILL.md frontmatter at skills/huggingface-llm-trainer/SKILL.md",[524,525,527,529,531,533,535,537,539,541,543,545,547,549,551,553,555,557,559],{"path":323,"priority":308},{"path":526,"priority":435},"references/gguf_conversion.md",{"path":528,"priority":435},"references/hardware_guide.md",{"path":530,"priority":435},"references/hub_saving.md",{"path":532,"priority":435},"references/local_training_macos.md",{"path":534,"priority":435},"references/reliability_principles.md",{"path":536,"priority":435},"references/trackio_guide.md",{"path":538,"priority":435},"references/training_methods.md",{"path":540,"priority":435},"references/training_patterns.md",{"path":542,"priority":435},"references/troubleshooting.md",{"path":544,"priority":435},"references/unsloth.md",{"path":546,"priority":497},"scripts/convert_to_gguf.py",{"path":548,"priority":497},"scripts/dataset_inspector.py",{"path":550,"priority":497},"scripts/estimate_cost.py",{"path":552,"priority":497},"scripts/hf_benchmarks.py",{"path":554,"priority":497},"scripts/train_dpo_example.py",{"path":556,"priority":497},"scripts/train_grpo_example.py",{"path":558,"priority":497},"scripts/train_sft_example.py",{"path":560,"priority":497},"scripts/unsloth_sft_example.py",{"basePath":253,"description":10,"displayName":12,"installMethods":562,"rationale":563,"selectedPaths":564,"source":314,"sourceLanguage":17,"type":476},{"claudeCode":263},"SKILL.md frontmatter at skills/huggingface-local-models/SKILL.md",[565,566,568,570],{"path":323,"priority":308},{"path":567,"priority":435},"references/hardware.md",{"path":569,"priority":435},"references/hub-discovery.md",{"path":571,"priority":435},"references/quantization.md",{"basePath":330,"description":331,"displayName":332,"installMethods":573,"rationale":574,"selectedPaths":575,"source":314,"sourceLanguage":17,"type":476},{"claudeCode":263},"SKILL.md frontmatter at skills/huggingface-paper-publisher/SKILL.md",[576,577,579,581,583,585,587,589],{"path":323,"priority":308},{"path":578,"priority":497},"examples/example_usage.md",{"path":580,"priority":435},"references/quick_reference.md",{"path":582,"priority":497},"scripts/paper_manager.py",{"path":584,"priority":497},"templates/arxiv.md",{"path":586,"priority":497},"templates/ml-report.md",{"path":588,"priority":497},"templates/modern.md",{"path":590,"priority":497},"templates/standard.md",{"basePath":338,"description":592,"displayName":340,"installMethods":593,"rationale":594,"selectedPaths":595,"source":314,"sourceLanguage":17,"type":476},"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":263},"SKILL.md frontmatter at skills/huggingface-papers/SKILL.md",[596],{"path":323,"priority":308},{"basePath":386,"description":598,"displayName":388,"installMethods":599,"rationale":600,"selectedPaths":601,"source":314,"sourceLanguage":17,"type":476},"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":263},"SKILL.md frontmatter at skills/huggingface-tool-builder/SKILL.md",[602,603,605,607,609,611,613,615],{"path":323,"priority":308},{"path":604,"priority":435},"references/baseline_hf_api.py",{"path":606,"priority":435},"references/baseline_hf_api.sh",{"path":608,"priority":435},"references/baseline_hf_api.tsx",{"path":610,"priority":435},"references/find_models_by_paper.sh",{"path":612,"priority":435},"references/hf_enrich_models.sh",{"path":614,"priority":435},"references/hf_model_card_frontmatter.sh",{"path":616,"priority":435},"references/hf_model_papers_auth.sh",{"basePath":370,"description":618,"displayName":372,"installMethods":619,"rationale":620,"selectedPaths":621,"source":314,"sourceLanguage":17,"type":476},"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":263},"SKILL.md frontmatter at skills/huggingface-trackio/SKILL.md",[622,623,625,627],{"path":323,"priority":308},{"path":624,"priority":435},"references/alerts.md",{"path":626,"priority":435},"references/logging_metrics.md",{"path":628,"priority":435},"references/retrieving_metrics.md",{"basePath":410,"description":630,"displayName":412,"installMethods":631,"rationale":632,"selectedPaths":633,"source":314,"sourceLanguage":17,"type":476},"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":263},"SKILL.md frontmatter at skills/huggingface-vision-trainer/SKILL.md",[634,635,637,638,640,642,643,645,646,647,649,651],{"path":323,"priority":308},{"path":636,"priority":435},"references/finetune_sam2_trainer.md",{"path":530,"priority":435},{"path":639,"priority":435},"references/image_classification_training_notebook.md",{"path":641,"priority":435},"references/object_detection_training_notebook.md",{"path":534,"priority":435},{"path":644,"priority":435},"references/timm_trainer.md",{"path":548,"priority":497},{"path":550,"priority":497},{"path":648,"priority":497},"scripts/image_classification_training.py",{"path":650,"priority":497},"scripts/object_detection_training.py",{"path":652,"priority":497},"scripts/sam_segmentation_training.py",{"basePath":418,"description":654,"displayName":420,"installMethods":655,"rationale":656,"selectedPaths":657,"source":314,"sourceLanguage":17,"type":476},"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":263},"SKILL.md frontmatter at skills/train-sentence-transformers/SKILL.md",[658,659,661,663,665,667,669,670,672,674,676,678,680,682,684,685,687,689,691,693,695,697,699,701,703,705,707,709],{"path":323,"priority":308},{"path":660,"priority":435},"references/base_model_selection.md",{"path":662,"priority":435},"references/dataset_formats.md",{"path":664,"priority":435},"references/evaluators_cross_encoder.md",{"path":666,"priority":435},"references/evaluators_sentence_transformer.md",{"path":668,"priority":435},"references/evaluators_sparse_encoder.md",{"path":528,"priority":435},{"path":671,"priority":435},"references/hf_jobs_execution.md",{"path":673,"priority":435},"references/losses_cross_encoder.md",{"path":675,"priority":435},"references/losses_sentence_transformer.md",{"path":677,"priority":435},"references/losses_sparse_encoder.md",{"path":679,"priority":435},"references/model_architectures.md",{"path":681,"priority":435},"references/prompts_and_instructions.md",{"path":683,"priority":435},"references/training_args.md",{"path":542,"priority":435},{"path":686,"priority":497},"scripts/mine_hard_negatives.py",{"path":688,"priority":497},"scripts/train_cross_encoder_distillation_example.py",{"path":690,"priority":497},"scripts/train_cross_encoder_example.py",{"path":692,"priority":497},"scripts/train_cross_encoder_listwise_example.py",{"path":694,"priority":497},"scripts/train_sentence_transformer_distillation_example.py",{"path":696,"priority":497},"scripts/train_sentence_transformer_example.py",{"path":698,"priority":497},"scripts/train_sentence_transformer_make_multilingual_example.py",{"path":700,"priority":497},"scripts/train_sentence_transformer_matryoshka_example.py",{"path":702,"priority":497},"scripts/train_sentence_transformer_multi_dataset_example.py",{"path":704,"priority":497},"scripts/train_sentence_transformer_static_embedding_example.py",{"path":706,"priority":497},"scripts/train_sentence_transformer_with_lora_example.py",{"path":708,"priority":497},"scripts/train_sparse_encoder_distillation_example.py",{"path":710,"priority":497},"scripts/train_sparse_encoder_example.py",{"basePath":402,"description":712,"displayName":404,"installMethods":713,"rationale":714,"selectedPaths":715,"source":314,"sourceLanguage":17,"type":476},"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":263},"SKILL.md frontmatter at skills/transformers-js/SKILL.md",[716,717,719,721,723,725,727,729],{"path":323,"priority":308},{"path":718,"priority":435},"references/CACHE.md",{"path":720,"priority":435},"references/CONFIGURATION.md",{"path":722,"priority":435},"references/EXAMPLES.md",{"path":724,"priority":435},"references/MODEL_ARCHITECTURES.md",{"path":726,"priority":435},"references/MODEL_REGISTRY.md",{"path":728,"priority":435},"references/PIPELINE_OPTIONS.md",{"path":730,"priority":435},"references/TEXT_GENERATION.md",{"sources":732},[733],"manual",{"closedIssues90d":241,"description":735,"forks":242,"homepage":736,"license":247,"openIssues90d":243,"pushedAt":244,"readmeSize":239,"stars":245,"topics":737},"Give your agents the power of the Hugging Face ecosystem","https://huggingface.co",[],{"classifiedAt":739,"discoverAt":740,"extractAt":741,"githubAt":741,"updatedAt":739},1778690772996,1778689536128,1778690770714,[224,225,223,221,222,226],{"evaluatedAt":251,"extractAt":290,"updatedAt":251},[],[746,765,786,805],{"_creationTime":747,"_id":748,"community":749,"display":750,"identity":752,"providers":753,"relations":761,"tags":762,"workflow":763},1778690773482.4827,"k175sdyyg60kjnnbkm4029s70186ngbn",{"reviewCount":8},{"description":317,"installMethods":751,"name":318,"sourceUrl":13},{"claudeCode":318},{"basePath":316,"githubOwner":225,"githubRepo":254,"locale":17,"slug":318,"type":255},{"evaluate":754,"extract":760},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":755,"targetMarket":227,"tier":228},[221,756,757,225,758,224,759],"training","fine-tuning","trl","mlops",{"commitSha":280},{"parentExtensionId":258,"repoId":286},[757,224,225,221,759,756,758],{"evaluatedAt":764,"extractAt":290,"updatedAt":764},1778690836703,{"_creationTime":766,"_id":767,"community":768,"display":769,"identity":772,"providers":773,"relations":782,"tags":783,"workflow":784},1778690773482.4834,"k179sm2kkyd7r7nz9jsx62jm9x86mw4a",{"reviewCount":8},{"description":339,"installMethods":770,"name":771,"sourceUrl":13},{"claudeCode":340},"Hugging Face Papers",{"basePath":338,"githubOwner":225,"githubRepo":254,"locale":17,"slug":340,"type":255},{"evaluate":774,"extract":781},{"promptVersionExtension":214,"promptVersionScoring":215,"score":775,"tags":776,"targetMarket":227,"tier":228},100,[225,777,778,779,277,780],"papers","arxiv","ai","metadata",{"commitSha":280,"license":247},{"parentExtensionId":258,"repoId":286},[779,778,225,780,777,277],{"evaluatedAt":785,"extractAt":290,"updatedAt":785},1778690901306,{"_creationTime":787,"_id":788,"community":789,"display":790,"identity":792,"providers":793,"relations":801,"tags":802,"workflow":803},1778690773482.4844,"k1785s3263hzxs6ne1nsbzas5186m86v",{"reviewCount":8},{"description":371,"installMethods":791,"name":372,"sourceUrl":13},{"claudeCode":372},{"basePath":370,"githubOwner":225,"githubRepo":254,"locale":17,"slug":372,"type":255},{"evaluate":794,"extract":800},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":795,"targetMarket":227,"tier":228},[759,796,797,225,798,799],"experiment-tracking","monitoring","python","cli",{"commitSha":280},{"parentExtensionId":258,"repoId":286},[799,796,225,759,797,798],{"evaluatedAt":804,"extractAt":290,"updatedAt":804},1778690988981,{"_creationTime":806,"_id":807,"community":808,"display":809,"identity":811,"providers":812,"relations":816,"tags":817,"workflow":818},1778690773482.4841,"k172m7ench1yy64c6nbcx5pmm586mphh",{"reviewCount":8},{"description":363,"installMethods":810,"name":364,"sourceUrl":13},{"claudeCode":364},{"basePath":362,"githubOwner":225,"githubRepo":254,"locale":17,"slug":364,"type":255},{"evaluate":813,"extract":815},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":814,"targetMarket":227,"tier":228},[225,799,278,759,275,276],{"commitSha":280},{"parentExtensionId":258,"repoId":286},[799,275,278,225,759,276],{"evaluatedAt":819,"extractAt":290,"updatedAt":819},1778690967596]