Execute Hugging Face Hub operations using the hf CLI. Download models/datasets, upload files, manage repos, and run cloud compute jobs.
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.
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.
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.
Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.
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.
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.
Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting model-card recommendations (trigger words, steps, guidance, LoRA scale, example inputs), and shipping to ZeroGPU hardware as a private Space by default.
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.
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.
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package.
Build reusable scripts for Hugging Face Hub and API workflows. Useful for chaining API calls, enriching Hub metadata, or automating repeated tasks.
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.
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.
Coding rules for Gradio Spaces using Hugging Face Spaces ZeroGPU hardware. Covers `@spaces.GPU`, duration and quota tuning, pickle-based process isolation, `gr.State` semantics across the worker boundary, the CUDA availability model, concurrency safety, and CUDA wheel-only build constraints.
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.
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.
Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.
Generate or edit images from text and optional photos
Consult a council of LLMs for a refined answer
Extract text, formulas, or tables from images
Edit images with text prompts and style adapters
Generate live web pages from text prompts
Generate full HTML web apps from text prompts
Generate and run Python or web code from a text prompt
Chat with an AI assistant using the LFM2.5 model
Chat with a multimodal AI that can answer text and image queries
Extract text, tables, formulas, and charts from images
Generate web app HTML/React code from a text description
Generate speech from text using voice design, cloning or presets
Chat with AI using text and images
Generate expressive speech from text with optional voice reference
Explore LLM benchmark leaderboards across multiple categories
Explore NLP tasks like sentiment, NER, QA, and summarization
Transform AI text into human-like writing and detect AI-generated content
Generate AI-powered responses to your text prompts
Chat with an AI assistant in real time
Chat with AI using text and images
Summarize health information in simple language
Generate or edit images from text and optional photos
Extract Korean vocabulary with translations from PDFs websites audio
Chat with an AI‑powered assistant
Analyze uploaded session logs and get AI-driven insights
Save and query personal notes with AI
Generate interactive graphs from blood test data
Watch an AI agent escape a maze in real time
Consult a council of LLMs for a refined answer
Generate music tracks from text prompts
Generate natural-sounding speech from text
Explore and compare speech recognition model benchmarks
Generate a full HTML webpage from a text prompt
Chat with a multimodal AI using text and media
Chat with an AI using text, images, audio, or video
Generate images from text prompts with customizable settings
Chat with an AI using text, images, audio, or video
Generate speech audio from text with optional voice cloning
Generate high‑quality images from text in seconds
Generate speech in any voice from text
Analyze music and answer questions from audio or YouTube links
Transcribe audio to text with timestamps and downloadable files
Transcribe audio files into text instantly
Generate speech from text with optional voice cloning
Answer complex questions with web‑sourced research
Generate detailed captions for your images
Generate detailed prompts from any image
Extract text, formulas, or tables from images
Edit images with text prompts and style adapters
Transcribe audio to text with multilingual streaming support
Just a hello world agent — a minimal A2A reference implementation demonstrating the Agent-to-Agent protocol with streaming support.
>
>-
Prompt for creating the high-level technical architecture for an Epic, based on a Product Requirements Document.
Prompt for creating an Epic Product Requirements Document (PRD) for a new epic. This PRD will be used as input for generating a technical architecture specification.
Prompt for creating detailed feature implementation plans, following Epoch monorepo structure.
Prompt for creating Product Requirements Documents (PRDs) for new features, based on an Epic.
Helps with creating burger orders
All Azure MCP tools to create a seamless connection between AI agents and Azure services.
The ESRP OSS MCP server exposes tools to discover & validate trusted Microsoft OSS Packages.
A Model Context Protocol (MCP) server for NuGet.
The Power BI Modeling MCP Server brings Power BI semantic modeling capabilities to your AI agents.
A basic MCP server to operate on the Postman API.
Create GitHub Issues from implementation plan phases using feature_request.yml or chore_request.yml templates.
Create a new implementation plan file for new features, refactoring existing code or upgrading packages, design, architecture or infrastructure.
Create time-boxed technical spike documents for researching and resolving critical development decisions before implementation.
Discovers all projects in a .NET solution, classifies each for Oracle-to-PostgreSQL migration eligibility, and produces a persistent master migration plan. Use when starting a multi-project Oracle-to-PostgreSQL migration, creating a migration inventory, or assessing which .NET projects contain Oracle dependencies.
Creates structured bug reports for defects found during Oracle-to-PostgreSQL migration. Use when documenting behavioral differences between Oracle and PostgreSQL as actionable bug reports with severity, root cause, and remediation steps.
Creates integration test cases for .NET data access artifacts during Oracle-to-PostgreSQL database migrations. Generates DB-agnostic xUnit tests with deterministic seed data that validate behavior consistency across both database systems. Use when creating integration tests for a migrated project, generating test coverage for data access layers, or writing Oracle-to-PostgreSQL migration validation tests.
>
|-
|-
Mandatory checks to run before completing any task that touches md files or dart code in this repository.
Generate draw.io diagrams as .drawio files and export to PNG/SVG/PDF with embedded XML
>
>
>
>
Configures Flutter Driver for app interaction and converts MCP actions into permanent integration tests. Use when adding integration testing to a project, exploring UI components via MCP, or automating user flows with the integration_test package.
Adds interactive widget previews to the project using the previews.dart system. Use when creating new UI components or updating existing screens to ensure consistent design and interactive testing.
Implement a component-level test using `WidgetTester` to verify UI rendering and user interactions (tapping, scrolling, entering text). Use when validating that a specific widget displays correct data and responds to events as expected.
Architects a Flutter application using the recommended layered approach (UI, Logic, Data). Use when structuring a new project or refactoring for scalability.