Verified skills

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.

Create, deploy, and debug machine learning applications on Hugging Face Spaces using Gradio, Docker, or Static SDKs, with support for ZeroGPU and dedicated hardware.

Track and visualize ML training experiments with Trackio, including logging metrics, firing alerts, and retrieving data via CLI. Supports real-time dashboards, webhook alerts, and HF Space syncing.

Build ML demos on Hugging Face Spaces with ZeroGPU hardware, covering @spaces.GPU decorator usage, duration and quota tuning, process isolation, CUDA availability model, concurrency safety, and build constraints.

Fetch dataset metadata, paginate rows, search text, apply filters, and download parquet URLs from the Hugging Face Dataset Viewer API.

Train or fine-tune language and vision models using TRL or Unsloth on Hugging Face Jobs cloud infrastructure, with support for SFT, DPO, GRPO, and reward modeling, plus GGUF conversion for local deployment.

Search the Hugging Face Hub for llama.cpp-compatible GGUF models, select the right quantization, and run them locally with llama-cli or llama-server.

Creates reusable command-line scripts and utilities for the Hugging Face API, enabling chaining, piping, and intermediate data processing.

Trains and fine-tunes vision models for object detection, image classification, and segmentation using Hugging Face Transformers on cloud GPUs, with automatic dataset validation and Hub persistence.

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware, with backend selection between vLLM, Transformers, and accelerate.

Publish and manage research papers on Hugging Face Hub, including creating paper pages, linking papers to models and datasets, claiming authorship, and generating professional markdown-based research articles.

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA, including picking the right base pipeline, designing a tailored UI, and publishing the Space.

Proceed through ordinary ambiguity by making reasonable assumptions, keeping momentum, validating as you go, and ending with a clear recap of decisions, changes, verification, and residual risk.

Makes completion state obvious at the end of every response using a red/yellow/green status block.

Transform text plans into interactive visual documents with diagrams, code snippets, and review surfaces for coding agents.

Compare, cross-review, and merge competing plans from multiple agents into one executable direction with a clear handoff.

Turn a PR, branch, commit, or git diff into an interactive visual recap with diagrams, file maps, API/schema summaries, annotated diffs, and focused review notes.

Watch, audit, and fix another agent's work by reconstructing the original request, inspecting evidence, and reporting gaps.

Orchestrate token-heavy research, coding, and testing by delegating bounded tasks to cheaper subagents while reserving Claude Fable for architecture, synthesis, and final review.

Orchestrate expensive frontier models as reviewers and cheaper subagents for bounded, token-heavy work to optimize cost and quality.

Forces web searches and reading of official docs before implementing, integrating, or debugging third-party APIs, libraries, and services to ensure accuracy and avoid guesswork.

Keep long-running agent work within 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.

Guides contributors through adding, updating, publishing, documenting, validating, and wiring public skills in the BuilderIO/skills repository, covering plain skills, instruction-style skills, app-backed/MCP skills, and Plan skill sync.

Write correct, efficient Kusto Query Language queries with coverage of syntax, joins, dynamic types, datetime pitfalls, regex, serialization, memory management, and advanced functions.

Captures and analyzes Windows debug output (OutputDebugString, DbgPrint/KdPrint) from the command line, with filtering, bounded execution, and remote monitoring.

Build applications that programmatically interact with GitHub Copilot using the Copilot SDK, supporting session management, custom tools, streaming, hooks, MCP servers, and deployment across Node.js, Python, Go, and .NET.

Guides the creation of high-quality MCP servers that enable LLMs to interact with external services through well-designed tools, covering planning, implementation, testing, and evaluation across multiple programming languages.

Provides a structured guide for creating effective skills for AI coding agents, with emphasis on Azure SDKs and Microsoft Foundry services.

Create and manage OAuth2-capable identities for AI agents using Microsoft Graph beta API.

Query official Microsoft documentation to understand concepts, find tutorials, configuration options, limits, quotas, and best practices for Azure, .NET, M365, Windows, Power Platform, and other Microsoft technologies.

Implements a continual learning loop for AI coding agents using hooks, two-tier memory (global and local), and automatic pattern detection to persist and apply learnings across sessions.

Generate AI-powered podcast-style audio narratives from text using Azure OpenAI's GPT Realtime Mini model via WebSocket, with full-stack implementation from React frontend to Python FastAPI backend.

Transform raw notes, error logs, voice dictation, or screenshots into structured GitHub-flavored markdown issue reports.

Review UI implementations against design quality standards and design system compliance, or create distinctive, production-grade frontend interfaces from scratch.

Design well-architected, production-grade cloud systems following Azure Architecture Center best practices, including design principles, architecture styles, cloud design patterns, and technology choice frameworks.