Trusted skills for AI agents from official vendors and established maintainers. Every skill is attributed to its author, scanned, and comes with install steps for your AI tool.
706 skills
GoogleOfficial
Develop, deploy, and manage custom BigQuery User-Defined Functions (UDFs) using SQL, JavaScript, Python, or external Cloud Run endpoints.
GoogleOfficial
Build and manage AI-powered applications, agents, and flows using the Genkit Python SDK.
GoogleOfficial
Analyze the downstream impact of BigQuery asset changes using Google Cloud data lineage.
Hugging FaceOfficial
A comprehensive toolkit for publishing, managing, and linking research papers within the Hugging Face ecosystem.
Hugging FaceOfficial
Trackio is a lightweight experiment tracking library for logging, visualizing, and alerting on machine learning training metrics.
Hugging FaceOfficial
Identify and compare top-performing AI models based on benchmark leaderboards and hardware constraints.
Hugging FaceOfficial
Integrate Hugging Face paper pages to retrieve, analyze, and manage AI research paper metadata and content.
Hugging FaceOfficial
Run machine learning models directly in JavaScript and TypeScript environments.
Hugging FaceOfficial
A structured workflow for training and fine-tuning sentence-transformers models including bi-encoders, cross-encoders, sparse, and multi-vector architectures.
Hugging FaceOfficial
Estimate memory requirements for Hugging Face Safetensors and GGUF models without downloading them.
Hugging FaceOfficial
Train and fine-tune language models on Hugging Face infrastructure using TRL or Unsloth.
Hugging FaceOfficial
Integrate with the Hugging Face Dataset Viewer API to explore, filter, and extract metadata from hosted datasets.
Hugging FaceOfficial
A guide for post-training LLMs using the TRL (Transformers Reinforcement Learning) library for SFT, DPO, GRPO, KTO, and reward modeling.
Hugging FaceOfficial
A comprehensive workflow for training and fine-tuning vision models on Hugging Face Jobs cloud infrastructure.
Hugging FaceOfficial
Integrate Hugging Face Hub capabilities directly into your AI assistant using MCP server tools.
Android (Google)Official
Integrate the LiteRT-LM Kotlin API to run open text LLMs on Android devices using CPU or GPU acceleration.
Android (Google)Official
Build autonomous on-device agentic workflows in Android apps using the ML Kit GenAI Agent API.
OpenAIOfficial
Diagnose why a metric changed or differs from expectation. Use when the task is to identify likely drivers of a metric movement, anomaly, gap, or discrepancy.
OpenAIOfficial
Design, build, revise, or QA quantitative charts and figures. Use when an analytical answer needs visual judgment, whether for an inline answer, report, dashboard, notebook, or artifact.
OpenAIOfficial
Assess whether structured data, query results, dashboards, or analytical evidence are trustworthy enough to use. Use when the task is to check data quality, reconcile conflicting sources or metric definitions, or decide whether evidence is safe to cite.
OpenAIOfficial
Validate whether an analysis is accurate, well-supported, and ready to share or use for a decision. Use when reviewing methodology, calculations, comparisons, visuals, caveats, or conclusions.
OpenAIOfficial
A router skill for managing NVIDIA Neural Reconstruction (NuRec) workflows, datasets, and engine tasks.
OpenAIOfficial
Build source-backed dashboards for monitoring performance, exploring drivers, or acting on product and business metrics. Use when the task needs a dashboard, scorecard, or monitoring view with clear metrics, filters, source definitions, and QA.
OpenAIOfficial
Create, edit, or validate reproducible SQL or Python notebooks. Use for notebooks, SQL/Python scratchpads, reproducible exploration, audit trails, or runnable companions where the analysis should be reviewable or rerunnable.