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.
284 skills
AnthropicOfficial
Comprehensive reference for integrating Anthropic's Claude API, SDKs, and Managed Agents into your applications.
K-Dense· Community
Integrate Hugging Face Transformers for model loading, inference, and fine-tuning across NLP, vision, and audio tasks.
K-Dense· Community
Integrate with the self-hosted Open Notebook platform to automate research ingestion, context-aware chat, and AI-driven analysis.
Seth Hobson· Community
A structured workflow for supervised fine-tuning of vision-language models, focusing on adapter configuration and silent failure prevention.
Seth Hobson· Community
A comprehensive framework for evaluating LLM application performance using automated metrics, human feedback, and LLM-as-a-judge techniques.
Seth Hobson· Community
Provides configuration recipes and best-practice hyperparameters for LoRA and QLoRA supervised fine-tuning.
Seth Hobson· Community
Align fine-tuned models with human preference data using DPO, ORPO, KTO, or SimPO methods.
Seth Hobson· Community
A comprehensive guide to building Retrieval-Augmented Generation (RAG) systems for grounding LLM applications in external data.
Seth Hobson· Community
A decision-making framework to determine if fine-tuning is necessary and which training method best fits your data and task.
Seth Hobson· Community
Patterns and implementation strategies for combining vector and keyword search to improve retrieval accuracy in RAG systems.
Seth Hobson· Community
A skeptical strategist that gatekeeps fine-tuning requests by enforcing rigorous evaluation baselines and method selection.
Seth Hobson· Community
An expert AI engineer persona for building, orchestrating, and deploying production-ready LLM applications and agentic systems.
Seth Hobson· Community
A guide to selecting and optimizing embedding models for semantic search and RAG applications.
Seth Hobson· Community
A structured workflow for training reasoning and verifiable task behavior using GRPO and Reinforcement Learning from Verifiable Rewards.
Seth Hobson· Community
Convert graded evaluation traces and production logs into SFT examples and DPO preference pairs for model training.
Seth Hobson· Community
Prepare, format, and validate datasets for supervised fine-tuning and preference training.
GitHubOfficial
Unified agent for instrumenting, auditing, and managing LLM application telemetry and prompts using Comet Opik.
GitHubOfficial
Manage LLM-as-judge evaluation workflows on Arize for projects and experiments.
GitHubOfficial
Optimize and debug LLM prompts using production trace data, evaluations, and the ax CLI.
GitHubOfficial
An interactive verification agent that audits AI-generated content through claim extraction, source verification, and adversarial review.
GitHubOfficial
A persistent, compounding knowledge base that combines an LLM-maintained wiki with a structured knowledge graph for evidence-backed retrieval.
GitHubOfficial
A comprehensive guide for instrumenting LLM applications with OpenInference tracing for Phoenix AI observability.
GitHubOfficial
Manage, run, and analyze model performance experiments using the Arize ax CLI.
AnthropicOfficial
A framework for decomposing natural language queries into parallel, source-specific search operations.