Skills for Claude Desktop

Build MCP Server

anthropics

Streamline your MCP server development with guided discovery.

Doublecheck

github

A verification pipeline for AI-generated claims.

Troubleshoot

microsoft

Analyze logs to understand chat agent behavior.

Agent Governance

github

Implement safety and trust controls for AI agents.

Pinecone RAG

github

Build RAG pipelines with Pinecone as your vector database.

Agent User Creation

github

Enable AI agents as digital workers in Microsoft Entra ID.

A

Agentic Evaluation

github

Enhance AI outputs through iterative evaluation and refinement.

Agent Introspection Debugging

affaan-m

Systematic self-debugging for AI agent failures.

Bootstrap Soul

bytedance

Personalize your AI partner through guided conversation.

S

Skill Installer

anthropics

Safely install community skills from a registry.

Memory & State Management

google-gemini

Enhance bot memory and session synchronization.

Skill Orchestrator

sickn33

Intelligently coordinates skills for complex tasks.

Long Horizon Prompting

muratcankoylan

Craft precise prompts for autonomous agents.

BDI Mental State Modeling

muratcankoylan

Transform RDF context into agent mental states.

Team Composition Patterns

wshobson

Optimize agent team setups for various tasks.

Checkpoint Promotion

wshobson

Ensure your AI model meets quality standards before deployment.

Preference Optimization

wshobson

Align models with user preferences efficiently.

E

Eval Harness First

wshobson

Essential setup for fine-tuning AI models.

Fine-Tuning Method Selection

wshobson

Streamline your fine-tuning decisions effectively.

Team Communication Protocols

wshobson

Enhance agent collaboration with structured messaging.

T

Trace To Training Data

wshobson

Transform evaluation traces into training data efficiently.

Naval Perspective

alchaincyf

Engage with Naval Ravikant's thought framework.

Inter-Agent Protocol

alirezarezvani

Streamline communication among C-suite AI agents.

Prompt Engineer

jeffallan

Optimize and evaluate prompts for LLMs effectively.