AI Skills for Anthropic API

Optimizes LLM API costs with model routing, budget tracking, retry logic, and prompt caching for efficient usage.

Designs advanced LLM applications using LangChain and LangGraph for AI agents, memory management, and tool integration.

Enables the creation of AI agents that interact with computers like humans, focusing on security and automation through vision-based control.

Expertly builds stateful, multi-actor AI applications using LangGraph, focusing on graph construction and state management.

LangChain enables the development of LLM-powered applications with agents and RAG, supporting multiple providers and integrations.

Automates startup processes by orchestrating specialized agents across various domains, enabling zero human intervention from PRD to deployment.

Builds AI-powered products that effectively utilize AI APIs, focusing on prompt engineering, cost management, and user experience.

LlamaIndex is a data framework for building LLM applications, enabling document ingestion, indexing, and querying for enhanced knowledge retrieval.

Provides a platform for monitoring and debugging LLM applications, enabling systematic evaluation and tracing of model outputs.

Enables the creation of complex AI systems using declarative programming and automatic prompt optimization with DSPy from Stanford NLP.

Facilitates structured data extraction from LLM responses using Pydantic validation and supports multiple LLM providers.

Automates multi-agent orchestration for startups, enhancing efficiency across engineering, QA, DevOps, and business operations.

Builds AI-powered products that effectively utilize APIs to solve specific problems, focusing on user experience and cost management.

Automates GitHub workflows using AI for PR reviews, issue triage, and CI/CD integration, enhancing development efficiency.

Expertly builds stateful, multi-actor AI applications using LangGraph, focusing on graph construction and state management.

Enables the creation and management of Python-based AI agents using the AWS Strands SDK for autonomous workflows and custom tools.

Generates type-safe BAML code for LLM workflows, enabling structured outputs and seamless integration with various frameworks.

Facilitates the deployment of new OpenClaw agents through a conversational interface, leveraging Docker for seamless onboarding.

Automatically routes tasks to the best AI model based on type and cost, optimizing performance across multiple providers.

Generates and executes declarative AI workflows using the comanda CLI, enabling multi-model orchestration and YAML-based configurations.