agent-architecture
Implement production-grade AI agents with LangGraph, tool-calling guardrails, SSE streaming, and episodic memory. Includes anti-patterns, fix pairs, and stateful architecture patterns.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
151 skills found
Implement production-grade AI agents with LangGraph, tool-calling guardrails, SSE streaming, and episodic memory. Includes anti-patterns, fix pairs, and stateful architecture patterns.
Anthropic Claude AI models for high-performance coding, large-context analysis, and GUI interaction.
Multi-model LLM integration patterns for Claude, GPT, Gemini, and Ollama. Features API handling, prompt engineering, token management, and model-agnostic orchestration.
Automate Instagram posts via Telegram or CLI. Features residential proxy bypass, session caching, and WaveSpeed image integration.
Epistemic safety analysis for JSON data in prompts to prevent LLM hallucinations and reasoning errors when handling incomplete or large-scale datasets.
Search the web for real-time data and research using the Turing Tavily proxy. Use for up-to-date information, current events, and web-based research tasks.
Comprehensive office productivity toolkit for AI agents, featuring PDF, Word, Excel, PowerPoint, and internal communication automation capabilities.
Automate frontend API integration using Apidog and MCP servers. Generate TypeScript types, TanStack Query hooks, and axios-based clients from OpenAPI specifications for consistent, type-safe API consumption.
MPC-based multi-chain wallet SDK and CLI for AI agents and developers. Perform secure, threshold-signed crypto operations (send, swap, sign) across 40+ blockchains without seed phrases.
A toolkit for building robust LLM integrations: API patterns, streaming, function calling, RAG pipelines, and cost-effective model routing.
The foundational skill for the Superpowers methodology. Ensures agents correctly identify and invoke required development skills before starting any task or conversation.
Project bootstrap for Claude Code with safety guardrails, git workflow automation, project auditing, and structured multi-phase planning.