agentic-workflows
Build production-grade AI agents using LangGraph, Anthropic/OpenAI/vLLM, and structured outputs. Features streaming, A2A protocol, Pydantic validation, vector memory, and guardrails for resilient, multi-agent workflows.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
543 skills found
Build production-grade AI agents using LangGraph, Anthropic/OpenAI/vLLM, and structured outputs. Features streaming, A2A protocol, Pydantic validation, vector memory, and guardrails for resilient, multi-agent workflows.
Orchestrates multi-agent development workflows, managing task decomposition, requirement analysis, and quality assurance for complex software projects.
Enables cross-session context persistence for Claude Code, managing history, project decisions, and workflow patterns to ensure seamless task continuation.
Expert consultant for designing and building high-quality, consistent AI agent skills. Guides you through discovery, architecture, and creation phases to ensure reliable, composable, and efficient skill delivery.
Semantic code analysis guide for Serena MCP. Automatically prioritizes Serena tools for symbols, references, and code memory to optimize context and efficiency.
Draft professional emails across business, technical, and customer service contexts. Includes templates for requests, follow-ups, updates, and more with customizable tones.
Intelligently migrate existing brownfield projects to the AgenticDev structure using AI-powered analysis to reorganize documentation, generate rich frontmatter, and preserve git history.
Designer's eye QA: detects and automates fixes for visual inconsistencies, spacing, hierarchy, and UI polish issues. Iteratively verifies with before/after screenshots.
Retrieve real-time library documentation, code examples, and technical guidance using the Context7 API for frameworks like React, FastAPI, and Next.js.
Automate drafting tweets and threads on X (Twitter) using browser automation. Ensures content is saved to drafts for manual review.
Multi-LLM code review pipeline using consensus-based analysis to detect security, architectural, and quality issues.
Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.