multi-agent-patterns
Architect multi-agent systems to overcome context limits, using patterns like supervisor, swarm, and hierarchical models to manage complex workflows.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
525 skills found
Architect multi-agent systems to overcome context limits, using patterns like supervisor, swarm, and hierarchical models to manage complex workflows.
Research agent for Nia: index/search remote codebases, docs, and packages. Optimizes AI context by prioritizing full source indexing over web fetches to reduce hallucinations.
A comprehensive automation skill for Cosense (formerly Scrapbox) enabling page reading, searching, creating, and safe editing via API.
Convert Figma designs to project-consistent UI code using TemPad Dev MCP for precise markup, styling, and token integration.
A collection of design patterns for the Langroid multi-agent framework, covering agent configuration, tool handling, task orchestration, and external integrations.
Conduct systematic literature reviews across PubMed, arXiv, and Semantic Scholar with AI-driven synthesis, verified citations, and mandatory schematic visualization.
Analyze markdown documentation files to ensure compliance with predefined AI token budgets and optimize content for efficient AI ingestion.
Optimize agent context windows through KV-caching, observation masking, summarization-based compaction, and context partitioning to reduce costs and latency.
Execute implementation plans in separate sessions with review checkpoints, ensuring task-by-task verification and robust code quality.
Automate complete internationalization for Fumadocs. Configures multi-language routing, language switcher, sidebar filtering, and content structure for Next.js projects.
Build interactive, hypermedia-driven web applications using Rust, Axum, and HTMX for dynamic, real-time UI updates without complex JavaScript frameworks.
Expert copyeditor and writing specialist that identifies grammar, logic, and flow errors in text with actionable, targeted fix suggestions.