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.
524 skills found
Architect multi-agent systems to overcome context limits, using patterns like supervisor, swarm, and hierarchical models to manage complex workflows.
A runtime skill discovery engine for AI agents. Search and retrieve specialized agent skills (SKILL.md) on-demand via REST API or MCP to inject procedural knowledge into your agent's context.
Framework for orchestrating long-running agentic tasks, evidence-based delivery, and automated QA gates following Simon Willison's iterative loop.
Plan features through an interactive, multi-step process that generates comprehensive Product Requirements Documents (PRDs) with user stories, acceptance criteria, and technical specifications.
Manage Neovim configurations, plugin ecosystems, and custom reproducible builds.
Install and manage Codex agent skills from curated lists or GitHub repositories.
A comprehensive financial modeling suite for investment analysis, featuring DCF valuation, sensitivity testing, Monte Carlo simulations, and scenario planning.
Rigorous research skill that enforces source verification via WebFetch and content analysis to prevent hallucinated citations.
Create structured, high-quality technical implementation plans via an agent-driven, iterative process. Ideal for complex refactoring, new features, and technical design.
Physical hardware synthesis bridge for PAI. Generates blueprints, 3D printing code, SVG paths for laser cutting, and G-Code for CNC machining to bring agentic designs into the physical world.
Advanced multi-language debugging support with stack trace analysis, runtime error triage, and automated diagnostic tools for containerized and distributed systems.
Manage Google Search Console indexing: track status, sync sitemaps with GSC data, handle indexing lag, and process false positives with prioritized markdown reports.