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.
153 skills found
Architect multi-agent systems to overcome context limits, using patterns like supervisor, swarm, and hierarchical models to manage complex workflows.
Implement ReasoningBank adaptive learning with AgentDB's ultra-fast vector backend. Features trajectory tracking, verdict judgment, memory distillation, and pattern recognition for self-learning autonomous agents.
Shared memory and collaboration layer for AI coding agents to track actions, manage sessions, detect conflicts, and preserve project context across tools.
A standardized workflow for converting raw PM notes, workshops, or rough drafts into polished, validated, and repository-compliant AI skills.
Teacher-focused student profiling tool: OCR answer sheets, summarize performance, and update student profiles with targeted physics learning goals.
Real-time AI news briefing tool. Instantly search the web for any topic, get summarized insights in Chinese, and receive professional briefing cards via Feishu.
Automate high-quality screenshot generation for MicroSim visualizations using Chrome headless mode. Ideal for documentation, social media previews, and quality assessment.
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.
Analyze Claude Code session history to identify inefficiencies, optimize token usage, and suggest workflow improvements.
Transforms content to match specific voice profiles, tones, or styles using configurable YAML templates for consistent brand and narrative output.
A comprehensive aphorism and quote management system for thematic content enrichment, research, and newsletter curation.
An autonomous AI agent loop that executes Claude Code repeatedly to build features from structured PRDs until completion.