copilotkit-agent-patterns
por generaljerel
Coding Agents & IDEsResumen
Patterns for building AI agents that integrate with CopilotKit.
Descripción
Qué hace esta skill
A collection of 20 architecture and implementation rules for building AI agents that connect to CopilotKit. Covers AG-UI event streaming, shared state management, human-in-the-loop checkpoints, and generative UI emission. Organized into five priority tiers for incremental adoption.
Rather than piecing together AG-UI protocol behavior from scattered docs, these rules give ordered, opinionated patterns that cover the full lifecycle from architecture to generative UI.
Cuándo usarla
- Adding approval gates before an agent takes a destructive action
- Streaming agent output incrementally into a React UI component
- Syncing shared state between a LangGraph agent and a CopilotKit frontend
- Rendering dynamic UI components from agent tool calls
- Configuring MCP server endpoints for external tool access in an agent
Flujo de trabajo de ejemplo
User asks: How do I add a human approval step before my agent deletes records?
- 1
Consult hitl-approval-gates rule to confirm tool calls are the correct mechanism for approval gates
- 2
Consult hitl-timeout-fallback rule to add a timeout with safe fallback behavior
- 3
Consult hitl-context-in-prompt rule to ensure the user sees enough context to decide
- 4
Consult hitl-resume-state rule to preserve full agent state after the user responds
Agent implementation with an approval gate tool call, timeout handling, rich decision context in the prompt, and correct state restoration on resume
Instalación
clawhub install generaljerel/copilotkit-agent-patternsEjecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.