Aller au contenu
TakoAPI
Retour aux skills

copilotkit-agent-patterns

par generaljerel

Coding Agents & IDEs
330Téléchargements rapportés par clawskills.sh
0Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

Patterns for building AI agents that integrate with CopilotKit.

Description

Ce que fait ce 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.

Quand l'utiliser

  • 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

Exemple de workflow

ENTRÉE

User asks: How do I add a human approval step before my agent deletes records?

AGENT
  1. 1

    Consult hitl-approval-gates rule to confirm tool calls are the correct mechanism for approval gates

  2. 2

    Consult hitl-timeout-fallback rule to add a timeout with safe fallback behavior

  3. 3

    Consult hitl-context-in-prompt rule to ensure the user sees enough context to decide

  4. 4

    Consult hitl-resume-state rule to preserve full agent state after the user responds

SORTIE

Agent implementation with an approval gate tool call, timeout handling, rich decision context in the prompt, and correct state restoration on resume

Installation

clawhub install generaljerel/copilotkit-agent-patterns

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens