Token导航 LogoToken导航TokenDH.com
效率需要联网clawhub未标认证来源可访问clear审计通过

copilotkit-reactcopilotkit React 效率

Agent Skill

用于辅助前端页面、组件、样式和交互逻辑的开发与维护。它适合让 Agent 生成或审查 React、Next.js、Vue、Tailwind、CSS 等相关代码,整理组件结构,或定位布局和性能问题。使用时需要结合项目现有设计系统、路由和构建方式,避免只生成孤立片段;涉及页面改动时,应配合本地预览和构建检查确认视觉效果。

总安装

22,815

周安装

932

GitHub Stars

1

下载量

7,381
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:copilotkit-react(copilotkit React 效率)
来源仓库:https://github.com/generaljerel/copilotkit-react
安装命令:
openclaw skills install copilotkit-react
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install copilotkit-react

简介

用于辅助 React 前端组件、样式和交互逻辑开发。

  • 适合生成或审查 Next.js、Vue、Tailwind 相关代码。
  • 通过 clawhook 安装,需确认项目路由和构建方式。
  • 使用时应结合设计系统,避免孤立片段输出。
  • 涉及页面改动时建议本地预览确认效果。copilotkit-react 属于效率类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

name
copilotkit-react-patterns
description
CopilotKit React best practices for agentic applications. Use when writing, reviewing, or refactoring React code that uses CopilotKit hooks (useAgent, useFrontendTool, useRenderTool, useCopilotAction, useCopilotReadable), providers (CopilotKit), or chat UI components (CopilotChat, CopilotSidebar, CopilotPopup). Triggers on tasks involving agent integration, tool rendering, shared state, or generative UI in React.
license
MIT
metadata
author
copilotkit
version
2.0.0

CopilotKit React Patterns

Best practices for building agentic React applications with CopilotKit. Contains 25 rules across 6 categories, prioritized by impact to guide code generation and refactoring. Covers both v1 (@copilotkit/react-core) and v2 (@copilotkit/react-core/v2) APIs.

When to Apply

Reference these guidelines when:

  • Setting up CopilotKit provider in a React application
  • Using agent hooks (useAgent, useFrontendTool, useCopilotAction)
  • Rendering tool calls or custom messages from agents
  • Managing shared state between UI and agents via useCopilotReadable or useCoAgent
  • Building chat interfaces with CopilotChat, CopilotSidebar, or CopilotPopup
  • Configuring suggestions for proactive agent assistance

Rule Categories by Priority

PriorityCategoryImpactPrefix
1Provider SetupCRITICALprovider-
2Agent HooksHIGHagent-
3Tool RenderingHIGHtool-
4Context & StateMEDIUMstate-
5Chat UIMEDIUMui-
6SuggestionsLOWsuggestions-

Quick Reference

1. Provider Setup (CRITICAL)

  • provider-runtime-url - Always configure runtimeUrl to connect to your agent backend
  • provider-single-endpoint - Configure the agent prop for CoAgent routing
  • provider-nested-providers - Scope agent configurations with nested CopilotKit providers
  • provider-tool-registration - Register tools via hooks inside provider, not as props when possible

2. Agent Hooks (HIGH)

  • agent-use-agent-updates - Specify update subscriptions to avoid unnecessary re-renders
  • agent-agent-id - Always pass agentId when running multiple agents
  • agent-context-description - Write descriptive context values for useCopilotReadable
  • agent-frontend-tool-deps - Declare dependency arrays for useFrontendTool
  • agent-stable-tool-handlers - Use useCallback for tool handler functions

3. Tool Rendering (HIGH)

  • tool-typed-args - Define Zod schemas for useRenderTool parameters (v2)
  • tool-status-handling - Handle all three tool call statuses (inProgress, executing, complete)
  • tool-wildcard-fallback - Register a wildcard renderer as fallback for unknown tools
  • tool-render-vs-frontend - Use useRenderTool for display-only, useFrontendTool for side effects
  • tool-component-hook - Use useFrontendTool render prop for simple component rendering

4. Context & State (MEDIUM)

  • state-minimal-context - Provide only relevant context to agents, not entire app state
  • state-structured-values - Use structured objects in useCopilotReadable, not serialized strings
  • state-context-granularity - Split context into multiple useCopilotReadable calls by domain
  • state-avoid-stale-closures - Use functional state updates in tool handlers

5. Chat UI (MEDIUM)

  • ui-chat-layout - Choose CopilotSidebar for persistent chat, CopilotPopup for on-demand
  • ui-custom-labels - Always customize labels for your domain instead of defaults
  • ui-welcome-screen - Provide a welcome screen with suggested prompts
  • ui-input-mode - Use appropriate inputMode for your use case

6. Suggestions (LOW)

  • suggestions-configure - Use useConfigureSuggestions (v2) or useCopilotChatSuggestions (v1)
  • suggestions-context-driven - Provide rich context so suggestions are relevant
  • suggestions-loading-state - Handle suggestion loading states via useSuggestions (v2)

How to Use

Read individual rule files for detailed explanations and code examples:

rules/provider-runtime-url.md
rules/agent-use-agent-updates.md
rules/tool-typed-args.md

Each rule file contains:

  • Brief explanation of why it matters
  • Incorrect code example with explanation
  • Correct code example with explanation
  • Additional context and references

Full Compiled Document

For the complete guide with all rules expanded: AGENTS.md

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

75.58%
按下载量换算5,579

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

未展示

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills