Token导航 LogoToken导航TokenDH.com
前端设计敏感数据github未标认证来源可访问clear审计提醒

typescript-sdkTypeScript SDK 搜索

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

857

周安装

35

GitHub Stars

4

下载量

274
CodexClaudeCursorGemini CLI

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

3

许可证

MIT

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:typescript-sdk(TypeScript SDK 搜索)
来源仓库:https://github.com/inkeep/skills
仓库路径:skills/typescript-sdk
安装命令:
npx skills add https://github.com/inkeep/skills --skill typescript-sdk
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/inkeep/skills --skill typescript-sdk

简介

辅助前端页面与组件的开发维护,支持多种主流框架和技术栈。

  • 可用于生成或审查 React、Vue、Tailwind CSS 等相关代码。
  • 需结合项目路由结构和构建配置使用,确保代码可集成。
  • 涉及视觉改动时建议配合本地构建验证实际效果。
  • typescript-sdk 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Typescript Sdk

Overview

The TypeScript SDK provides a declarative way to define agents, sub-agents, tools, and their relationships.

Rules (49)

Read individual rule files for detailed explanations and code examples on particular tasks or topics:

TitleTopicDescription
Sub Agent Relationships Overviewtypescript-sdk/agent-relationshipsTransfer and delegation relationships between Sub Agents
When to Use Transfers vs Delegationtypescript-sdk/agent-relationshipsGuidelines for choosing between transfer and delegation relationships
Types of Delegation Relationshipstypescript-sdk/agent-relationshipsSub agent, external agent, and team agent delegation
Configuring StopWhentypescript-sdk/agent-settingsControl stopping conditions to prevent infinite loops in agents
Sub Agent Parameters Referencetypescript-sdk/agent-settingsComplete parameter reference for subAgent() configuration
CLI inkeep add Commandtypescript-sdk/cli-referencePull a template project or MCP from the Inkeep Agents Cookbook
CLI inkeep config Commandtypescript-sdk/cli-referenceManage Inkeep configuration values
CLI Configuration File Structuretypescript-sdk/cli-referenceStructure of inkeep.config.ts and configuration priority
CLI inkeep dev Commandtypescript-sdk/cli-referenceStart the Inkeep dashboard server for visual agents orchestration
CLI Environment Variablestypescript-sdk/cli-referenceEnvironment variables respected by the CLI and SDK
CLI inkeep init Commandtypescript-sdk/cli-referenceInitialize a new Inkeep configuration file in your project
CLI inkeep list-agent Commandtypescript-sdk/cli-referenceList all available agents for a specific project
CLI inkeep login Commandtypescript-sdk/cli-referenceAuthenticate with a deployment using the device code flow
CLI inkeep logout Commandtypescript-sdk/cli-referenceClear stored credentials for a profile
CLI inkeep profile Commandtypescript-sdk/cli-referenceManage named CLI profiles for multiple remotes, credentials, and environments
CLI inkeep pull Commandtypescript-sdk/cli-referencePull project configuration from server and update local TypeScript files
CLI inkeep push Commandtypescript-sdk/cli-referencePush agent configurations to your server
CLI inkeep update Commandtypescript-sdk/cli-referenceUpdate the Inkeep CLI to the latest version
Runtime Limits Configurationtypescript-sdk/configure-runtime-limitsHow to configure execution limits, timeouts, and constraints
Runtime Configuration Variablestypescript-sdk/configure-runtime-limitsAll available environment variables for configuring runtime limits
Context Fetchers Overviewtypescript-sdk/context-fetchersHow to use context fetchers to embed real-time data in agent prompts
Credential Store Optionstypescript-sdk/credentials/overviewOptions for storing MCP server and external agent credentials
Data Operation Types Referencetypescript-sdk/data-operationsAll data operation event types and their payloads
Data Operations Overviewtypescript-sdk/data-operationsHow to enable and use data operations for debugging and monitoring
External Agents Overviewtypescript-sdk/external-agentsHow to configure and use external agents using the A2A protocol
Passing Context via Headerstypescript-sdk/headersHow to pass dynamic context to agents via HTTP headers
Using Headers in Agentstypescript-sdk/headersHow to use header values in prompts, context fetchers, and external tools
Conversation Memory Overviewtypescript-sdk/memoryHow conversation history is managed and included in context windows
Model Types Referencetypescript-sdk/modelsWhen to use each model type in the configuration hierarchy
Model Provider Optionstypescript-sdk/modelsConfiguration options for different model providers
Supported Models Referencetypescript-sdk/modelsList of supported model providers and their API keys
Defining Artifact Componentstypescript-sdk/structured-outputs/artifact-componentsHow to define artifact components with preview fields for citations and sources
Defining Data Componentstypescript-sdk/structured-outputs/data-componentsHow to define data components using Zod schemas
Status Updates Configurationtypescript-sdk/structured-outputs/status-updatesHow to configure AI-powered status updates for agents
Function Tools Execution Environmenttypescript-sdk/tools/function-toolsSandbox providers, runtime configuration, and security guarantees
Function Tools Overviewtypescript-sdk/tools/function-toolsUse cases and how to create function tools
Environment-Aware MCP Serverstypescript-sdk/tools/mcp-toolsConfigure MCP tools to switch based on environment (dev vs production)
MCP Tool Authenticationtypescript-sdk/tools/mcp-toolsAuthentication methods for MCP servers including API keys, OAuth, and custom headers
MCP Tool Overridestypescript-sdk/tools/mcp-toolsCustomize how individual MCP tools appear to agents
Selecting MCP Toolstypescript-sdk/tools/mcp-toolsHow to selectively enable tools from MCP servers
Registering MCP Servers as Toolstypescript-sdk/tools/mcp-toolsHow to register and configure MCP tools for your agents
Tool Approvals Configurationtypescript-sdk/tools/tool-approvalsHow to configure tools to require user approval before execution
Responding to Tool Approval Requeststypescript-sdk/tools/tool-approvalsHow to approve or deny tool execution requests
Trigger Configuration Optionstypescript-sdk/triggers/overviewConfiguration options for triggers including authentication, schemas, and transforms
Triggers Overviewtypescript-sdk/triggers/overviewCreating webhook endpoints to invoke agents from external services
Trigger Configuration Optionstypescript-sdk/triggers/webhooksConfiguration options for triggers including authentication, schemas, and transforms
Triggers Overviewtypescript-sdk/triggers/webhooksCreating webhook endpoints to invoke agents from external services
Configuration Priority Hierarchytypescript-sdk/workspace-configurationHow CLI flags, env vars, and config file values are resolved
Workspace Configuration Filetypescript-sdk/workspace-configurationStructure and options for inkeep.config.ts

Other Resources

For additional information, see:

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

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

Claude Code

28.34%
按下载量换算78

Antigravity

23.15%
按下载量换算63

OpenCode

16.49%
按下载量换算45

Cursor

12.65%
按下载量换算35

Codex

7.29%
按下载量换算20

Gemini CLI

2.97%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。

来源信息

继续浏览同类 Skills