“hooks”的搜索结果

从Claude Code工作记录中识别用户修正、错误解决方法和重复流程，积累带有依据与置信度的行为规则，按项目整理，并将相关规则发展为技能、命令或智能体。

• 让智能体学习工作偏好和流程
• 按项目整理开发规范
• 将学到的规则转为技能

读取仓库设置和智能体运行环境，盘点已连接工具与可用功能，区分缺少工作流程和缺少外部集成的情况，并按优先级提出三至五项ECC后续建议。

• 检查Claude Code设置
• 盘点已连接工具及其功能
• 判断是否需要添加插件

梳理GitHub、Linear及本地通知，按重要程度和负责人设计接收渠道，合并重复事件，并明确哪些应即时提醒、汇总发送、进入待办列表或仅记录日志。

• 统一多个工具的通知流程
• 减少CI失败的重复提醒
• 区分紧急提醒与汇总通知

从 Claude Code 中的修正、错误解决和重复操作中提取带置信度的行为规则，按项目分别管理，并将相关规则整合为技能、命令或智能体。

• 将修正指令和重复工作积累为知识
• 按项目分别管理开发规范
• 将行为规则整合为技能或命令

检查Claude Code配置中的重复技能、过时记忆和多余权限等项目，逐项提供依据并征求确认，通过停用或移存进行可撤销的整理，并记录修改与恢复方法。

• 批量安装技能后检查重复
• 检查过时记忆和多余钩子
• 整理重复的权限配置

帮助为 Claude Code 插件实现按项目保存设置与状态的机制，通过本地文件切换行为，涵盖设置读取、默认值和数值验证。

• 为插件增加按项目保存的设置
• 通过设置启用或停用钩子
• 保存智能体任务和进度

帮助创建和整理Claude Code插件，说明配置文件、命令与技能的存放位置、组件自动加载机制，以及不依赖安装位置的路径配置方法。

• 创建插件初始框架
• 整理命令和技能的存放位置
• 配置不依赖安装位置的路径

清理 iOS 应用中由 /ios-qa 添加的调试机制，移除 DebugBridge 包及连接代码，并清理状态检查、调试显示、生成代码和应用内集成逻辑。

• 在 /ios-qa 检查后清理应用
• 移除 DebugBridge
• 移除状态服务与调试浮层

依据browser-use参考资料，协助编写Python浏览器自动化代码，涵盖安装、智能体与浏览器配置、模型连接、自定义工具、运行监控及费用跟踪。

• 用Python自动执行浏览器操作
• 配置智能体与浏览器认证
• 添加自定义工具和执行钩子

将心理学与行为科学用于营销文案和设计，调整吸引关注的开头、信息呈现方式及价格展示，帮助你审视促销表达。

• 调整吸引关注的开头
• 审视信息呈现方式
• 改善价格展示方式

在执行前对任务分流，报告被判定可跳过LLM调用的任务比例，为其余任务提供推荐模型与费用上限估算，并保存结果供后续费用报告使用。

• 批量处理相似任务前检查
• 审视简单代码转换的LLM费用
• 确认Agent Booster适用比例

Automate Docker Hub administration through Composio: create organizations and repositories, list teams, invite members, and configure webhooks that notify other services when container images are pushed to a repository.

中文简介正在准备中。当前显示英语简介。

• Create a Docker Hub organization or repository
• Review repositories with filters and sorting
• List teams and invite organization members

Check opencode commands, HTTP server behavior, lifecycle events, and terminal startup with purpose-built scripts. Find stored sessions by ID, title, or scoped message searches, and export conversations as JSON for further inspection.

中文简介正在准备中。当前显示英语简介。

• Check CLI commands and HTTP server health
• Observe lifecycle events associated with plugin hooks
• Check terminal startup and keyboard input

Create a new native Muse plugin package with its manifest and requested capability files, then validate it using the installed muse CLI. Receive a file inventory, validation results, and an installation proposal for later use.

中文简介正在准备中。当前显示英语简介。

• Package skills as a new Muse plugin
• Create a Muse plugin with command templates
• Define hooks or MCP server connections

Audit a Claude Code setup for installation problems, broken settings, unused extensions, and duplicated instructions. It reviews local usage evidence, recommends cleanup, and applies approved fixes, with separate confirmation for permission changes.

中文简介正在准备中。当前显示英语简介。

• Diagnose installation and configuration problems
• Review unused skills, MCP servers, and plugins
• Trim duplicated or unnecessary CLAUDE.md guidance

Create a Codex plugin scaffold with a valid manifest, optional folders for skills and supporting files, and personal marketplace entries. Also guides validation and the cache refresh and reinstall steps used during local plugin development.

中文简介正在准备中。当前显示英语简介。

• Create the initial structure for a personal Codex plugin
• Add folders for skills, hooks, scripts, and assets
• Register and update a plugin in a personal marketplace

Analyze a project’s code and existing settings to recommend useful Claude Code automations. Receive tailored suggestions for event-triggered actions, specialist agents, skills, plugins, and external tool connections, with reasons and setup locations.

中文简介正在准备中。当前显示英语简介。

• Choosing Claude Code features for a new project
• Finding ways to automate formatting and checks
• Selecting external tool connections for the project

Build AI agents that make phone calls and send or receive SMS through the AgentPhone API. Manage phone numbers, configure voice agents and event notifications, and inspect call transcripts and account usage.

中文简介正在准备中。当前显示英语简介。

• Create an AI voice agent with a phone number
• Send and receive SMS through AgentPhone
• Review call transcripts and account usage

Create and edit Agent QA tests, test suites, and hooks, then validate their structure and tool-generated IDs before running them. Use MCP, an agent tool connection, or the CLI within a configured workspace.

中文简介正在准备中。当前显示英语简介。

• Create and validate a checkout test for staging
• Update an existing test suite
• Check YAML definitions and IDs

Analyze a project's code and configuration to recommend useful Claude Code automations. Get tailored suggestions for event-triggered actions, specialist agents, reusable skills, plugins, and external tool connections, with reasons for each recommendation.

中文简介正在准备中。当前显示英语简介。

• Set up Claude Code for a new project
• Find useful formatting and testing automations
• Choose external tool connections for a project's stack

Analyze Android apps in a CTF sandbox using static inspection and Frida hooks, which observe or alter running code. Trace request signing, local storage, and Java-to-native boundaries to reproduce a request accepted by the server.

中文简介正在准备中。当前显示英语简介。

• Tracing request-signing inputs and outputs
• Inspecting Java-to-native calls with runtime hooks
• Examining app settings, databases, and token storage

Check your understanding of one Claude Code tutorial lesson with a 10-question quiz. Get feedback after each round, a final score, and specific topics to review, whether you take it before, during, or after studying.

中文简介正在准备中。当前显示英语简介。

• Check prior knowledge before a lesson
• Check understanding while studying
• Review weak areas after a lesson

Learn how to check Claude Code tool calls against a policy and create digitally signed execution records. This walkthrough covers setup, offline verification, tamper demonstrations, and CI/CD integration before adopting the protect-mcp runtime plugin.

中文简介正在准备中。当前显示英语简介。

• Evaluate signed audit records before adopting runtime hooks
• Demonstrate offline verification and tamper detection
• Verify agent execution records in CI/CD

Configure a Claude Code hook that checks shell commands before execution and blocks flags that skip Git checks or commit signing. It helps preserve existing commit quality checks while documenting the guard's limits.

中文简介正在准备中。当前显示英语简介。

• Blocking flags that skip commit checks
• Preventing commands that disable commit signing
• Sharing Claude Code guard settings across a team