Anthropic

帮助将常用任务指令整理为Claude Code斜杠命令，涵盖参数传递、文件引用、执行工具指定，以及包含用户交互的流程编排。

• 将固定审查指令整理为命令
• 通过参数指定文件或问题编号
• 共享团队通用工作流程

将使用Claude Sonnet 4.0、Sonnet 4.5或Opus 4.1的代码及API配置迁移至Opus 4.5，并按需调整提示词。

• 更新现有代码中的模型标识符
• 按所用平台迁移API配置
• 调整导致工具调用过多的提示词

帮助创建Hookify规则，在Claude执行命令或编辑文件时按条件发出警告或阻止操作，涵盖正则表达式、多条件匹配，以及规则的测试和调整。

• 阻止危险的命令行操作
• 编辑敏感文件时发出警告
• 在编辑时检测调试代码

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

指导通过MCP为Claude Code插件连接外部服务，涵盖连接方式选择、服务器配置、身份验证、工具权限设置，以及连接和工具调用的运行检查。

• 为插件添加本地MCP服务器
• 设置外部服务的身份验证
• 通过命令或智能体使用多个服务

帮助创建响应 Claude Code 操作前后、停止及会话开始事件的钩子，配置危险操作验证、完成检查和项目信息加载，并涵盖测试与调试。

• 执行前检查命令和文件写入
• 智能体停止前检查工作完成情况
• 会话开始时加载项目信息

Review an Anthropic Cookbook notebook for clear explanations, code quality, technical accuracy, and practical usefulness. It combines automated checks, including exposed credential detection, with a scored report and specific recommendations tied to sections and lines.

中文简介正在准备中。当前显示英语简介。

• Review a Cookbook notebook before publication
• Check introductions and conclusions against learning objectives
• Scan for hardcoded API keys and credentials

Build financial models for valuation and investment analysis using discounted future cash flows, assumption testing, and probability simulations. Outputs include Excel models, comparison tables, charts, and valuation ranges to examine possible outcomes and risks.

中文简介正在准备中。当前显示英语简介。

• Build a company valuation model from financial statements
• Test how growth and discount rates affect valuation
• Simulate acquisition valuation under uncertain assumptions

Calculate financial ratios from company statements to assess profitability, ability to cover obligations, efficiency, and valuation. Results include explanations, comparisons across periods, available industry benchmarks, and a formatted Excel report.

中文简介正在准备中。当前显示英语简介。

• Comparing profitability across reporting periods
• Assessing ability to cover short-term obligations
• Calculating valuation ratios for investment analysis

Apply corporate brand standards to PowerPoint, Excel, and PDF documents. The skill guides colors, fonts, layouts, logo placement, and writing style, with scripts for applying formatting and checking compliance.

中文简介正在准备中。当前显示英语简介。

• Creating presentations with consistent corporate branding
• Standardizing spreadsheet tables and charts
• Checking PDF layouts and writing style

Investigate one difficult mathematics problem through repeated rounds of independent agent work and review. Track proved, refuted, and unresolved claims, check proposed proofs, and produce a self-contained proof.md that clearly states what remains unproved.

中文简介正在准备中。当前显示英语简介。

• Investigate a difficult mathematics problem over multiple rounds
• Check a proposed proof through independent reviews
• Track proved claims and unresolved gaps

Build Claude Code plugin hooks: automated checks triggered by tool use or session events. Get guidance on prompt and command hooks for validating actions, checking task completion, loading context, and testing configurations.

中文简介正在准备中。当前显示英语简介。

• Checking dangerous commands before execution
• Verifying completion before the agent stops
• Loading project context when a session starts

Connect Claude Code plugins to external services through MCP, a protocol that makes service functions available as tools. Covers connection types, configuration files, authentication, tool permissions, and testing for local servers and hosted services.

中文简介正在准备中。当前显示英语简介。

• Connecting a plugin to an external API
• Configuring a local MCP server
• Setting up OAuth or token authentication

Build a single HTML file with controls, an instant preview, and a copyable prompt. Use it to explore designs, data queries, concepts, or reviews visually, then turn selected settings into clear instructions for an agent.

中文简介正在准备中。当前显示英语简介。

• Explore colors, typography, and spacing visually
• Build data queries with interactive controls
• Review documents with approval and comment controls

Design autonomous agents for Claude Code plugins, including when they should run, what they should do, and which tools they may use. Provides file templates and guidance for validating configuration and testing behavior.

中文简介正在准备中。当前显示英语简介。

• Create a code review agent
• Clarify when an agent should run
• Limit the tools an agent can access

Create and organize Claude Code plugins with guidance on configuration files, commands, agents, skills, hooks, and MCP servers. Learn where components belong, how automatic loading works, and how to reference files across different installation locations.

中文简介正在准备中。当前显示英语简介。

• Create the directory structure for a new plugin
• Organize commands, agents, skills, and hooks
• Make file references work across installation locations

Manage access to a Telegram channel integration by approving pairing codes, updating allowed users, and setting direct-message and group policies. Check pending requests and adjust reply behavior through configuration files read by the channel server.

中文简介正在准备中。当前显示英语简介。

• Approve or deny a Telegram pairing request
• Review and update allowed users
• Change direct-message access policies

Create reusable slash commands for recurring work in Claude Code. This guide covers arguments, file references, tool permissions, shell commands, and input checks, with examples for reviews, tests, documentation, and plugin workflows.

中文简介正在准备中。当前显示英语简介。

• Turning recurring requests into reusable commands
• Building commands with arguments and file references
• Organizing commands shared across a team

Review CLAUDE.md files, which provide project instructions to Claude Code. Receive a scored quality report covering commands, structure, and outdated guidance, then approve focused edits that keep the instructions concise and useful.

中文简介正在准备中。当前显示英语简介。

• Auditing project instructions for Claude Code
• Updating outdated build and test commands
• Reviewing instructions across multiple packages

Manage who can contact an assistant through the iMessage channel. Update approved senders, approve pairing codes, and configure direct message and group access rules by editing the channel’s local settings.

中文简介正在准备中。当前显示英语简介。

• Add or remove approved iMessage senders
• Approve or reject a pending pairing code
• Set group access and mention requirements

Build a tabbed project status page with goals, workstreams, owners, risks, and next actions. Publish it privately on claude.ai, then refresh the same URL from current sources and report what changed since the previous update.

中文简介正在准备中。当前显示英语简介。

• Sharing progress across multiple workstreams
• Tracking a software migration across several PRs
• Summarizing research or launch milestones

Set up a Telegram bot channel for reaching the assistant. Save or remove the bot token, inspect configuration and pending access requests, and get guidance on limiting contact to an approved list of senders.

中文简介正在准备中。当前显示英语简介。

• Saving a Telegram bot token for initial setup
• Checking token settings and pending pairing requests
• Reviewing who can contact the assistant

Turn local Claude Code session history into a personal activity report, cross-checked with local Git history. Generate Markdown and standalone HTML showing project activity, touched files, related commits, and each project's share of compute usage.

中文简介正在准备中。当前显示英语简介。

• Explaining Claude Code usage to a manager
• Reviewing monthly activity across projects
• Preparing evidence for a personal performance review

Create and improve skills for Claude Code plugins. Define when a skill should activate, organize its instructions and supporting files, and check that examples, scripts, and references work together as intended.

中文简介正在准备中。当前显示英语简介。

• Create a new skill inside a Claude Code plugin
• Clarify the requests that should activate a skill
• Split lengthy instructions into supporting references