# Claude Docs

> Rewrite text following user-given instructions, such as with a different tone, audience, or style.

## Pages

- [Adaptive editor](adaptive-editor.md): Rewrite text following user-given instructions, such as with a different tone, audience, or style.
- [Admin API overview](administration-api.md): **The Admin API is unavailable for individual accounts.** To collaborate with teammates and add members, set up your ...
- [Airport code analyst](airport-code-analyst.md): Find and extract airport codes from text.
- [Alien anthropologist](alien-anthropologist.md): Analyze human culture and customs from the perspective of an alien anthropologist.
- [Alliteration alchemist](alliteration-alchemist.md): Generate alliterative phrases and sentences for any given subject.
- [Archive Workspace](archive-workspace.md): paths:
- [Babel's broadcasts](babels-broadcasts.md): Create compelling product announcement tweets in the world's 10 most spoken languages.
- [Bash tool](bash-tool.md): The bash tool enables Claude to execute shell commands in a persistent bash session, allowing system operations, scri...
- [Batch processing](batch-processing.md): Batch processing is a powerful approach for handling large volumes of requests efficiently. Instead of processing req...
- [Be clear, direct, and detailed](be-clear-and-direct.md): While these tips apply broadly to all Claude models, you can find prompting tips specific to extended thinking models...
- [Skill authoring best practices](best-practices.md): Learn how to write effective Skills that Claude can discover and use successfully.
- [Beta headers](beta-headers.md): Documentation for using beta headers with the Claude API
- [Brand builder](brand-builder.md): Craft a design brief for a holistic brand identity.
- [Cancel a Message Batch](canceling-message-batches.md): Batches may be canceled any time before processing ends. Once cancellation is initiated, the batch enters a`cancelin...
- [Career coach](career-coach.md): Engage in role-play conversations with an AI career coach.
- [Let Claude think (chain of thought prompting) to increase performance](chain-of-thought.md): While these tips apply broadly to all Claude models, you can find prompting tips specific to extended thinking models...
- [Chain complex prompts for stronger performance](chain-prompts.md): While these tips apply broadly to all Claude models, you can find prompting tips specific to extended thinking models...
- [Choosing the right model](choosing-a-model.md): Selecting the optimal Claude model for your application involves balancing three key considerations: capabilities, sp...
- [Citations](citations.md): Claude is capable of providing detailed citations when answering questions about documents, helping you track and ver...
- [Cite your sources](cite-your-sources.md): Get answers to questions about a document's content with relevant citations supporting the response.
- [Prompting best practices](claude-4-best-practices.md): This guide provides specific prompt engineering techniques for Claude 4.x models, with specific guidance for Sonnet 4...
- [Claude Code Analytics API](claude-code-analytics-api.md): Programmatically access your organization's Claude Code usage analytics and productivity metrics with the Claude Code...
- [Google Sheets add-on](claude-for-sheets.md): The [Claude for Sheets extension](https://workspace.google.com/marketplace/app/claude%5Ffor%5Fsheets/909417792257) in...
- [Claude in Microsoft Foundry](claude-in-microsoft-foundry.md): Access Claude models through Microsoft Foundry with Azure-native endpoints and authentication.
- [Claude on Amazon Bedrock](claude-on-amazon-bedrock.md): Anthropic's Claude models are now generally available through Amazon Bedrock.
- [Claude on Vertex AI](claude-on-vertex-ai.md): Anthropic's Claude models are now generally available through [Vertex AI](https://cloud.google.com/vertex-ai).
- [Client SDKs](client-sdks.md): We provide client libraries in a number of popular languages that make it easier to work with the Claude API.
- [Code clarifier](code-clarifier.md): Simplify and explain complex code in plain language.
- [Code consultant](code-consultant.md): Suggest improvements to optimize Python code performance.
- [Code execution tool](code-execution-tool.md): Claude can analyze data, create visualizations, perform complex calculations, run system commands, create and edit fi...
- [Computer use tool](computer-use-tool.md): Claude can interact with computer environments through the computer use tool, which provides screenshot capabilities ...
- [Content moderation](content-moderation.md): Content moderation is a critical aspect of maintaining a safe, respectful, and productive environment in digital appl...
- [Context editing](context-editing.md): Automatically manage conversation context as it grows with context editing.
- [Context windows](context-windows.md): The "context window" refers to the entirety of the amount of text a language model can look back on and reference whe...
- [Corporate clairvoyant](corporate-clairvoyant.md): Extract insights, identify risks, and distill key information from long corporate reports into a single memo.
- [Cosmic Keystrokes](cosmic-keystrokes.md): Generate an interactive speed typing game in a single HTML file, featuring side-scrolling gameplay and Tailwind CSS s...
- [Tracking Costs and Usage](cost-tracking.md): Understand and track token usage for billing in the Claude Agent SDK
- [Create Invite](create-invite.md): paths:
- [Create Skill Version](create-skill-version.md): paths:
- [Create Skill](create-skill.md): paths:
- [Add Workspace Member](create-workspace-member.md): paths:
- [Create Workspace](create-workspace.md): paths:
- [Create a Message Batch](creating-message-batches.md): Send a batch of Message creation requests.
- [CSV converter](csv-converter.md): Convert data from various formats (JSON, XML, etc.) into properly formatted CSV files.
- [Culinary creator](culinary-creator.md): Suggest recipe ideas based on the user's available ingredients and dietary preferences.
- [Custom Tools](custom-tools.md): Build and integrate custom tools to extend Claude Agent SDK functionality
- [Customer support agent](customer-support-chat.md): This guide walks through how to leverage Claude's advanced conversational capabilities to handle customer inquiries i...
- [Data organizer](data-organizer.md): Turn unstructured text into bespoke JSON tables.
- [Define your success criteria](define-success.md): Building a successful LLM-based application starts with clearly defining your success criteria. How will you know whe...
- [Delete Invite](delete-invite.md): paths:
- [Delete Skill Version](delete-skill-version.md): paths:
- [Delete Skill](delete-skill.md): paths:
- [Delete Workspace Member](delete-workspace-member.md): paths:
- [Delete a Message Batch](deleting-message-batches.md): Delete a Message Batch.
- [Create strong empirical evaluations](develop-tests.md): After defining your success criteria, the next step is designing evaluations to measure LLM performance against those...
- [Direction decoder](direction-decoder.md): Transform natural language into step-by-step directions.
- [Dream interpreter](dream-interpreter.md): Offer interpretations and insights into the symbolism of the user's dreams.
- [Efficiency estimator](efficiency-estimator.md): Calculate the time complexity of functions and algorithms.
- [Email extractor](email-extractor.md): Extract email addresses from a document into a JSON-formatted list.
- [Embeddings](embeddings.md): Text embeddings are numerical representations of text that enable measuring semantic similarity. This guide introduce...
- [Emoji encoder](emoji-encoder.md): Convert plain text into fun and expressive emoji messages.
- [Errors](errors.md): Our API follows a predictable HTTP error code format:
- [Ethical dilemma navigator](ethical-dilemma-navigator.md): Help the user think through complex ethical dilemmas and provide different perspectives.
- [Using the Evaluation Tool](eval-tool.md): The [Claude Console](https://console.anthropic.com/dashboard) features an **Evaluation tool** that allows you to test...
- [Excel formula expert](excel-formula-expert.md): Create Excel formulas based on user-described calculations or data manipulations.
- [Extended thinking tips](extended-thinking-tips.md): export const TryInConsoleButton = ({userPrompt, systemPrompt, maxTokens, thinkingBudgetTokens, buttonVariant = "prima...
- [Building with extended thinking](extended-thinking.md): export const TryInConsoleButton = ({userPrompt, systemPrompt, maxTokens, thinkingBudgetTokens, buttonVariant = "prima...
- [Download a File](files-content.md): Download the contents of a Claude generated file
- [Create a File](files-create.md): Upload a file
- [Delete a File](files-delete.md): Make a file inaccessible through the API
- [List Files](files-list.md): List files within a workspace
- [Get File Metadata](files-metadata.md): paths:
- [Files API](files.md): The Files API lets you upload and manage files to use with the Claude API without re-uploading content with each requ...
- [Fine-grained tool streaming](fine-grained-tool-streaming.md): Tool use now supports fine-grained [streaming](/en/docs/build-with-claude/streaming) for parameter values. This allow...
- [Function fabricator](function-fabricator.md): Create Python functions based on detailed specifications.
- [Futuristic fashion advisor](futuristic-fashion-advisor.md): Suggest avant-garde fashion trends and styles for the user's specific preferences.
- [Get API Key](get-api-key.md): paths:
- [Get Claude Code Usage Report](get-claude-code-usage-report.md): Retrieve daily aggregated usage metrics for Claude Code users.
- [Get Cost Report](get-cost-report.md): paths:
- [Get Invite](get-invite.md): paths:
- [Get Organization Info](get-me.md): paths:
- [Get Usage Report for the Messages API](get-messages-usage-report.md): paths:
- [Get Skill Version](get-skill-version.md): paths:
- [Get Skill](get-skill.md): paths:
- [Get started with Claude](get-started.md): Make your first API call to Claude and build a simple web search assistant
- [Get User](get-user.md): paths:
- [Get Workspace Member](get-workspace-member.md): paths:
- [Get Workspace](get-workspace.md): paths:
- [Git gud](git-gud.md): Generate appropriate Git commands based on user-described version control actions.
- [Glossary](glossary.md): These concepts are not unique to Anthropic’s language models, but we present a brief summary of key terms below.
- [Google apps scripter](google-apps-scripter.md): Generate Google Apps scripts to complete tasks based on user requirements.
- [Grading guru](grading-guru.md): Compare and evaluate the quality of written texts based on user-defined criteria and standards.
- [Grammar genie](grammar-genie.md): Transform grammatically incorrect sentences into proper English.
- [Hal the humorous helper](hal-the-humorous-helper.md): Chat with a knowledgeable AI that has a sarcastic side.
- [Streaming refusals](handle-streaming-refusals.md): Starting with Claude 4 models, streaming responses from Claude's API return **`stop_reason`:`"refusal"`** when strea...
- [null](home.md): export function openSearch() {
- [Hosting the Agent SDK](hosting.md): Deploy and host Claude Agent SDK in production environments
- [Idiom illuminator](idiom-illuminator.md): Explain the meaning and origin of common idioms and proverbs.
- [How to implement tool use](implement-tool-use.md): We recommend using the latest Claude Sonnet (4.5) or Claude Opus (4.1) model for complex tools and ambiguous queries;...
- [Increase output consistency (JSON mode)](increase-consistency.md): **For guaranteed JSON schema conformance**
- [Interview question crafter](interview-question-crafter.md): Generate questions for interviews.
- [Intro to Claude](intro.md): Claude is a highly performant, trustworthy, and intelligent AI platform built by Anthropic. Claude excels at tasks in...
- [IP addresses](ip-addresses.md): Anthropic services use fixed IP addresses for both inbound and outbound connections. You can use these addresses to c...
- [Keep Claude in character with role prompting and prefilling](keep-claude-in-character.md): This guide provides actionable tips to keep Claude in character, even during long, complex interactions.
- [LaTeX legend](latex-legend.md): Write LaTeX documents, generating code for mathematical equations, tables, and more.
- [Legal summarization](legal-summarization.md): This guide walks through how to leverage Claude's advanced natural language processing capabilities to efficiently su...
- [Lesson planner](lesson-planner.md): Craft in depth lesson plans on any subject.
- [Prompt Library](library.md): Explore optimized prompts for a breadth of business and personal tasks.
- [List API Keys](list-api-keys.md): paths:
- [List Invites](list-invites.md): paths:
- [List Skill Versions](list-skill-versions.md): paths:
- [List Skills](list-skills.md): paths:
- [List Users](list-users.md): paths:
- [List Workspace Members](list-workspace-members.md): paths:
- [List Workspaces](list-workspaces.md): paths:
- [List Message Batches](listing-message-batches.md): List all Message Batches within a Workspace. Most recently created batches are returned first.
- [Long context prompting tips](long-context-tips.md): While these tips apply broadly to all Claude models, you can find prompting tips specific to extended thinking models...
- [Master moderator](master-moderator.md): Evaluate user inputs for potential harmful or illegal content.
- [MCP connector](mcp-connector.md): Claude's Model Context Protocol (MCP) connector feature enables you to connect to remote MCP servers directly from th...
- [Model Context Protocol (MCP)](mcp.md): MCP is an open protocol that standardizes how applications provide context to LLMs.
- [Meeting scribe](meeting-scribe.md): Distill meetings into concise summaries including discussion topics, key takeaways, and action items.
- [Memo maestro](memo-maestro.md): Compose comprehensive company memos based on key points.
- [Memory tool](memory-tool.md): The memory tool enables Claude to store and retrieve information across conversations through a memory file directory...
- [Count Message tokens](messages-count-tokens.md): Count the number of tokens in a Message.
- [Messages](messages.md): Send a structured list of input messages with text and/or image content, and the model will generate the next message...
- [Migrating from Text Completions](migrating-from-text-completions-to-messages.md): Migrating from Text Completions to Messages
- [Migrating to Claude 4.5](migrating-to-claude-4.md): This guide covers two key migration paths to Claude 4.5 models:
- [Mindfulness mentor](mindfulness-mentor.md): Guide the user through mindfulness exercises and techniques for stress reduction.
- [Mitigate jailbreaks and prompt injections](mitigate-jailbreaks.md): Jailbreaking and prompt injections occur when users craft prompts to exploit model vulnerabilities, aiming to generat...
- [Model deprecations](model-deprecations.md): As we launch safer and more capable models, we regularly retire older models. Applications relying on Anthropic model...
- [List Models](models-list.md): List available models.
- [Get a Model](models.md): Get a specific model.
- [Modifying system prompts](modifying-system-prompts.md): Learn how to customize Claude's behavior by modifying system prompts using three approaches - output styles, systemPr...
- [Mood colorizer](mood-colorizer.md): Transform text descriptions of moods into corresponding HEX codes.
- [Motivational muse](motivational-muse.md): Provide personalized motivational messages and affirmations based on user input.
- [Multilingual support](multilingual-support.md): Claude excels at tasks across multiple languages, maintaining strong cross-lingual performance relative to English.
- [Use examples (multishot prompting) to guide Claude's behavior](multishot-prompting.md): While these tips apply broadly to all Claude models, you can find prompting tips specific to extended thinking models...
- [Neologism creator](neologism-creator.md): Invent new words and provide their definitions based on user-provided concepts or ideas.
- [OpenAI SDK compatibility](openai-sdk.md): Anthropic provides a compatibility layer that enables you to use the OpenAI SDK to test the Claude API. With a few co...
- [null](overview.md): Model cards
- [PDF support](pdf-support.md): Process PDFs with Claude. Extract text, analyze charts, and understand visual content from your documents.
- [Handling Permissions](permissions.md): Control tool usage and permissions in the Claude Agent SDK
- [Perspectives ponderer](perspectives-ponderer.md): Weigh the pros and cons of a user-provided topic.
- [Philosophical musings](philosophical-musings.md): Engage in deep philosophical discussions and thought experiments.
- [PII purifier](pii-purifier.md): Automatically detect and remove personally identifiable information (PII) from text documents.
- [Plugins in the SDK](plugins.md): Load custom plugins to extend Claude Code with commands, agents, skills, and hooks through the Agent SDK
- [Polyglot superpowers](polyglot-superpowers.md): Translate text from any language into any language.
- [Portmanteau poet](portmanteau-poet.md): Blend two words together to create a new, meaningful portmanteau.
- [Prefill Claude's response for greater output control](prefill-claudes-response.md): While these tips apply broadly to all Claude models, you can find prompting tips specific to extended thinking models...
- [Pricing](pricing.md): Learn about Anthropic's pricing structure for models and features
- [Product naming pro](product-naming-pro.md): Create catchy product names from descriptions and keywords.
- [Prompt caching](prompt-caching.md): Prompt caching is a powerful feature that optimizes your API usage by allowing resuming from specific prefixes in you...
- [Automatically generate first draft prompt templates](prompt-generator.md): Our prompt generator is compatible with all Claude models, including those with extended thinking capabilities. For p...
- [Use our prompt improver to optimize your prompts](prompt-improver.md): Our prompt improver is compatible with all Claude models, including those with extended thinking capabilities. For pr...
- [Use prompt templates and variables](prompt-templates-and-variables.md): When deploying an LLM-based application with Claude, your API calls will typically consist of two types of content:
- [Generate a prompt](prompt-tools-generate.md): Generate a well-written prompt
- [Improve a prompt](prompt-tools-improve.md): Create a new-and-improved prompt guided by feedback
- [Templatize a prompt](prompt-tools-templatize.md): Templatize a prompt by indentifying and extracting variables
- [Prose polisher](prose-polisher.md): Refine and improve written content with advanced copyediting techniques and suggestions.
- [Pun-dit](pun-dit.md): Generate clever puns and wordplay based on any given topic.
- [Python bug buster](python-bug-buster.md): Detect and fix bugs in Python code.
- [Agent SDK reference - Python](python.md): Complete API reference for the Python Agent SDK, including all functions, types, and classes.
- [Get started with Agent Skills in the API](quickstart.md): Learn how to use Agent Skills to create documents with the Claude API in under 10 minutes.
- [Rate limits](rate-limits.md): To mitigate misuse and manage capacity on our API, we have implemented limits on how much an organization can use the...
- [Reduce hallucinations](reduce-hallucinations.md): Even the most advanced language models, like Claude, can sometimes generate text that is factually incorrect or incon...
- [Reducing latency](reduce-latency.md): Latency refers to the time it takes for the model to process a prompt and and generate an output. Latency can be infl...
- [Reduce prompt leak](reduce-prompt-leak.md): Prompt leaks can expose sensitive information that you expect to be "hidden" in your prompt. While no method is foolp...
- [Remote MCP servers](remote-mcp-servers.md): export const MCPServersTable = ({platform = "all"}) => {
- [Remove User](remove-user.md): paths:
- [Retrieve Message Batch Results](retrieving-message-batch-results.md): Streams the results of a Message Batch as a`.jsonl`file.
- [Retrieve a Message Batch](retrieving-message-batches.md): This endpoint is idempotent and can be used to poll for Message Batch completion. To access the results of a Message ...
- [Review classifier](review-classifier.md): Categorize feedback into pre-specified tags and categorizations.
- [Riddle me this](riddle-me-this.md): Generate riddles and guide the user to the solutions.
- [Sci-fi scenario simulator](sci-fi-scenario-simulator.md): Discuss with the user various science fiction scenarios and associated challenges and considerations.
- [Search results](search-results.md): Enable natural citations for RAG applications by providing search results with source attribution
- [Second-grade simplifier](second-grade-simplifier.md): Make complex text easy for young learners to understand.
- [Service tiers](service-tiers.md): Different tiers of service allow you to balance availability, performance, and predictable costs based on your applic...
- [Session Management](sessions.md): Understanding how the Claude Agent SDK handles sessions and session resumption
- [Simile savant](simile-savant.md): Generate similes from basic descriptions.
- [Using Agent Skills with the API](skills-guide.md): Learn how to use Agent Skills to extend Claude's capabilities through the API.
- [Agent Skills in the SDK](skills.md): Extend Claude with specialized capabilities using Agent Skills in the Claude Agent SDK
- [Slash Commands in the SDK](slash-commands.md): Learn how to use slash commands to control Claude Code sessions through the SDK
- [Socratic sage](socratic-sage.md): Engage in Socratic style conversation over a user-given topic.
- [Spreadsheet sorcerer](spreadsheet-sorcerer.md): Generate CSV spreadsheets with various types of data.
- [SQL sorcerer](sql-sorcerer.md): Transform everyday language into SQL queries.
- [Storytelling sidekick](storytelling-sidekick.md): Collaboratively create engaging stories with the user, offering plot twists and character development.
- [Streaming Input](streaming-vs-single-mode.md): Understanding the two input modes for Claude Agent SDK and when to use each
- [Streaming Messages](streaming.md): When creating a Message, you can set`"stream": true`to incrementally stream the response using [server-sent events]...
- [Structured outputs](structured-outputs.md): Structured outputs constrain Claude's responses to follow a specific schema, ensuring valid, parseable output for dow...
- [Subagents in the SDK](subagents.md): Working with subagents in the Claude Agent SDK
- [Supported regions](supported-regions.md): Here are the countries, regions, and territories we can currently support access from:
- [System Prompts](system-prompts.md): See updates to the core system prompts on [Claude.ai](https://www.claude.ai) and the Claude [iOS](http://anthropic.co...
- [Text editor tool](text-editor-tool.md): Claude can use an Anthropic-defined text editor tool to view and modify text files, helping you debug, fix, and impro...
- [Ticket routing](ticket-routing.md): This guide walks through how to harness Claude's advanced natural language understanding capabilities to classify cus...
- [Time travel consultant](time-travel-consultant.md): Help the user navigate hypothetical time travel scenarios and their implications.
- [Todo Lists](todo-tracking.md): Track and display todos using the Claude Agent SDK for organized task management
- [Token counting](token-counting.md): Token counting enables you to determine the number of tokens in a message before sending it to Claude, helping you ma...
- [Token-efficient tool use](token-efficient-tool-use.md): Starting with Claude Sonnet 3.7, Claude is capable of calling tools in a token-efficient manner. Requests save an ave...
- [Tongue twister](tongue-twister.md): Create challenging tongue twisters.
- [Trivia generator](trivia-generator.md): Generate trivia questions on a wide range of topics and provide hints when needed.
- [Tweet tone detector](tweet-tone-detector.md): Detect the tone and sentiment behind tweets.
- [Agent SDK reference - TypeScript](typescript.md): Complete API reference for the TypeScript Agent SDK, including all functions, types, and interfaces.
- [Update API Keys](update-api-key.md): paths:
- [Update User](update-user.md): paths:
- [Update Workspace Member](update-workspace-member.md): paths:
- [Update Workspace](update-workspace.md): paths:
- [Usage and Cost API](usage-cost-api.md): Programmatically access your organization's API usage and cost data with the Usage & Cost Admin API.
- [Use XML tags to structure your prompts](use-xml-tags.md): While these tips apply broadly to all Claude models, you can find prompting tips specific to extended thinking models...
- [Versions](versioning.md): When making API requests, you must send an`anthropic-version`request header. For example,`anthropic-version: 2023-...
- [Vision](vision.md): The Claude 3 and 4 families of models comes with new vision capabilities that allow Claude to understand and analyze ...
- [VR fitness innovator](vr-fitness-innovator.md): Brainstorm creative ideas for virtual reality fitness games.
- [Web fetch tool](web-fetch-tool.md): The web fetch tool allows Claude to retrieve full content from specified web pages and PDF documents.
- [Web search tool](web-search-tool.md): The web search tool gives Claude direct access to real-time web content, allowing it to answer questions with up-to-d...
- [Website wizard](website-wizard.md): Create one-page websites based on user specifications.
- [What's new in Claude 4.5](whats-new-claude-4-5.md): Claude 4.5 introduces two models designed for different use cases:
- [Using the Messages API](working-with-messages.md): Practical patterns and examples for using the Messages API effectively