《Cursor Docs》-Subagents
Subagents are specialized AI assistants that Cursor's agent can delegate tasks to. Each subagent operates in its own context window, handles specific types of work, and returns its result to the parent agent. Use subagents to break down complex tasks, do work in parallel, and preserve context in the main conversation.
Read More《Cursor Docs》-Agent Skills
Agent Skills is an open standard for extending AI agents with specialized capabilities. Skills package domain specific knowledge and workflows that agents can use to perform specific tasks.
Read More《Cursor Docs》-Security Agents
Security Agents scan your code for security bugs, risky patterns, and vulnerabilities.
Read More《Cursor Docs》-Cursor TypeScript SDK
The @cursor/sdk package lets you call Cursor's agent from your own code. The same agent that runs in the Cursor IDE, CLI, and web app is now scriptable from TypeScript. Run the /sdk skill inside Cursor to get started.
Read More《Cursor Docs》-Cursor Python SDK
The cursor sdk package lets you call Cursor's agent from your own Python code. The same agent that runs in the Cursor IDE, CLI, and web app is scriptable from Python with sync and async clients, typed dataclasses, and ordinary iteration for streams and pages. Run the /sdk skill inside Cursor to get started.
Read More《Cursor Docs》-SDK Changelog
The latest features, improvements, and fixes shipping to the Cursor SDK, covering @cursor/sdk on npm and cursor sdk on PyPI.
Read More《Cursor Docs》-Cursor SDK Bridge
The SDK Bridge is a small local server that embeds the TypeScript SDK and exposes the same agent surface over a stable Connect/protobuf protocol. Use it to script Cursor agents from languages without a first party SDK.
Read More《Cursor Docs》-Rules
Rules provide system level instructions to Agent. They bundle prompts, scripts, and more together, making it easy to manage and share workflows across your team.
Read More《Cursor Docs》-Third Party Hooks
Cursor supports loading hooks from third party tools, enabling compatibility with existing hook configurations from other AI coding assistants.
Read More《Cursor Docs》-sandbox.json reference
Configure sandbox behavior with a sandbox.json file to control network access, filesystem paths, and more.
Read More《Cursor Docs》-Plugins reference
Reference documentation for building, structuring, and submitting Cursor plugins. Plugins package rules, skills, agents, commands, MCP servers, and hooks into distributable bundles that work in the Cursor IDE.
Read More《Cursor Docs》-permissions.json reference
Use permissions.json to configure MCP tool and terminal command allowlists and to steer the Auto review mode classifier so tools run without approval.
Read More《Cursor Docs》-Keyboard Shortcuts
Overview of keyboard shortcuts in Cursor. See all keyboard shortcuts by pressing Cmd R then Cmd S or by opening command palette Cmd Shift P and searching for Keyboard Shortcuts.
Read More《Cursor Docs》-Ignore file
Cursor reads and indexes your project's codebase to power its features. Control which directories and files Cursor can access using a .cursorignore file in your root directory.
Read More《Cursor Docs》-Deeplinks
Deeplinks allow you to share prompts, commands, and rules with others, enabling collaboration and knowledge sharing across teams and communities.
Read More《Cursor Docs》-Plugins
Plugins package rules, skills, agents, commands, MCP servers, and hooks into distributable bundles.
Read More《Cursor Docs》-Settings
Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.
Read More《Cursor Docs》-Pull requests
Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.
Read More《Cursor Docs》-Mirror a GitHub repository
Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.
Read More《Cursor Docs》-Integrations
Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.
Read More《Cursor Docs》-Clone, Push & Pull
Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.
Read More《Cursor Docs》-Create an Origin repository
Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.
Read More《Cursor Docs》-Codebase settings
Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.
Read More《Cursor Docs》-Pull request commands
Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.
Read More《Cursor Docs》-Commands
Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.
Read More《Cursor Docs》-Install the CLI
Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.
Read More《Cursor Docs》-Browse & Search
Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.
Read More《Cursor Docs》-Origin
Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.
Read More《Cursor Docs》-Kimi K3
Kimi K3 is Moonshot AI's latest open weight model. It sits above Kimi K2.7 Code for long running agent work: thorough upfront reasoning, strong one shot persistence, and the highest CursorBench score we've measured from an open model.
Read More《Cursor Docs》-Kimi K2 7 Code
We recommend using Kimi K3 for new work. K2.7 Code remains available as a lower cost Moonshot option.
Read More《Cursor Docs》-Grok 4 6
Grok 4.6 is a frontier model from Cursor and SpaceXAI for complex coding and knowledge work. It builds on Grok 4.5 with improved instruction following and long horizon agentic work.
Read More《Cursor Docs》-Grok 4 5
We recommend using Grok 4.6 for improved instruction following and long horizon agentic work. Grok 4.5 remains available.
Read More《Cursor Docs》-Gpt 5 Mini
We recommend using GPT 5.3 Codex for most tasks. It's more capable at a similar price point.
Read More《Cursor Docs》-Gpt 5 Fast
We recommend using GPT 5.3 Codex. It's faster than previous generations and more cost effective.
Read More《Cursor Docs》-Gpt 5 Codex
We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.
Read More《Cursor Docs》-Gpt 5 6 Terra
GPT 5.6 Terra is the mid tier model in OpenAI's GPT 5.6 family. It sits between Sol and Luna on intelligence and price, making it a strong pick for everyday agentic coding when you want more capability than Luna without Sol's cost.
Read More《Cursor Docs》-Gpt 5 6 Sol
GPT 5.6 Sol is OpenAI's flagship GPT 5.6 model in Cursor. It is the strongest of the Sol, Terra, and Luna family: persistent on long running agent work, fast enough for interactive sessions, and notably concise in how it communicates.
Read More《Cursor Docs》-Gpt 5 6 Luna
GPT 5.6 Luna is the smallest and lowest cost model in OpenAI's GPT 5.6 family. Use it for high volume, latency sensitive, or cost sensitive agent work where Sol or Terra would be more than you need.
Read More《Cursor Docs》-Gpt 5 5
GPT 5.5 is OpenAI's most intelligent model in Cursor. It keeps momentum on long running work and stays on task for significantly longer before stopping early, which matters most in complex, multi step coding sessions.
Read More《Cursor Docs》-Gpt 5 4 Nano
GPT 5.4 Nano is the smallest and fastest model in the GPT 5.4 family. At $0.20 per million input tokens, it's built for high volume workloads where speed and cost matter more than peak reasoning. Reach for it when you need quick classification, extraction, ranking, or lightweight coding support.
Read More《Cursor Docs》-Gpt 5 4 Mini
GPT 5.4 Mini brings good performance to cost sensitive workflows.
Read More《Cursor Docs》-Gpt 5 4
GPT 5.4 is OpenAI's most capable model to date. It outperforms all other models on our internal benchmarks. For cost sensitive workflows where raw intelligence matters less, GPT 5.3 Codex remains a strong option at a lower price point.
Read More《Cursor Docs》-Gpt 5 3 Codex
GPT 5.3 Codex is OpenAI's flagship coding model. It leads Terminal Bench by a wide margin and performs on par with Opus 4.6 on our internal benchmarks, at roughly one third the price. Much faster than previous GPT generations. A strong default for most coding tasks.
Read More《Cursor Docs》-Gpt 5 2 Codex
We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.
Read More《Cursor Docs》-Gpt 5 2
GPT 5.2 has access to all agent tools when used with Cursor including:
Read More《Cursor Docs》-Gpt 5 1 Codex Mini
We recommend using GPT 5.3 Codex for most tasks. It's more capable at a similar price point.
Read More《Cursor Docs》-Gpt 5 1 Codex Max
We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.
Read More《Cursor Docs》-Gpt 5 1 Codex
We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.
Read More《Cursor Docs》-Gpt 5
We recommend using GPT 5.3 Codex. It scores higher on benchmarks, is faster, and more cost effective.
Read More《Cursor Docs》-Glm 5 2
GLM 5.2 has access to all agent tools when used with Cursor including:
Read More《Cursor Docs》-Gemini 3 Pro Image Preview
This model is used exclusively for the image generation tool inside Cursor. It is not selectable as a chat model.
Read More《Cursor Docs》-Gemini 3 Pro
We recommend using Gemini 3.1 Pro. It's the latest version with stronger multimodal capabilities and the same pricing.
Read More《Cursor Docs》-Gemini 3 Flash
Gemini 3 Flash is Google's speed optimized model. At $0.50 per million input tokens, it's one of the cheapest options available. Use it for simple coding tasks, quick edits, and executing plans written by a more capable model.
Read More《Cursor Docs》-Gemini 3 7 Flash
Gemini 3.7 Flash is Google's latest speed tier model. It pairs strong agentic coding performance with low per token costs. Use it for high throughput coding tasks that benefit from reasoning and a large context window.
Read More《Cursor Docs》-Gemini 3 6 Flash
We recommend using Gemini 3.7 Flash. It's Google's latest speed tier model with lower input and output prices.
Read More《Cursor Docs》-Gemini 3 5 Flash
We recommend using Gemini 3.7 Flash. It's Google's latest speed tier model with lower input and output prices.
Read More《Cursor Docs》-Gemini 3 1 Pro
Gemini 3.1 Pro is Google's latest model. It processes images alongside code, making it strong for UI/UX work from design mockups. It supports context windows up to 1M tokens.
Read More《Cursor Docs》-Gemini 2 5 Flash
We recommend using Gemini 3.7 Flash. It's Google's latest speed tier model.
Read More《Cursor Docs》-Cursor Composer 2 5
Composer 2.5 is Cursor's own agentic model. It builds on Composer 2 with stronger intelligence on long agentic tasks, better effort calibration, tool selection, intent understanding, and reliability.
Read More《Cursor Docs》-Cursor Composer 1
We strongly recommend using Composer 2.5. It's smarter and includes more usage on individual plans.
Read More《Cursor Docs》-Claude Sonnet 5
Claude Sonnet 5 is Anthropic's latest medium tier model and replaces Sonnet 4.6. It pushes quality close to Opus while keeping Sonnet's lower per token price. It supports thinking mode and context windows up to 1M tokens, making it a strong default for everyday coding when you want frontier reasoning without Opus pricing.
Read More《Cursor Docs》-Claude Opus 5
Claude Opus 5 is Anthropic's latest Opus model and replaces Opus 4.8. It is a step change over Opus 4.8 on agentic coding, professional knowledge work, and long horizon reasoning, and it lands on par with Fable 5 on CursorBench at Opus pricing. We recommend the high thinking variant for the best results.
Read More《Cursor Docs》-Claude Opus 4 8
We recommend using Claude Opus 5. It replaces Opus 4.8 with stronger agentic coding and long horizon reasoning at the same price.
Read More《Cursor Docs》-Claude Opus 4 7 Fast
Fast mode for Claude Opus 4.7 bills at a much higher per token rate than standard Opus 4.7. Use it selectively for time sensitive or critical work where cost is secondary.
Read More《Cursor Docs》-Claude Opus 4 7
We recommend using Claude Opus 5. It is Anthropic's latest Opus release with the same pricing and stronger agentic capabilities.
Read More《Cursor Docs》-Claude Opus 4 6
We recommend using Claude Opus 5. It scores higher on CursorBench, offers stronger autonomous capabilities, and is priced the same.
Read More《Cursor Docs》-Claude Opus 4 5
We recommend using Claude Opus 5. It's the latest Opus with stronger reasoning and code quality.
Read More《Cursor Docs》-Claude Fable 5
Claude Fable 5 is Anthropic's most capable generally available model for autonomous knowledge work and coding. It is a Mythos class model with strong safeguards, built to handle long running, complex, and asynchronous tasks where earlier models needed more frequent check ins.
Read More《Cursor Docs》-Claude 4 Sonnet 1M
We recommend using Claude Sonnet 5, which also supports up to 1M tokens of context.
Read More《Cursor Docs》-Claude 4 Sonnet
We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.
Read More《Cursor Docs》-Claude 4 6 Sonnet
We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.
Read More《Cursor Docs》-Claude 4 5 Sonnet
We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.
Read More《Cursor Docs》-Claude 4 5 Haiku
For stronger results, consider Claude Sonnet 5 or Gemini 3 Flash for a fast, affordable alternative.
Read More《Cursor Docs》-Models & Pricing
Cursor supports frontier models from OpenAI, Anthropic, Google, SpaceXAI, and more. Pro, Pro Plus, and Ultra include two usage pools so you can pick the right balance of intelligence, speed, and cost. Start, our plan for developers in India, covers the Cursor Models pool.
Read More《Cursor Docs》-MCP Install Links
Looking to share MCP servers, rules, and more? Plugins make it easier to bundle and distribute everything in one package. You can publish to the Cursor Marketplace or your team's private marketplace.
Read More《Cursor Docs》-Xcode
Xcode 26.3+ exposes a built in MCP server that gives Cursor direct access to your Xcode projects. Cursor's agent can read and edit files, trigger builds, run tests, capture SwiftUI previews, and search Apple's documentation; all without leaving your editor.
Read More《Cursor Docs》-Slack
With Cursor's integration for Slack, you can use Cloud Agents to work on your tasks directly from Slack by mentioning @cursor with a prompt.
Read More《Cursor Docs》-Notion
Connect Cursor to Notion so you can delegate specs, tasks, and comments to agents. Because the integration is built on the Cursor SDK, every agent uses the same runtime, harness, and models that power Cursor.
Read More《Cursor Docs》-Microsoft Teams
With Cursor's integration for Microsoft Teams, you can use Cloud Agents to work on tasks directly from Microsoft Teams by mentioning @Cursor with a prompt.
Read More《Cursor Docs》-Linear
Use Cloud Agents directly from Linear by delegating issues to Cursor or mentioning @Cursor in comments.
Read More《Cursor Docs》-Jira
With Cursor's integration for Jira, you can use Cloud Agents to work on Jira work items by assigning them to Cursor or mentioning @Cursor in Jira.
Read More《Cursor Docs》-JetBrains
Use Cursor's AI agent in IntelliJ IDEA, PyCharm, WebStorm, and other JetBrains IDEs through the Agent Client Protocol (ACP).
Read More《Cursor Docs》-GitLab
The GitLab integration connects your repositories so you can use features like Cloud Agents and Bugbot.
Read More《Cursor Docs》-GitHub
The Cursor GitHub app connects your repositories so you can use features like Cloud Agents and Bugbot.
Read More《Cursor Docs》-Cursor Blame
Understanding how AI contributed to your codebase helps with review, compliance, and debugging. This page covers how Cursor Blame surfaces AI versus human authorship in git history.
Read More《Cursor Docs》-Bitbucket
Connect Bitbucket Cloud repositories to Cloud Agents and Bugbot. Connect Bitbucket Data Center repositories to Bugbot.
Read More《Cursor Docs》-Azure DevOps
The Azure DevOps integration connects Azure DevOps Services repositories to Cloud Agents and Bugbot.
Read More《Cursor Docs》-Hooks
Hooks let you observe, control, and extend the agent loop using custom scripts. Define hooks in hooks.json files at the project or user level, or install them through plugins from Customize . Hooks are spawned processes that communicate over stdio using JSON in both directions. They run before or after defined stages of the agent loop and can observe, block, or modify behavior.
Read More《Cursor Docs》-Quickstart
This guide gets you from install to your first useful change in Cursor. You'll sign in, ask Cursor to explain your codebase, make a small edit, and review the result.
Read More《Cursor Docs》-Extension API reference
Cursor exposes extension APIs under vscode.cursor for programmatic configuration. Use these APIs from VS Code extensions to register MCP servers and plugin paths without editing config files.
Read More《Cursor Docs》-Run Cursor in your evals
Use the Cursor SDK to run Cursor's agent loop inside your own eval harness. The same agent that powers the Cursor IDE, CLI, and web app is scriptable from TypeScript, so you can score Grok 4.6 (and other models we support) on your benchmarks.
Read More《Cursor Docs》-Security and Privacy Hardening
This page consolidates the security and privacy guidance spread across the Cursor docs into one reference, so teams configuring Cursor can review and apply the right controls without hunting through every page. Each item links to its source doc for the full detail.
Read More《Cursor Docs》-Privacy and Data Governance
Understanding how data flows through Cursor is critical for security reviews and compliance assessments. This documentation explains what data goes where, what guarantees you have, and where that data lives geographically.
Read More《Cursor Docs》-Pooled usage
Pooled usage gives your Enterprise team a shared usage pool instead of fixed per user allocations. Everyone draws from a single committed amount that spans your contract period, so agent usage is available wherever it's needed most.
Read More《Cursor Docs》-Organizations
Organizations are the top level container for Enterprise customers. They sit above teams and give you one place to manage shared identity, administration, and organization wide settings.
Read More《Cursor Docs》-Organization Groups
Organization Groups are org level cohorts in Cursor Enterprise, such as Engineering, Contractors, or Pilot Users. Members can come from any team in your Organization, and a user can belong to many groups at once.
Read More《Cursor Docs》-OpenTelemetry Export Wire Reference
Companion to OpenTelemetry Export. Full wire surface: every metric, log event, attribute, enum, and presence rule.
Read More《Cursor Docs》-OpenTelemetry Export
OpenTelemetry Export streams Cursor usage data for your team to a collector you run. Cursor sends metrics (tokens, tool calls, best effort cost) and logs (API requests, errors, corrections, skills, hooks, plugins, and cloud agent lifecycle events) to one team managed destination. Export runs server side.
Read More《Cursor Docs》-Network Configuration
Cursor needs to communicate with backend services and AI providers. This documentation covers how to configure Cursor to work within your network infrastructure, including proxies, firewalls, and encryption requirements.
Read More《Cursor Docs》-Model and Integration Management
Your team can access multiple AI models and integrate Cursor with various services. This documentation covers how to control which models are available, manage MCP server trust, and set up integrations with tools like Slack, GitHub, and Linear.
Read More《Cursor Docs》-LLM Safety and Controls
AI models can behave unexpectedly. This documentation covers how to control what agents can do, set up safety guardrails, and guide LLM behavior toward desired outcomes.
Read More《Cursor Docs》-Identity and Access Management
Identity and access management controls who can use Cursor in your organization and what they can do. You'll set up authentication, automate user provisioning, and enforce policies through device management.
Read More《Cursor Docs》-Endpoint Security Configuration
Cursor loads JavaScript modules and performs file I/O during startup. Endpoint security software that intercepts file operations or injects into processes can slow startup past internal timeouts, causing features like Agent to fail. This page covers how to configure exclusions so Cursor works alongside your security stack.
Read More《Cursor Docs》-Deployment Patterns
This guide covers how to deploy the Cursor editor and CLI tools to developer machines in your organization. Most organizations deploy both the editor (for daily development work) and the CLI (for automation, CI/CD, and scripting).
Read More《Cursor Docs》-Compliance and Monitoring
Compliance requires visibility into who did what, when, and why. This documentation covers audit logs, AI code tracking, certifications, and how to meet regulatory requirements.
Read More《Cursor Docs》-HIPAA Business Associate Agreements
Cursor supports HIPAA Business Associate Agreements (BAAs) for Enterprise customers.
Read More《Cursor Docs》-Admin Setup Guide
Cursor is designed with enterprise rollouts in mind. On the Cursor Admin Dashboard, you'll find everything you need to manage Cursor usage for your organization.
Read More《Cursor Docs》-Enterprise
Cursor provides enterprise grade security, compliance, and administrative controls for organizations deploying AI assisted development at scale.
Read More《Cursor Docs》-AWS Bedrock
Route AI requests through your AWS Bedrock account instead of Cursor's model providers. This lets your team use existing AWS credits and keep requests within your AWS infrastructure.
Read More《Cursor Docs》-Customize Cursor
Plugins, skills, and MCPs let you customize Cursor for your workflows. The Customize page brings them into one place.
Read More《Cursor Docs》-Cursor Router
Cursor Router is the model routing system behind Auto . Not every request needs frontier level intelligence, so the router sends each request to the model that fits the task: simple requests go to fast, efficient models while complex work goes to the most capable ones.
Read More《Cursor Docs》-Pull Request Page
The Pull Request (PR) page is where you can review a pull request in detail. It brings together the PR summary, code changes, comments, checks, and merge actions in once place so you can move from understanding the change to taking action on it.
Read More《Cursor Docs》-Pull Request Inbox
Use the Pull Request (PR) Inbox to keep track of pull requests that need your attention. Cursor Review groups pull requests into sections based on their current state, and you can create custom sections for your own workflow.
Read More《Cursor Docs》-Merge Queue
Merge Queue experience gives your team one place to line up pull requests, keep the default branch green, and land stacks without making every author babysit rebases.
Read More《Cursor Docs》-Parameters
This reference documents every command and flag available in the Cursor Review CLI (gt).
Read More《Cursor Docs》-Worktrees
The UI native worktrees feature described on this page is only available in the Agents Window. In the IDE, use the Worktree Skills commands below.
Read More《Cursor Docs》-VS Code Migration
Cursor is based upon the VS Code codebase, allowing us to focus on making the best AI powered coding experience while maintaining a familiar editing environment. This makes it easy to migrate your existing VS Code settings to Cursor.
Read More《Cursor Docs》-Cloud Environment Setup
Cloud agents run on isolated Ubuntu machines. Configure the environment so the agent has the same repos, tools, dependencies, secrets, and network access a developer would use.
Read More《Cursor Docs》-Cloud Agents settings
Workspace admins can configure Cloud Agents from the Cloud Agents dashboard.
Read More《Cursor Docs》-Governed Cloud Agents for private code and internal services
Coding agents that work on private code have to clear a specific bar: source that can't leave your network, a compliance perimeter to honor, access and network policy you control, and a setup that fits the infrastructure you already run.
Read More《Cursor Docs》-Secrets & Network
Cloud Agents are available in Privacy Mode. We never train on your code and only retain code for running the agent. Learn more about Privacy mode.
Read More《Cursor Docs》-Security overview
This page explains how Cloud Agents are built and secured. It walks through what happens when an agent runs, how access is granted, where the code and data live, how they're isolated and encrypted, and what controls you have over each stage. It answers the questions that come up when a team evaluates Cloud Agents against its security requirements.
Read More《Cursor Docs》-Private Connectivity
Cursor supports private network connectivity for Enterprise teams that need Cursor to work with systems that are not reachable from the public internet. This includes self hosted GitHub Enterprise Server, GitLab Enterprise, Bitbucket Data Center, Artifactory, Nexus, private source control APIs, and webhook traffic from those systems back to Cursor.
Read More《Cursor Docs》-Cursor for iOS
Cursor for iOS is in beta. Features may change before general availability.
Read More《Cursor Docs》-Agent metadata
Agent metadata is in preview and subject to change, including breaking changes.
Read More《Cursor Docs》-OIDC tokens
Cloud Agents can mint short lived OIDC JWTs from inside the VM and use them to assume cloud roles or call internal services without storing long lived credentials in Secrets.
Read More《Cursor Docs》-Cloud Agent Builds
Builds prepare your Cloud Agent environment in the background. Each agent starts from a pre built machine with your repositories, tools, and dependencies ready.
Read More《Cursor Docs》-Best Practices
Use these recommendations to get more reliable Cloud Agent runs.
Read More《Cursor Docs》-Automations
Cursor Automations run cloud agents in the background, either on a schedule or in response to events from GitHub, GitLab, Slack, webhooks, Linear, and more.
Read More《Cursor Docs》-Webhooks
When you create an agent with a webhook URL, Cursor will send HTTP POST requests to notify you about status changes. Currently, only statusChange events are supported, specifically when an agent encounters an ERROR or FINISHED state.
Read More《Cursor Docs》-Cloud Agents API
The Cloud Agents API v1 is in public beta. APIs may change before general availability.
Read More《Cursor Docs》-Cloud Agents
Cloud agents use the same agent fundamentals but run in isolated VMs in the cloud with full development environments instead of on your local machine. The development environment is similar to the setup on your laptop: cloned repos, installed dependencies, secrets, startup commands, and network access.
Read More《Cursor Docs》-Using Agent in CLI
The CLI supports the same modes as the editor. Switch modes using slash commands or the mode flag.
Read More《Cursor Docs》-Shell Mode
Shell Mode runs shell commands directly from the CLI without leaving your conversation. Use it for quick, non interactive commands with safety checks and output displayed in the conversation.
Read More《Cursor Docs》-Terminal setup
Configure your terminal for the best Cursor CLI experience. This guide covers keybindings for multi line input, Vim mode, and theme synchronization.
Read More《Cursor Docs》-Slash commands
Command Description /model [filter] Select a model. Press Tab to edit. /run everything [on\ off\ status] Toggle Run Everything or show its status. /auto run is an alias. /plan [prompt] Switch to Plan mode, show the current plan, or submit a prompt in Plan mode /ask Toggle Ask mode for read only questions /debug [prompt] Toggle Debug mode or submit a prompt in Debug mode /goal [objective] Give the agent a long lived objective to work towards until it's fully complete. Rolling out. /logs Show the debug log path and copy it to the clipboard /update Update Cursor Agent to the latest version /max mode Toggle Max Mode on legacy request based plans /rename <name Rename the current chat session /clear Start a new chat session. /new, /new chat, and /newchat are aliases. /resume Open recent chats and resume one /fork Fork the current chat into a new session /summarize Summarize the conversation to reduce context. /compress is an alias. /rewind Jump back to a previous message /vim Toggle Vim keys /line numbers Toggle line numbers in code blocks /show thinking Toggle thinking block display /status indicators Toggle terminal title status indicators /shell [command] Enter Shell Mode. /sh and /run are aliases. /about Show CLI version, system, and account info. Also copies it to the clipboard. /setup terminal Configure terminal newline keybindings. See Terminal setup. /help [command] Show help. Use /help <command for command details. /feedback <message Share feedback with the team /open Open the repository's Git root in Cursor. /cursor is an alias. /copy request id Copy the last request ID to the clipboard /copy conversation id Copy the current conversation ID to the clipboard /logout Sign out from Cursor /quit Exit /exit Exit /mcp [list\ list tools] [identifier] Manage MCP servers and list tools for a server /plugin [subcommand] Manage plugins and marketplaces /config Configure CLI settings interactively /copy Copy a previous user message to the clipboard /sandbox Configure sandbo
Read More《Cursor Docs》-Permissions
Configure what the agent is allowed to do using permission tokens in your CLI configuration. Permissions are set in /.cursor/cli config.json (global) or <project /.cursor/cli.json (project specific).
Read More《Cursor Docs》-Output format
The Cursor Agent CLI provides multiple output formats with the output format option when combined with print. These formats include structured formats for programmatic use (json, stream json) and a simplified text format for human readable output (text).
Read More《Cursor Docs》-Authentication
Cursor CLI supports two authentication methods: browser based login (recommended) and API keys.
Read More《Cursor Docs》-Cursor CLI
Cursor CLI lets you interact with AI agents directly from your terminal to write, review, and modify code. Whether you prefer an interactive terminal interface or print automation for scripts and CI pipelines, the CLI provides powerful coding assistance right where you work.
Read More《Cursor Docs》-MCP
The Cursor CLI supports Model Context Protocol (MCP) servers, allowing you to connect external tools and data sources to agent. MCP in the CLI uses the same configuration as the editor any MCP servers you've configured will work with both.
Read More《Cursor Docs》-Using Headless CLI
Use Cursor CLI in scripts and automation workflows for code analysis, generation, and refactoring tasks.
Read More《Cursor Docs》-GitHub Actions
Use Cursor CLI in GitHub Actions and other CI/CD systems to automate development tasks.
Read More《Cursor Docs》-CLI Changelog
The latest features, improvements, and fixes shipping to Cursor CLI. Run agent version to check your installed version, and agent update to upgrade in place.
Read More《Cursor Docs》-ACP
Cursor CLI supports ACP (Agent Client Protocol) for advanced integrations. You can run agent acp and connect a custom client over stdio using JSON RPC.
Read More《Cursor Docs》-Bugbot
Bugbot reviews pull requests and identifies bugs, security issues, and code quality problems.
Read More《Cursor Docs》-PR Routing & Approval
PR Routing & Approval routes pull requests to the right reviewers and can approve low risk changes.
Read More《Cursor Docs》-Cursor APIs Overview
Cursor provides multiple APIs for programmatic access to your team's data, AI powered coding agents, and analytics.
Read More《Cursor Docs》-Terminal
Cursor runs shell commands directly in your terminal. Your Run Mode controls when commands run, when Cursor asks, and when terminal commands enter the sandbox.
Read More《Cursor Docs》-Canvases
Canvases let Cursor create interactive artifacts that render next to the chat. Instead of scrolling through a long markdown table or code block, you get a standalone view, laid out with sections, stats, and tables, that you can reopen, edit, and iterate on.
Read More《Cursor Docs》-Browser
Agent can control a web browser to test applications, audit accessibility, convert designs into code, and more. With full access to console logs and network traffic, Agent can debug issues and automate comprehensive testing workflows.
Read More《Cursor Docs》-Run Modes
Run Modes control how the Cursor agent runs tool calls, and when Cursor interrupts you for approval.
Read More《Cursor Docs》-Agent Security
AI can behave unexpectedly due to prompt injection, hallucinations, and other issues. We protect users with guardrails that limit what agents can do. By default, sensitive actions require your manual approval. This document explains our guardrails and what they mean for you.
Read More《Cursor Docs》-Prompting agents
Direct Agent with text prompts in the chat input. You can attach context, images, and voice, and switch models at any point.
Read More《Cursor Docs》-Plan Mode
Plan Mode creates detailed implementation plans before writing any code. Agent researches your codebase, asks clarifying questions, and generates a reviewable plan you can edit before building.
Read More《Cursor Docs》-Cursor Agent
Agent is Cursor's assistant that can complete complex coding tasks independently, run terminal commands, and edit code. Access in sidepane with Cmd+I.
Read More《Cursor Docs》-Design Mode
Design Mode lets you direct agents with visual prompts. From the browser in the Agents Window, you can click an element, draw on the page, or describe a change by voice. Cursor captures the context it needs and edits the code while you move on to the next change.
Read More《Cursor Docs》-Debug Mode
Debug Mode helps you find root causes and fix tricky bugs that are hard to reproduce or understand. Instead of immediately writing code, the agent generates hypotheses, adds log statements, and uses runtime information to pinpoint the exact issue before making a targeted fix.
Read More《Cursor Docs》-Agents Window
The Agents Window is Cursor's agent first interface. It provides a unified workspace to build with agents across repos and environments, including local, cloud, remote SSH, and more. It combines the power of parallel agents with the depth and control of a development environment.
Read More《Cursor Docs》-Agent Review
Agent Review runs a dedicated code review on your local changes from inside Cursor.
Read More《Cursor Docs》-SSO
SAML 2.0 SSO is available at no additional cost on Teams and Enterprise plans. Use your existing identity provider (IdP) to authenticate team members without separate Cursor accounts.
Read More《Cursor Docs》-SCIM
SCIM 2.0 provisioning automatically manages your team members and directory groups through your identity provider. Available on Enterprise plans with SSO enabled, contact sales to get access.
Read More《Cursor Docs》-Team Pricing
There are two business plans: Teams and Enterprise (Custom). Teams offers two types of seats: Standard ($40/user/mo) and Premium (5x usage at $120/user/mo).
Read More《Cursor Docs》-Members, Roles, and Seat Types
Cursor Teams use roles for permissions and seat types for usage limits.
Read More《Cursor Docs》-Dashboard
The dashboard lets you access billing, set up usage based pricing, and manage your Team.
Read More《Cursor Docs》-Analytics API
The Analytics API provides comprehensive insights into your team's Cursor usage, including AI assisted coding metrics, active users, model usage, and more.
Read More《Cursor Docs》-Usage Analytics
Usage Analytics are available for Team and Enterprise customers.
Read More《Cursor Docs》-AI Code Tracking API
The AI Code Tracking API lets you track AI generated code contributions across your team's repositories, including per commit AI usage and granular accepted AI changes.
Read More《Cursor Docs》-Admin API
The Admin API lets you programmatically access your team's data, including member information, usage metrics, spending details, and model access.
Read More《Cursor Docs》-Regions
Some of our model providers have location based restrictions, which means certain models may not be available in your region. When this happens, those models won’t appear in Cursor, but you’ll still be able to use all other available models without interruption.
Read More《Cursor Docs》-Request-Based Pricing (Legacy)
This page covers Cursor's legacy request based pricing model that was used before the transition to usage based pricing.
Read More《Cursor Docs》-Organization API
The Organization API lets you perform actions that apply across teams linked to an organization, such as moving users between those teams, reporting on pooled usage across teams, managing organization groups, and reading or updating model access. It uses an Organization API key and the same HTTP patterns as the team Admin API.
Read More《Cursor Docs》-Cyber Safeguards
Cyber Safeguards settings are available on the Enterprise plan and are configured per Organization Group at Organization → Groups . These are not billing groups or SCIM directory groups.
Read More《Cursor Docs》-Billing Groups
Billing groups allow Enterprise admins to understand and manage spend across groups of users. This functionality is useful for reporting, internal chargebacks, and budgeting.
Read More《Cursor Docs》-Cursor Documentation
Cursor is a coding agent for building ambitious software. Use it to understand your codebase, plan and build features, fix bugs, review changes, and work with the tools you already use.
Read MoreWrite Your First Agent Skill Using the Official template-skill
Template-skill is the starting skeleton of Skill in Anthropic's official repository anthropics/skills, with only one SKILL.md file containing name and description placeholders in the directory. Agent Skills became an open standard in December 2025, and the same file can be enabled by scanning directories in Cursor, Claude Code, and Codex CLI respectively. This article follows the official template and agentskills.io specifications to explain the frontmatter fields, directory structure, installation paths of each tool, and how to fill in the template to create the first triggerable Skill.
Read MoreAdding Analytics: Let AI Agent Integrate PostHog into Web Applications According to Standard Procedures
# 官方正式翻译结果： adding-analytics is a SKILL.md in the awesome-cursor-skills repository, which formalizes the process of integrating PostHog into web applications: identify the framework, install posthog-js/posthog-node, initialize the Provider, supplement pageview tracking for SPAs, manage keys using environment variables, and add custom events, Feature Flags and session replays as needed. This article cross-verifies based on the original Skill content and official documents of PostHog, Cursor, Claude Code and Codex, explains the installation directory, reproducible examples, as well as the differences between variable names, React package paths, pageview default behavior, input desensitization and other aspects compared with current official documents.
Read MoreDatabase Design: Let AI Agents Design Table Relationships, Indexes, Constraints and ORM According to Specifications
# SKILL.md for Database Design (Included in awesome-cursor-skills) ## Overview This is a database modeling skill collected in awesome-cursor-skills, which covers entity identification, table relationships, constraints, indexes, and Prisma/Drizzle configuration. ## Six-step Workflow Verified against the official original text, the workflow is as follows: 1. **Entity Identification**: Extract core business entities from requirements 2. **Define Entity Attributes**: Clarify each entity's fields and data types 3. **Establish Table Relationships**: Map one-to-one, one-to-many, and many-to-many associations between entities 4. **Set Up Constraints**: Add NOT NULL, unique, primary key, foreign key and other constraints to ensure data integrity 5. **Design Indexes**: Create appropriate indexes to optimize query performance 6. **Generate ORM Configuration**: Write standardized Prisma or Drizzle schema files based on the designed database structure ## PostgreSQL Example & Installation Method ### Example Code ```sql -- Sample PostgreSQL table creation script CREATE TABLE users ( id SERIAL PRIMARY KEY, username VARCHAR(50) UNIQUE NOT NULL, email VARCHAR(255) UNIQUE NOT NULL, created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP ); CREATE TABLE posts ( id SERIAL PRIMARY KEY, title VARCHAR(255) NOT NULL, content TEXT, author_id INTEGER NOT NULL, created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP, FOREIGN KEY (author_id) REFERENCES users(id) ON DELETE CASCADE ); -- Sample index CREATE INDEX idx_posts_author_id ON posts(author_id); ``` ### Prisma Configuration Example ```prisma generator client { provider = "prisma-client-js" } datasource db { provider = "postgresql" url = env("DATABASE_URL") } model User { id Int @id @default(autoincrement()) username String @unique @db.VarChar(50) email String @unique @db.VarChar(255) createdAt DateTime @default(now()) @db.Timestamptz() posts Post[] } model Post { id Int @id @default(autoincrement()) title String @db.VarChar(255) content String? authorId Int author User @relation(fields: [authorId], references: [id], onDelete: Cascade) createdAt DateTime @default(now()) @db.Timestamptz() } ``` ### Drizzle Configuration Example ```typescript import { pgTable, serial, varchar, text, integer, timestamp, unique } from 'drizzle-orm/pg-core'; export const users = pgTable('users', { id: serial('id').primaryKey(), username: varchar('username', { length: 50 }).notNull(), email: varchar('email', { length: 255 }).notNull(), createdAt: timestamp('created_at').defaultNow().notNull() }, (table) => { return { usernameUnique: unique().on(table.username), emailUnique: unique().on(table.email), } }); export const posts = pgTable('posts', { id: serial('id').primaryKey(), title: varchar('title', { length: 255 }).notNull(), content: text('content'), authorId: integer('author_id').notNull(), createdAt: timestamp('created_at').defaultNow().notNull() }, (table) => { return { authorRef: foreignKey({ columns: [table.authorId], foreignColumns: [users.id] }).onDelete('cascade'), authorIndex: index('idx_posts_author_id').on(table.authorId) } }); ``` ## Supplementary Role of AI Programming This skill makes up for the shortcomings of AI programming in schema design: 1. Provides standardized, step-bysted operating specifications to avoid AI from generating incomplete or non-compliant database schemas 2. Combines business requirements with technical implementation, helping AI transform abstract business logic into a practical, production-ready database structure 3. Standardizes the connection between logical design and physical implementation, ensuring the consistency of schema design from demand analysis to ORM code generation ## Usage Restrictions 1. **PostgreSQL Dialect Limitation**: The current skill takes PostgreSQL as the only demonstration database, and may need to be adjusted when adapting to MySQL, SQL Server and other relational databases 2. **ORM Scope Limitation**: Only covers Prisma and Drizzle two mainstream Node.js ORM frameworks, and is not applicable to ORM tools in other programming languages or non-mainstream Node.js ORMs 3. **Basic Database Design Only**: Focuses on conventional relational database modeling, and does not cover special scenarios such as distributed databases, columnar storage databases, and non-relational databases 4. Requires manual verification: AI generated content still needs developers to check for business matching, performance bottlenecks and compliance issues in actual production environments
Read More# Adding Stripe: Enabling AI Agents to Integrate Stripe Payments via Standard Procedures
# Adding Stripe is a community Agent Skill in awesome-cursor-skills, compiling Stripe Checkout, subscription Webhooks and Customer Portal into a 7-step checklist. Based on the original SKILL.md text and cross-referenced with the documentation for Stripe Checkout, Webhooks, Billing Portal and Cursor Skills, this article explains what problem it solves, how to install it in Cursor / Claude Code / Codex, as well as usage notes such as signature verification, Customer ID and API version.
Read MoreUse recording-browser-flow-as-test: Walk through the process in the browser and automatically generate Playwright tests
# Introduction to `recording-browser-flow-as-test` in spencerpauly/awesome-cursor-skills: This tool allows users to walk through user workflows step-by-step using Cursor's built-in browser, record accessibility tree information via `browser_snapshot`, and then generate Playwright tests that use stable locators such as `getByRole` and `getByLabel`. This article verifies the installation commands, prerequisites, recording steps, assertion and hardening suggestions, as well as inapplicable scenarios such as 2FA and verification codes.
Read More# Accessibility Auditing: Performing Accessibility Audits Using Cursor Browser's ARIA Tree
### Translated Abstract: Introducing accessibility-auditing in spencerpauly/awesome-cursor-skills: Leveraging Cursor's built-in browser tools including `browser_navigate`, `browser_snapshot` and `browser_press`, it conducts audits on the page ARIA tree covering missing labels, semantic HTML, keyboard navigation order, ARIA misuses and color contrast issues. It generates a categorized report with Critical/Warnings/Passed statuses and can directly modify the source code. The document also explains the installation methods via `.cursor/skills` directory or `npx skills add` command, as well as applicable scenarios and compliance review considerations.
Read MoreVisual QA Testing in Cursor: Capture Screenshots, Console Logs and Network Requests in One Go
visual-qa-testing is an Agent Skill in the community repository awesome-cursor-skills, which guides Cursor Agent to use the built-in browser (cursor-ide-browser) to perform visual QA after modifying the UI: confirm the development service, take page screenshots, check console errors and network requests, and conduct verification after interacting with button forms. Based on SKILL.md and Cursor's official Skills/Browser documentation, this article explains its positioning, installation directory and npx skills installation method, typical calling steps, as well as precautions such as relying on the built-in browser and being an alternative to non-test frameworks.
Read MoreLet Agent fix itself until all tests pass with grinding-until-pass
### 介绍 This article introduces `grinding-until-pass` from spencerpauly/awesome-cursor-skills: It enables the Agent to independently fix issues until tests, builds, or lint checks pass via the `fix→run→check` loop. We verify that the steps follow the official SKILL.md rules, including iterating within 10 times, fixing one thing at a time, and prohibiting deleting tests or suppressing errors. We also explain the installation methods using `npx skills` or copying the skill to `.cursor/skills`, along with target command examples and advanced usage of Cursor Hooks. This skill is suitable for scenarios such as large-scale refactoring, dependency upgrades, and clearing failed builds after merging branches; manual intervention is required for slow tests or when design changes are needed.
Read More# Standard Conventional Commits Written with the `writing-commit-messages` Skill
### Translated English Abstract: This article introduces the `writing-commit-messages` section in spencerpauly/awesome-cursor-skills: how to use Agent Skill to constrain commit messages to follow Conventional Commits specifications (including type prefixes, scopes, body content, and BREAKING CHANGE sections). It verifies the rules in SKILL.md, good and bad examples, commit granularity requirements, as well as the installation methods for Cursor skills: manually installing to the `.cursor/skills/` directory, and using `npx skills add` to install to both Cursor and Claude Code. This guide is suitable for teams that need standardized collaboration and automated changelog generation.
Read MoreUsing kubernetes-deploying Skill: Let AI Agents Generate Kubernetes Deployment Manifests According to Specifications
### 翻译结果： `kubernetes-deploying` from spencerpauly/awesome-cursor-skills is an Agent Skill designed for Kubernetes deployments. It encapsulates best practices including Deployment, Service, Ingress, ConfigMap, Secret, health checks, release strategies and HPA into the SKILL.md file, enabling AI programming tools such as Cursor, Claude Code and Codex to generate standardized manifests and work with common kubectl commands. This article introduces its capabilities, installation and activation methods, typical usage scenarios and usage notes based on official documentation.
Read MoreHand Over Production Incident Response Process to AI Agent via Incident-response Skill
# Incident Response in spencerpauly/awesome-cursor-skills This project packages the SEV grading, stopgap mitigation, internal and external communication, and 48-hour blameless post-incident review workflow for production incidents into an installable `SKILL.md`. It has verified official workflows and post-incident review templates, and provides enabling methods via `npx skills` or by copying to `.cursor/skills/` for use in Cursor, Claude Code, and Codex CLI, making it suitable for SRE/DevOps on-duty scenarios.
Read MoreParallelly familiarize yourself with unfamiliar codebase and generate onboarding documentation using codebase-onboarding
### 翻译结果： This article introduces the `codebase-onboarding` skill in spencerpauly/awesome-cursor-skills: it launches 5 read-only explore sub-agents in parallel to research architecture, data models, APIs, authentication and deployment respectively, then synthesizes the results into an ONBOARDING.md. Based on the official SKILL.md and Cursor Skills documentation, it explains the installation directory, the `npx skills` installation method, the calling mode of `/codebase-onboarding`, as well as applicable scenarios and review precautions.
Read More# Figma-Create-Design-System-Rules: Develop Project-Specific Design System Rules for Agents
This is an introduction to `figma-create-design-system-rules` in the openai/skills curated catalog: On the premise of connecting Figma MCP, it analyzes the codebase and generates project-level design system rules, constraining component paths, Design Tokens, styling solutions and the Figma-to-code workflow, and writes them into `CLAUDE.md`, `AGENTS.md` or `.cursor/rules/figma-design-system.mdc` respectively, to alleviate problems such as random use of spacing, hard-coded colors, and repeated creation of components when AI implements UI. The article verifies the installation method, five-step workflow and precautions.
Read More# Slack-GIF-Creator: Let AI Help You Make GIFs Compliant with Slack Specifications
Slack-gif-creator is an Agent Skill in Anthropic's official Skills repository. It encapsulates constraints such as GIF dimensions, frame rate and color specifically for the Slack scenario, and provides a GIFBuilder assembly tool, validators for verification, as well as guides on easing and animation concepts. This article introduces its positioning, core capabilities, as well as installation methods and typical usage in AI programming tools such as Cursor and Claude Code, helping developers quickly produce GIFs that can be uploaded to Slack using natural language.
Read MoreDetailed Explanation of canvas-design Skill: Incorporating Design Philosophy into AI to Generate PNG/PDF Static Visual Works
Canvas-design is a creative Agent Skill in Anthropic's official Skills repository. It adopts a two-step workflow of "first formulating design philosophy, then expressing it on the canvas, and finally conducting secondary refinement", and outputs .md manifesto and .png/.pdf visual finished products. This article verifies its core capabilities, canvas-fonts font resources, installation methods in Cursor and Claude Code, as well as typical usages such as posters and brand visuals and copyright considerations based on the official SKILL.md.
Read More# brand-guidelines: Let AI Agent Automatically Apply Anthropic Official Brand Specifications
`brand-guidelines` is an official Anthropic Skills example that writes brand colors (#141413, #d97757, etc.) and Poppins/Lora font rules into `SKILL.md`, enabling Agents to automatically align with visual specifications when generating PPTs, documents, and HTML. Based on verification against the official `SKILL.md` and the repository README, this article introduces its positioning, color palette details, installation methods for Cursor/Claude Code/Claude.ai, typical prompts, as well as reusable patterns and precautions for building enterprise self-built design specification Skills.
Read More### 正式译法（符合技术文章标题规范）： # Algorithmic Art: Integrate p5.js Algorithmic Art into AI Programming Assistants with Agent Skill
### Official Creative Skill: algorithmic-art from Anthropic This skill generates interactive algorithmic art based on p5.js and seed randomization. After verifying against the official SKILL.md document, this article explains its two-stage workflow of "algorithmic philosophy + HTML finished product", the constraints of the viewer.html template, as well as the installation methods and typical prompt words in Cursor, Claude Code and Claude.ai. It is suitable for developers who want to quickly create generative art or learn creative Agent Skills.
Read More# unit-test-generator: Let AI Agent Automatically Generate Unit Tests According to Specifications
The unit-test-generator is a community example Skill in the JackyST0/awesome-agent-skills repository. It standardizes the workflow of "identifying code, analyzing boundaries, selecting frameworks, and generating test cases" via SKILL.md, and supports multiple programming languages including Python, JavaScript/TypeScript, Java, Go, Rust, etc., as well as testing frameworks such as pytest, Jest, JUnit, etc. This article introduces its positioning, core capabilities, installation methods on platforms like Cursor/Codex, official divide function examples, applicable scenarios such as test case supplementation and team specification implementation, as well as usage notes.
Read MoreCode Review: Equip AI Programming Assistants with "Standardized Code Review Workflows"
code-review is an official sample Skill built into the awesome-agent-skills repository. It defines a unified code review process for AI programming tools such as Cursor, Claude Code, and Copilot via SKILL.md. It covers five types of checks including syntax, logic, security, performance and style, and outputs a standard report containing problem lists, improvement suggestions and three scores. This article introduces its origin, core capabilities, one-click/manual installation methods, typical usage and applicable scenarios, to help developers standardize AI-assisted code review quickly.
Read More### 正式译法（适配技术文档场景）： Setting up CI: Let AI Agents Help You Build GitHub Actions CI/CD Pipelines
# setup-ci from awesome-cursor-skills: A beginner-friendly DevOps skill for GitHub Actions This skill detects Node.js, Python, Go and other projects via the SKILL.md specification, then generates a `ci.yml` workflow that includes linting, testing, type checking and optional deployment. It emphasizes the use of `npm ci`, dependency caching and secret security best practices. This article covers installation (deploying to `.cursor/skills/`), typical usage and precautions, and is ideal for quickly setting up CI/CD for new projects.
Read MoreFour Perspectives on One PR: Practical Combat of Parallel Code Review Skills
### 翻译版本1（正式技术文档风格）： `parallel-code-review` is a Cursor-Native Skill in the `awesome-cursor-skills` repository. It leverages the Task tool to launch four read-only explore sub-agents simultaneously to review the same code diff across four dimensions: security, performance, correctness, and readability, before the main agent deduplicates and consolidates the results into a hierarchical report. After verifying against the official `SKILL.md`, this article introduces the installation methods (via `.cursor/skills/` or `npx skills`), four-step workflow (scope the changes, conduct parallel review, synthesize the report, and optional repair), as well as applicable scenarios and limitations. ### 翻译版本2（更贴合开源社区表述习惯）： `parallel-code-review` is a Cursor-native skill hosted in the `awesome-cursor-skills` repo. It uses the Task tool to spin up four read-only explore sub-agents at once to audit the same code diff from four perspectives: security, performance, correctness, and readability. The main agent will then deduplicate and merge the feedback into a tiered report. This article first cross-checks with the official `SKILL.md`, then walks through the installation steps (either via `.cursor/skills/` directory or `npx skills`), the four-stage workflow (select the changes to review, run parallel audits, compile the final report, and apply fixes optionally), plus the applicable use cases and current constraints of the skill.
Read MoreExtracting Skills from Repeated Patterns: Detailed Explanation of the Meta-skill building-skills-from-patterns
### 正式翻译（符合技术文档语境）： `building-skills-from-patterns` is a meta-skill in the `awesome-cursor-skills` repository. It teaches the Cursor Agent to recognize recurring multi-step workflows and save them as `SKILL.md` files under the `.cursor/skills/` directory. This article introduces its trigger conditions, four-step workflow, division of labor with Rules and Hooks, as well as installation methods and typical use cases, helping developers advance from "repeatedly dictating workflows" to "building reusable Skills on their own".
Read More# Systematic Debugging: Integrate Structured Debugging Methodology into Skill to Enable AI Troubleshooting Without Blind Guesses
### 正式翻译： The `systematic-debugging` repository comes from `awesome-cursor-skills`. It will write the five-step debugging process of reproduction, isolation, hypothesis, verification and repair into `SKILL.md`, covering git bisect, binary search and minimal reproduction. This article introduces its origin, core capabilities, installation methods in AI programming tools such as Cursor, as well as typical usages such as automatic triggering and explicit invocation via `/systematic-debugging`, helping developers constrain Agents to troubleshoot based on evidence rather than randomly modifying code.
Read More# 翻译结果： Architecture Decision Records: Documenting Technical Decisions with Agent Skill
### Translation: Let me introduce the *architecture-decision-records* skill included in awesome-cursor-skills: it teaches AI Agents to document technical decisions in accordance with ADR specifications, covering their backgrounds, alternative options and justifications. The skill covers when to write ADRs, template structures, a six-step workflow, installation methods and typical prompt examples, helping teams turn architectural governance from verbal agreements into retrievable decision logs.
Read MoreAdding E2E Tests: Building Playwright End-to-End Tests from Scratch with Agent Skill
### 正式翻译： # Adding E2E Tests from awesome-cursor-skills: Teach AI Agents to Build Playwright E2E Testing from Scratch This tutorial covers end-to-end setup with Playwright: installing dependencies, configuring `playwright.config.ts`, writing smoke tests and Page Objects, supplementing npm scripts and `.gitignore`, integrating GitHub Actions CI, and emphasizes best practices for `data-testid` and Playwright Codegen. It explains the positioning of this skill, its differences from webapp-testing, installation methods for Cursor/Claude Code, and a seven-step implementation workflow, making it suitable for frontend and full-stack projects that have not yet adopted E2E testing.
Read MoreAdding Auth: Enabling AI Agents to Integrate with Auth.js Authentication via Standard Procedures
*adding-auth* has been included in awesome-cursor-skills. The integration of Auth.js v5 with Next.js App Router has been organized into an 8-step workflow: dependency installation, setting up AUTH_SECRET, auth.ts configuration, OAuth setup, Route Handler implementation, login UI and route protection, and optional database Adapter. Verified against the official SKILL.md and Auth.js documentation, this article introduces the installation method and typical usage, suitable for web developers who need to quickly integrate OAuth and sessions.
Read More1. Auditing-Security: Systematically Audit Code Repositories with Agent Skill
### Introduction to awesome-cursor-skills Selected Skill auditing-security: Write review steps including OWASP Top 10, key leakage, injection and dependency vulnerabilities into SKILL.md for agents such as Cursor to conduct systematic audits of business code according to the 7-step checklist. The content covers installation methods, prompt examples, and the complementary relationship with Skill supply chain security tools such as SkillScan.
Read More# cloudflare-deploy: Let AI Agents Deploy Applications to Cloudflare Edge Network
`cloudflare-deploy` is an Agent Skill under the OpenAI openai/skills curated directory. It guides AI Agents to complete full-stack deployments on Cloudflare, including Workers, Pages, and services like KV/D1/R2, via decision trees and reference documents. This article verifies the official SKILL.md, introduces its differences from vercel-deploy, the installation methods for Codex/Cursor, the Wrangler authentication process and typical deployment commands, which is suitable for developers who need edge Serverless and multi-cloud deployments.
Read More### 版本1（面向技术用户，贴合原文语境）： `vercel-deploy`: Let AI Agents Deploy Projects to Vercel with One Click ### 版本2（更地道的技术文档译法）： `vercel-deploy`: Enable AI Agents to One-Click Deploy Projects to Vercel
Vercel-deploy is a Vercel deployment Skill in the OpenAI Skills curated directory, which guides AI Agents to one-click deploy applications to Vercel. It uses preview deployment by default; prioritizes Vercel CLI, and automatically downgrades to the deploy.sh script when not logged in, and can return previewUrl and claimUrl without prior account configuration. It supports automatic detection of frameworks such as Next.js, Nuxt, Astro, etc., and is applicable to tools such as Cursor, Codex CLI, and Claude Code.
Read Moregh-fix-ci: Use GitHub CLI to let AI help you debug failed CI checks on PRs
If your CI fails before a PR is merged, do you have to switch back and forth between the Actions page and your terminal to check logs? The officially curated OpenAI skill `gh-fix-ci` is specifically designed for GitHub Actions failure troubleshooting: it pulls PR checks and run logs via the GitHub CLI, uses bundled scripts to automatically extract error snippets, provides a repair plan first, and waits for approval before you modify the code. This article introduces the positioning of this skill, the usage of `inspect_pr_checks.py`, as well as the installation and enabling methods in tools such as Codex and Cursor.
Read More# doc-coauthoring: Use a three-stage structured workflow to let Agents help you write clear technical specifications and decision documents
Doc-coauthoring is a documentation co-creation Skill in Anthropic's official Skills repository, targeting structured writing scenarios such as technical specifications, decision documents, RFCs, and PRDs. Instead of generating a full article at one time, it guides the Agent through three phases: context collection, section-by-section polishing, and reader testing. It first supplements background information through meta-questions and information dumping, then conducts brainstorming, screening, drafting and iterative revision by chapter, and finally uses a context-free Claude to simulate reader questions to identify blind spots in the document. This article introduces its core capabilities, installation methods in Cursor and Claude Code, as well as typical interaction examples and applicable boundaries for writing decision docs.
Read Moreinternal-comms: Let AI Write Internal Communication Documents According to Company Format
Anthropic's official Skill internal-comms packages internal communication templates such as 3P weekly reports, all-staff newsletters, FAQs, and incident reports into the SKILL.md instruction set. This article introduces its workflow for loading examples/ guidelines by category, the installation method in Cursor / Claude Code, as well as typical prompt usages and customization suggestions.
Read More# web-artifacts-builder: Using React Stack to Enable Agents to Deliver Deployable Frontend HTML Artifacts
Anthropic’s official Skill `web-artifacts-builder` builds complex multi-component web artifacts using React 18, TypeScript, Vite, Tailwind and shadcn/ui. The `init-artifact.sh` initializes the scaffold and pre-installs over 40 components, while `bundle-artifact.sh` packages the project into a self-contained `bundle.html`. This article covers the installation and activation methods for tools like Claude Code and Cursor, a four-step workflow, and applicable scenarios, helping AI Agents deliver web pages following modern front-end engineering practices.
Read MoreTheme Factory: One-click skin changing for slides, documents and landing pages with Agent Skill
### 翻译结果： This article introduces Anthropic's official theme-factory Skill: it includes 10 preset themes (color schemes and fonts), which can apply unified styles to slides, documents, reports and HTML landing pages, and also supports custom themes. Based on the official SKILL.md and repository structure, this article explains the installation methods (CLI, manual copying, Claude Code plugin), standard skin-changing process and typical prompt examples, which is suitable for developers who need to unify the style in AI design workflows.
Read MoreAnthropic PDF Skill: Enabling AI Programming Assistants to Truly Handle All Scenarios of PDF Processing
This PDF is an Agent Skill maintained officially by Anthropic, which follows the Agent Skills open standard and can be used in Cursor, Claude Code and Codex. It covers high-frequency office automation scenarios including PDF reading and extraction, merging and splitting, rotating and watermarking, form filling, encryption and decryption, OCR and image extraction, etc., and includes tool selection guides for pypdf, pdfplumber, reportlab, qpdf, pdftotext and other tools. This article introduces the positioning, core capabilities, installation methods in Claude Code/Cursor/Codex, as well as official code examples and usage notes of the Skill.
Read MoreSkill: Let AI Truly Write Deliverable Word Documents
DOCX is a Word document Agent Skill publicly released by Anthropic in the anthropics/skills repository, which supports Claude's file creation and editing capabilities. This article introduces its positioning, three technical paths of creation/reading/editing, revision annotations and bundled scripts, installation methods in Cursor and Claude Code, as well as precautions such as docx-js and unzip/XML editing, to help developers truly deliver AI-generated content into deliverable .docx files.
Read More# webapp-testing: Let AI Agents Autonomously Validate Local Web Applications with Playwright
Anthropic's official webapp-testing Skill wraps Playwright browser automation into reusable, agent-friendly test workflows. It supports starting local dev servers, taking screenshots to inspect DOM, and capturing console logs, and validates dynamic single-page applications following a "inspect first, then operate" pattern. This article introduces its core capabilities, installation methods in Cursor and Claude Code, as well as the multi-server management with `with_server.py` and typical Playwright script examples, to help developers enable AI to independently run UI regression tests after modifying front-end code.
Read More# MCP-Builder: Official Anthropic Skill to Walk You Through Building High-Quality MCP Servers
MCP-builder is an Agent Skill in Anthropic's official Skills repository, specifically designed to guide developers in creating high-quality MCP servers. Based on the official SKILL.md and reference documents, this article introduces its four-stage workflow (research and planning, implementation, testing, evaluation), dual-stack support for TypeScript/Python, installation and activation methods (Cursor, Claude Code, etc.), typical prompt examples and usage precautions, to help developers systematically encapsulate external APIs into LLM-callable MCP tools.
Read MoreCursor integrates Gmail/Drive/Calendar: Directly read and write Google Workspace within the IDE Agent
On August 3, 2026, Cursor officially released its Google Workspace plugin, allowing coding Agents to access Gmail, Drive and Calendar within the IDE via Google's remote MCP server. This article sorts out the three major plugin capabilities, OAuth installation path, typical scenarios, as well as permissions and security precautions during the preview period, based on the official Changelog, Marketplace and Google developer documentation.
Read MoreThe Two AI Coding Powerhouses in 2026: How Claude Code and Cursor Will Divide Labor
In 2026, a new consensus has formed in the developer community: Claude Code (terminal Agent + Claude Agent SDK) and Cursor (AI IDE) are often used in combination rather than being an either-or choice. Based on official documentation from Anthropic and Cursor, as well as public reviews from Faros.ai, FutureProofing.dev and other sources, this paper compares the differences between the two tools in terms of MCP integration, subagents orchestration, multi-model routing, Bugbot review and token efficiency, proposes a practical division of labor scheme such as "Cursor for daily coding, Claude Code for cross-file refactoring and CI automation", and explains that Claude Code can coexist as an extension of Cursor.
Read MoreViral GitHub Project Ponytail: Lets AI Agents Write Code Like the "Laziest Senior Engineer"
Ponytail is an Agent Skill open-sourced around June 2026, which suppresses AI over-engineering through a seven-level YAGNI decision ladder. In the agentic benchmark built on the FastAPI+React template, the official report shows approximately 54% less code reduction, 22% fewer tokens, 20% lower costs, and 100% pass rate for security items. It is compatible with over 14 hosts including Claude Code, Cursor, Copilot and others. In early August 2026, it still ranked high on the daily list of findarepo with about 93,000 stars, and Hacker News was abuzz with the pain point of "AI writing too much code". This article introduces its principles, installation, commands and community controversies, helping developers decide whether to adopt it.
Read MoreCursor 3 Multi-Agent Architecture: How Planner/Worker Hierarchy Reduces Coding Costs by 15 Times
Cursor 3's upgraded Agent Swarm stratifies frontier model Planner with low-cost Workers: in a closed-book test of rewriting a database from scratch in Rust using only the SQLite manual, all four official configurations achieved 100% pass rate on sqllogictest. The total cost of Opus 4.8 + Composer 2.5 is approximately $1,339, which is about 7.9 times lower than the single-model GPT-5.5 cost of around $10,565 in controlled comparisons; the Worker layer cost can be reduced from $9,373 to $411. This article outlines the context separation principle, the self-developed VCS coordination mechanism, differences in cost calibers, and practical caveats.
Read More$60 Billion Acquisition of Cursor: Will SpaceX/xAI Reshape the Landscape of AI Programming Tools?
On June 16, 2026, SpaceX announced a $60 billion all-stock acquisition of Anysphere, the parent company of Cursor, with the deal expected to close in Q3 2026. Based on SEC filings and public reports, this article sorts out the transaction terms, the synergies of Colossus computing power, the conjectured product division of labor between Grok Build and Cursor, the impact on the competitive landscape of Claude Code and Copilot, and provides countermeasures and suggestions for individual and enterprise developers.
Read MoreCursor Multi-Agent Swarm Rebuilds SQLite for $1339: Planner/Worker Hierarchy Is the Economics of Agents
In July 2026, Cursor released the Agent Swarm research: relying solely on 835 pages of SQLite documentation, without source code or network access, the multi-agent swarm rebuilt SQLite in Rust and passed all sqllogictest tests. The total cost of the hybrid solution planned by Opus 4.8 plus executed by Composer 2.5 is approximately $1,339, while the cost of the single-model GPT-5.5 solution is about $10,565. This article sorts out the Planner/Worker layered architecture, the new harness coordination mechanism, experimental data and the open-source minisqlite product, and analyzes the cost advantage of the multi-agent approach of "using strong models for planning and weak models for execution" as well as its enlightenment to engineering practice.
Read MoreCursor 3 Multi-Agent Architecture: Planner/Worker Division Reduces Costs by Up to 15 Times
In July 2026, Cursor unveiled its upgraded Agent Swarm: the cutting-edge Planner model splits tasks and formulates plans, while the low-cost Composer 2.5 Worker is responsible for execution. In a closed benchmark where it replicated a database from scratch using only the SQLite manual, all configurations of the new architecture achieved a 100% pass rate in sqllogictest. The total cost of the Opus+Composer combination was approximately $1,339, nearly 15 times lower than the roughly $10,565 cost of a single GPT-5.5 model; the Opus configuration’s code volume was reduced by about 85% compared to the old Swarm. This article outlines the tree-shaped division of labor, self-developed VCS, failure mode governance and model economics, and notes that while this result represents a Cursor self-developed experiment, caution is still needed for its deployment in production.
Read More