Automates websites with Skyvern's AI browser agent to fill forms, extract data, download files, log in and run multi-step workflows through SDKs, REST, MCP or a CLI.
$ npx skills add Skyvern-AI/skyvern --skill skyvern -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Skyvern-AI/skyvern skyvern --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Skyvern-AI/skyvern.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs .claude/skills/skyvern && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "skyvern" agent skill from https://github.com/Skyvern-AI/skyvern/tree/main/docs into .claude/skills/skyvern/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skyvern", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Skyvern-AI/skyvern/tree/main/docsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Skyvern-AI/skyvern --skill skyvern -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Skyvern-AI/skyvern skyvern --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Skyvern-AI/skyvern.git skills-src && mkdir -p .agents/skills && cp -r skills-src/docs .agents/skills/skyvern && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skyvern" agent skill from https://github.com/Skyvern-AI/skyvern/tree/main/docs into .agents/skills/skyvern/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skyvern", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Skyvern-AI/skyvern --skill skyvern -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Skyvern-AI/skyvern skyvern --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Skyvern-AI/skyvern.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/docs .cursor/skills/skyvern && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "skyvern" agent skill from https://github.com/Skyvern-AI/skyvern/tree/main/docs into .cursor/skills/skyvern/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skyvern", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Skyvern-AI/skyvern.git --path docs--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Skyvern-AI/skyvern --skill skyvern -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Skyvern-AI/skyvern skyvern --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Skyvern-AI/skyvern.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/docs .gemini/skills/skyvern && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "skyvern" agent skill from https://github.com/Skyvern-AI/skyvern/tree/main/docs into .gemini/skills/skyvern/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skyvern", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Skyvern-AI/skyvern skyvernInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Skyvern-AI/skyvern --skill skyvern -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Skyvern-AI/skyvern.git skills-src && mkdir -p .github/skills && cp -r skills-src/docs .github/skills/skyvern && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "skyvern" agent skill from https://github.com/Skyvern-AI/skyvern/tree/main/docs into .github/skills/skyvern/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skyvern", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Skyvern-AI/skyvern --skill skyvern -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Skyvern-AI/skyvern skyvern --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Skyvern-AI/skyvern.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/docs .opencode/skills/skyvern && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "skyvern" agent skill from https://github.com/Skyvern-AI/skyvern/tree/main/docs into .opencode/skills/skyvern/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skyvern", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skyvernAutomates websites with Skyvern's AI browser agent to fill forms, extract data, download files, log in and run multi-step workflows through SDKs, REST, MCP or a CLI.
Skyvern drives a browser with language models and computer vision, so it can work on sites it has never seen. A single task takes a natural-language prompt and a starting URL, with optional inputs such as a JSON schema for structured output and a proxy country code for geo-routing. The same capability is reachable through a Python SDK, a TypeScript SDK, a REST API, an MCP server and a CLI.
For longer jobs, workflows chain blocks for navigation, actions, extraction, loops, login, file download and parsing, upload, email, webhooks, validation, waiting and code into reusable automations. Typical uses are filling forms, scraping prices or table rows, downloading invoices or reports from portals, and signing in to sites before acting. It needs a Skyvern Cloud API key or a self-hosted instance; the Python SDK requires Python 3.11 or newer and the TypeScript SDK Node.js 18 or newer.
Read from SKILL.md and the folder at commit f5f3f28. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
curlclaudepipFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
news.ycombinator.comapi.skyvern.comAlso links to:
skyvern.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
SKYVERN_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Requires a Skyvern Cloud API key (https://app.skyvern.com) or a self-hosted Skyvern instance. Python SDK requires Python 3.11+. TypeScript SDK requires Node.js 18+. MCP server works with Claude Code, Claude Desktop, Cursor, Windsurf, and VS Code.
From compatibility in the SKILL.md frontmatter.
Skyvern Browser Automation loads about 1.9k tokens when it runs. Until then it costs about 93 tokens; SKILL.md has 496 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from Skyvern-AI/skyvern at commit f5f3f28, republished under its AGPL-3.0 licence (© Skyvern-AI). 496 words, ~1,893 tokens.
.claude/skills/skyvern/SKILL.md (or your agent's skills folder). This skill also uses 512 other files; get the full folder from GitHub.Skyvern automates browser-based workflows using LLMs and computer vision. It navigates websites it has never seen before, filling forms, extracting data, and completing multi-step tasks via a simple API.
SDK reference (all methods, parameters, types in one page): https://skyvern.com/docs/sdk-reference/complete-reference
Execute a one-shot browser automation with natural language instructions.
Inputs:
prompt (required): Natural language description of what to dourl (required): Starting page URLdata_extraction_schema (optional): JSON schema for structured outputproxy_location (optional): Country code for geo-routing (e.g., US, DE)Python SDK:
from skyvern import Skyvern
client = Skyvern(api_key="YOUR_API_KEY")
result = await client.run_task(
prompt="Get the title of the top post on Hacker News",
url="https://news.ycombinator.com",
)TypeScript SDK:
import Skyvern from "@skyvern/client";
const client = new Skyvern({ apiKey: "YOUR_API_KEY" });
const result = await client.runTask({
prompt: "Get the title of the top post on Hacker News",
url: "https://news.ycombinator.com",
});REST API:
curl -X POST https://api.skyvern.com/api/v2/run \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt": "Get the top post title", "url": "https://news.ycombinator.com"}'Define a JSON schema to get consistent, typed output from any page.
result = await client.run_task(
prompt="Extract the top 3 posts",
url="https://news.ycombinator.com",
data_extraction_schema={
"type": "object",
"properties": {
"posts": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {"type": "string"},
"url": {"type": "string"},
"points": {"type": "integer"}
}
}
}
}
},
)Chain task blocks, loops, conditionals, data extraction, and file operations into reusable automations.
Block types: NavigationBlock, ActionBlock, ExtractBlock, LoopBlock, TextPromptBlock, LoginBlock, FileDownloadBlock, FileParseBlock, UploadBlock, EmailBlock, WebhookBlock, ValidationBlock, WaitBlock, CodeBlock, ForLoopBlock, WhileLoopBlock, FileURLParsingBlock, DownloadToS3Block, SendEmailBlock.
Use a ForLoopBlock when the workflow already has a fixed list to iterate over, such as extracted rows, uploaded files, or user-provided URLs. Use a WhileLoopBlock when the workflow should keep repeating until a condition changes, such as paginating while a Next button remains enabled, polling until a status is complete, or retrying while a recoverable page state is visible.
workflow = await client.create_workflow(
title="Invoice Downloader",
blocks=[...], # See workflow blocks reference
)
run = await client.run_workflow(workflow_id=workflow.workflow_id)Persist a live browser across multiple tasks to maintain login state, cookies, and page context.
session = await client.create_session()
# Run multiple tasks on the same browser
await client.run_task(prompt="Log in", url="https://example.com", browser_session_id=session.browser_session_id)
await client.run_task(prompt="Download invoice", url="https://example.com/billing", browser_session_id=session.browser_session_id)
await client.close_session(session.browser_session_id)Store passwords, TOTP/2FA secrets, and credit cards securely. Skyvern auto-fills login forms and generates 2FA codes during automation.
Supported credential providers: Skyvern vault (built-in), Bitwarden, 1Password, Azure Key Vault.
Connect AI assistants directly to browser automation. The MCP server exposes 75+ tools.
Install for Claude Code:
claude mcp add skyvern-cloud -- npx @anthropic-ai/skyvern-mcp@latest --skyvern-api-key YOUR_API_KEYInstall for Cursor/VS Code: Add to MCP config:
{
"mcpServers": {
"skyvern": {
"command": "npx",
"args": ["@anthropic-ai/skyvern-mcp@latest", "--skyvern-api-key", "YOUR_API_KEY"]
}
}
}pip install skyvern
export SKYVERN_API_KEY="YOUR_KEY"
skyvern browser session create # Start a cloud browser
skyvern browser act "Click the login button" # Natural language action
skyvern browser extract '{"title": "string"}' # Extract structured data
skyvern browser screenshot # Capture screenshot
skyvern task run --prompt "..." --url "..." # Run a task
skyvern workflow run --id wf_xxx # Run a workflowmax_steps to control costs.© Skyvern-AI, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 512 other files in docs of Skyvern-AI/skyvern.
Open the folder on GitHubat commit f5f3f28
Skyvern Browser Automation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Skyvern Browser Automation this skillSkyvern-AI/skyvern | 23k | — | ~1.9k | Automated safety check: Pass | AGPL-3.0 | |
| Anti Detect Browserantibrow/anti-detect-browser-skills | 17 | — | ~9.8k | Automated safety check: Warn | MIT | |
| Firecrawl Interact Integrationfirecrawl/firecrawl | 190k | 1 repos | ~731 | Automated safety check: Pass | ISC | |
| Brightdata SDK JSbrightdata/skills | 264 | — | ~3k | Automated safety check: Pass | MIT | |
| Tiered Web Browsing and Scrapingcode-yeongyu/oh-my-openagent | 70k | — | ~2.7k | Automated safety check: Warn | Custom licence | |
| Cloudflare Browser Renderingeinverne/dotfiles | 121 | — | ~4.9k | Automated safety check: Pass | GPL-3.0 |
antibrow/anti-detect-browser-skills
Drive Chromium from standard Playwright APIs with a real-device fingerprint applied in the kernel, one persistent isolated profile per identity, and a per-profile proxy whose exit IP sets timezone…
firecrawl/firecrawl
Guides adding Firecrawl's /interact endpoint to product code for pages that need clicks, forms, pagination or logged-in flows beyond plain scraping.
brightdata/skills
Web data extraction and discovery using the Bright Data JavaScript/TypeScript SDK (@brightdata/sdk).
code-yeongyu/oh-my-openagent
Routes a web request through the cheapest tier that can finish it, from headless extraction with WAF bypass up to a real stealth or signed-in browser, with screenshots as proof.
einverne/dotfiles
Guide for implementing Cloudflare Browser Rendering - a headless browser automation API for screenshots, PDFs, web scraping, and testing.
OpenMinis/MinisSkills
Skill for reading and writing Xiaohongshu (XHS) data using Python + UV.
Skyvern-AI/skyvern
Picks the right Skyvern CLI command for a web task, from quick yes/no checks to reusable multi-page workflows, instead of falling back to plain page fetching.
Skyvern-AI/skyvern
Walks through a Skyvern open-source release bump: update the version, rebuild the Python and TypeScript SDKs with Fern, commit, and open a pull request.
Skyvern-AI/skyvern
Smoke-tests a Skyvern deployment by checking the backend API, frontend rendering, browser session provisioning and workflow execution in sequence.
Skyvern-AI/skyvern
Reads your git diff, writes a handful of happy-path browser smoke tests, runs them with Skyvern or Chrome DevTools MCP and posts screenshot evidence to the PR.
Skyvern-AI/skyvern
Reads your git diff, decides whether the change needs browser QA, API checks or repo tests, runs that validation and reports pass or fail with evidence.
Works with
Automates websites with Skyvern's AI browser agent to fill forms, extract data, download files, log in and run multi-step workflows through SDKs, REST, MCP or a CLI. Skyvern drives a browser with language models and computer vision, so it can work on sites it has never seen. A single task takes a natural-language prompt and a starting URL, with optional inputs such as a JSON schema for structured output and a proxy country code for geo-routing.
Skyvern Browser Automation fits situations like: filling out a web form on a site that has no API; extracting structured data such as prices or table rows from a web page; downloading invoices or statements from a customer portal after logging in; running a multi-step browser workflow that spans several websites.
Run `npx skills add Skyvern-AI/skyvern --skill skyvern -a claude-code`. Or copy the skill folder (docs in Skyvern-AI/skyvern) into .claude/skills/skyvern in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Skyvern-AI/skyvern --skill skyvern -a codex`. Or copy the skill folder (docs in Skyvern-AI/skyvern) into .agents/skills/skyvern in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Skyvern-AI/skyvern --skill skyvern -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skyvern, .gemini/skills/skyvern, .github/skills/skyvern and .opencode/skills/skyvern in your project.
Going by SKILL.md and its folder, Skyvern Browser Automation needs the command-line tools its instructions call (curl, claude and pip) and credentials named SKYVERN_API_KEY. Our summary lists: A Skyvern Cloud API key or a self-hosted Skyvern instance; Python 3.11 or newer for the Python SDK; Node.js 18 or newer for the TypeScript SDK. Compatibility (from SKILL.md): Requires a Skyvern Cloud API key (https://app.skyvern.com) or a self-hosted Skyvern instance. Python SDK requires Python 3.11+. TypeScript SDK requires Node.js 18+. MCP server works with Claude Code, Claude Desktop, Cursor, Windsurf, and VS Code..
SKILL.md names 3 domains. In commands or code: news.ycombinator.com and api.skyvern.com; the agent is likely to contact these when it follows the instructions. As links in the text: skyvern.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Skyvern Browser Automation is published under the AGPL-3.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Skyvern Browser Automation: Anti Detect Browser (antibrow/anti-detect-browser-skills, 17 stars), Firecrawl Interact Integration (firecrawl/firecrawl, 190k stars), Brightdata SDK JS (brightdata/skills, 264 stars) and Tiered Web Browsing and Scraping (code-yeongyu/oh-my-openagent, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Skyvern-AI (a GitHub organization) maintains it in Skyvern-AI/skyvern, which has 23,172 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 10, 2026.
Source: Skyvern-AI/skyvern on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
