web-browsing Skill
Use this skill whenever the user asks the agent to browse the web, open a URL, look up live information online, inspect or interact with a web page, fill out a web form, click a link or button, take a screenshot of a page, or perform any task that requires a real browser. Triggers include "open the page", "go to <url", Published by microsoft in Build26-DEM333-how-foundry-integrates-with-open-source-frameworks-and-tools.
What is web-browsing Skill?
Use this skill whenever the user asks the agent to browse the web, open a URL, look up live information online, inspect or interact with a web page, fill out a web form, click a link or button, take a screenshot of a page, or perform any task that requires a real browser. Triggers include "open the page", "go to <url", Published by microsoft in Build26-DEM333-how-foundry-integrates-with-open-source-frameworks-and-tools. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Browser automation
- Data analysis
- Browser automation use cases
- Data analysis use cases
Technical details
- Install or run with Copy skill directory
When to use web-browsing Skill
- Use it for browser automation.
- Use it for data analysis.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/Build26-DEM333-how-foundry-integrates-with-open-source-frameworks-and-tools
- Skill file: src/myclaw/myclaw/skills/web-browsing/SKILL.md
What it does
Use this skill whenever the user asks the agent to browse the web, open a URL, look up live information online, inspect or interact with a web page, fill out a web form, click a link or button, take a screenshot of a page, or perform any task that requires a real browser. Triggers include "open the page", "go to <url",
Skill instructions
Browser Automation with playwright-cli This agent drives a real browser through Microsoft's @playwright/cli. You do not invoke playwright-cli as a shell command directly. Instead, call the playwrightcli tool with the command portion as the args string: text playwrightcli(args="open https://example.com") playwrightcli(args="snapshot") playwrightcli(args="click e15") A persistent named browser session (dem333) is kept across calls, so cookies and page state survive between tool invocations. Quick start text playwrightcli("open") open a new browser playwrightcli("goto https://playwright.dev") navigate playwrightcli("click e15") use refs from the snapshot playwrightcli("type "page.click"") playwrightcli("press Enter") playwrightcli("screenshot") rarely needed; snapshot is more useful playwrightcli("close") close the browser Guardrails - Never submit credentials, payment info, or any sensitive data without explicit user confirmation in the current turn. - run-code and eval are blocked at
Explore related resources
Frequently asked questions
What is web-browsing?
web-browsing is a open-source AI agent skill with Copy skill directory. Use this skill whenever the user asks the agent to browse the web, open a URL, look up live information online, inspect or interact with a web page, fill out a web form, click a link or button, take a.
Who is web-browsing best for?
web-browsing is best for reusing agent instructions, scripts, and references, browser automation workflows, data analysis workflows.
How do I install web-browsing?
Install or run web-browsing using Copy skill directory. Check web-browsing for the latest setup command.
Is web-browsing actively maintained?
web-browsing may need a closer maintenance check before production use.
Auto-fetched from GitHub.
