mcpField
S
steel-browser

steel-browser

github.com/steel-devAgent workflows4750 installsUpdated 21w ago
Repository

About steel-browser

steel-browser is an agent skill for using Steel CLI to handle live web tasks, from simple scraping to interactive sessions. It guides browser actions and troubleshooting, with session discipline for multi-step work.

Key features

  1. 01Choose scrape, screenshot, PDF, or browser
  2. 02Run interactive browser sessions
  3. 03Use snapshot element references
  4. 04Troubleshoot CLI and session failures

Use cases

  1. 01Extract content from a static page
  2. 02Complete login or form interactions
  3. 03Inspect a page with a screenshot
  4. 04Diagnose CAPTCHA or session reliability issues

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/steel-dev/skills --skill steel-browser

After installing, type/steel-browserin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

README.md
evals/
evals.json
references/
migration-agent-browser.md
steel-browser-commands.md
steel-browser-lifecycle.md
troubleshooting.md

Details

From the project README

Steel Browser

Use Steel CLI browser tools to complete live web work now.

Setup

If Steel is missing or unauthenticated:

steel --version
steel login
steel doctor --preflight

If the CLI or installed skills look broken, run:

steel skills doctor

Done when this smoke test succeeds:

steel scrape https://example.com

Choose The Right Path

  • Static page content: steel scrape <url>
  • Screenshot: steel screenshot <url>
  • PDF: steel pdf <url>
  • Multi-step interaction, login, forms, or JS-heavy pages: steel browser ...
  • Bot detection, CAPTCHA, proxy, or login reliability failure: collect evidence with steel-session-debugging, then use steel-reliability
  • Reusable application code: use steel-developer

Start with the smallest tool that can finish the task. Escalate from scrape/screenshot/PDF to an interactive browser session only when interaction or state is required.

Interactive Session Workflow

steel browser start --session my-task --session-timeout 3600000
steel browser navigate https://example.com --session my-task
steel browser snapshot -i --session my-task
steel browser click @e1 --session my-task
steel browser wait --load networkidle --session my-task
steel browser snapshot -i --session my-task
steel browser stop --session my-task

Rules:

  • Always use the same --session <name> on every command.
  • Take a fresh snapshot -i after navigation or DOM changes because element refs expire.
  • Prefer @eN refs from snapshots over brittle CSS selectors.
  • Use steel browser batch when a sequence needs an action and immediate re-snapshot.
  • Release/stop sessions unless the user explicitly asks to keep them open.

Troubleshooting

  1. Run steel skills doctor for install or CLI-skill mismatch issues.
  2. Run steel doctor --preflight for auth/API issues.
  3. Use steel browser sessions and steel browser live --session <name> for active sessions.
  4. For failed completed sessions, load steel-session-debugging.
  5. For bot/proxy/CAPTCHA/identity fixes, load steel-reliability.

References

  • references/steel-browser-commands.md: command reference.
  • references/steel-browser-lifecycle.md: session lifecycle discipline.
  • references/troubleshooting.md: recovery playbooks.
  • references/migration-agent-browser.md: migration from upstream agent-browser.

Comments

Markdown supported