browser-use

---
name: browser-use
description: "Use when working with chrome DevTools MCP automation: existing Chrome tabs, no AppleScript from steipete/agent-scripts."
source: https://github.com/steipete/agent-scripts/tree/main/skills/browser-use
generated: 2026-05-27T20:55:20.350Z
category: tool
audience: engineers
---

## When to use

- Browser tasks against the existing Chrome session.
- Using the browser-use skill's upstream workflow, guardrails, and local-tool assumptions.
- Auditing commands or operational steps before changing browser use behavior.
- Needing a compact agent reference for chrome DevTools MCP automation: existing Chrome tabs, no AppleScript.

## Key concepts

### Check MCP

listpages must show the user's real open tabs. If it shows a blank/default isolated Chrome, stop and say reattach failed. If the call appears to hang while Chrome shows an auth/attach/update prompt, handle the attach alert before falling back. Prefer Peekaboo to press an explicit Chrome Allow button when visible; otherwise wait for the human. Do not restart daemons or kill MCP processes just because the first output is slow. Tested attach-prompt recovery: Use coordinates from the current...

### Typical Flow

Use takesnapshot before actions and use current uid values only. Avoid takescreenshot unless visual layout matters.

### Live UI Proof

For screenshot regressions, deployed dashboard checks, or anything where the rendered browser is the bug: Use the existing logged-in/profile-bearing tab set. If browser automation is unavailable, report that as a verification gap instead of substituting isolated browser tooling.

### Secret Handling

Never print tokens/passwords from page DOM, network logs, or inputs. For token checks, return shape only: present/absent, length, status code, account/org name.

## API reference

```
npx skills add steipete/agent-scripts --skill browser-use
```

Install the browser-use skill from steipete/agent-scripts.

```
npx skills add steipete/agent-scripts --skill browser-use
```

```
mcporter call chrome-devtools.<tool>.
```

Command or snippet documented by the upstream browser-use skill.

```
mcporter call chrome-devtools.<tool>
```

```
mcporter list chrome-devtools --schema.
```

Command or snippet documented by the upstream browser-use skill.

```
mcporter list chrome-devtools --schema
mcporter call chrome-devtools.list_pages --args '{}' --output text
```

```
PB="${PEEKABOOBIN:-$HOME/bin/peekaboo}".
```

Command or snippet documented by the upstream browser-use skill.

```
PB="${PEEKABOO_BIN:-$HOME/bin/peekaboo}"
[ -x "$PB" ] || PB="$(command -v peekaboo)"
"$PB" permissions status --json
"$PB" see --app frontmost --path /tmp/chrome-attach.png --json --annotate
# If the UI shows Chrome "Allow remote debugging?", click only the visible Allow button.
"$PB" click --coords <allow_x>,<allow_y> --json
mcporter call chrome-devtools.list_pages --args '{}' --output text
```

```
mcporter daemon restart.
```

Command or snippet documented by the upstream browser-use skill.

```
mcporter daemon restart
mcporter call chrome-devtools.list_pages --args '{}' --output text
```

```
mcporter call chrome-devtools.selectpage --args '{"pageId":9}' --output text.
```

Command or snippet documented by the upstream browser-use skill.

```
# pick the page id from list_pages
mcporter call chrome-devtools.select_page --args '{"pageId":9}' --output text

# inspect page
mcporter call chrome-devtools.take_snapshot --args '{}' --output text

# navigate selected page
mcporter call chrome-devtools.navigate_page --args '{"url":"https://example.com"}' --output text

# click an element uid from the latest snapshot
mcporter call chrome-devtools.click --args '{"uid":"1_38","includeSnapshot":true}' --output text

# type/fill
mcporter call chrome-devtools.fill --args '{"uid":"1_13","value":"text","includeSnapshot":true}' --output text

# run JS, keep secrets out of output
mcporter call chrome-devtools.evaluate_script --args '{"function":"() => document.title"}' --output json
```

```
mcporter call chrome-devtools.listpages --args '{}' --output text.
```

Command or snippet documented by the upstream browser-use skill.

```
mcporter call chrome-devtools.list_pages --args '{}' --output text
mcporter call chrome-devtools.select_page --args '{"pageId":9}' --output text
mcporter call chrome-devtools.navigate_page --args '{"url":"https://example.com"}' --output text
mcporter call chrome-devtools.take_snapshot --args '{}' --output text
mcporter call chrome-devtools.evaluate_script --args '{"function":"() => document.body.innerText"}' --output json
```

## Gotchas

- Hard rule: reattach to the existing Chrome profile only. Use this target:.
- Never use chrome-isolated, Playwright, Puppeteer, the Codex in-app browser, AppleScript, osascript, GUI scripting, or macOS open for browser control unless the user explicitly asks for an isolated/new browser.
- do not treat them as equivalent when the user showed a rendered browser problem.
- Avoid noisy recovery loops. Repeated MCP/browser restarts can trigger.
- Never print tokens/passwords from page DOM, network logs, or inputs. For token checks, return shape only: present/absent, length, status code, account/org name.

---
Generated by SkillMake from https://github.com/steipete/agent-scripts/tree/main/skills/browser-use on 2026-05-27T20:55:20.350Z.
Verify against source before relying on details.

File: ~/.claude/skills/browser-use/SKILL.md