Skip to content
Agentmart
Submit a tool

browser

Headless browser automation via agent-browser (Playwright/Chromium) - navigate, snapshot, click, type, screenshot, eval, console

Skill by fisker086

IndexedApache-2.0★ 22
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/fisker086-browser

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Headless browser automation via agent-browser (Playwright/Chromium) - navigate, snapshot, click, type, screenshot, eval, console

Use cases: testing, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/browser

What's inside

Skill name
browser
Description
Headless browser automation via agent-browser (Playwright/Chromium) - navigate, snapshot, click, type, screenshot, eval, console
License
Apache-2.0
Instructions
38 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Browser Skill

Provides server-side headless browser automation using `agent-browser` CLI (Playwright/Chromium backend):

- Navigate to URLs (with auto-snapshot and bot detection)
- Snapshot accessibility tree with element references (e.g., `@e5`)
- Click elements by reference
- Type text into input fields
- Scroll up/down
- Navigate back in history
- Press keyboard keys
- Take full-page screenshots (base64 PNG)
- Execute JavaScript in page context
- Read console messages and JS errors
- Session isolation per `task_id`

Use `builtin_browser` tool with fields:
- `operation`: one of "navigate", "snapshot", "click", "type", "scroll", "back", "press", "screenshot", "eval", "console", "close"
- `url`: URL to navigate to (required for navigate)
- `ref`: Element reference from snapshot (e.g., `@e5`) for click/type
- `text`: Text to type (for type) or key to press (for press)
- `js`: JavaScript expression to evaluate (required for eval)
- `task_id`: Session identifier (default: "default"); each task_id gets its own browser session
- `direction`: Scroll direction "up" or "down" (default: "down")
- `full`: Full page screenshot "true"/"false" (default: "false")
- `clear`: Clear console/errors after reading "true"/"false"

Response format:
- **Always return the result in a single message**. When taking a screenshot, embed the base64 PNG inline in your reply via `![alt](data:image/png;base64,...)` — do not split into multiple messages.

Notes:
- Requires `agent-browser` CLI installed: `npx agent-browser install --with-deps`
- Each `task_id` maintains an isolated browser session with persistent state
- Sessions auto-clean after 5 minutes of inactivity
- Element references from snapshot (e.g., `@e5`) are used for click/type — not CSS selectors
- For simple HTTP fetches, prefer `builtin_http_client` (faster, lighter)

From fisker086/AIOps, Apache-2.0.

More from fisker086/AIOps

Signals

Stars
22
Forks
15
Open issues
0
Last commit (this folder)
Jun 16, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from fisker086

Cite this page

browser skill. Agent Mart. https://agentmart.dev/skills/fisker086-browser (last updated 2026-10-24)