← Back to Skills Marketplace
Playwright Browser Automation
by
onlyloveher
· GitHub ↗
· v1.0.0
· MIT-0
116
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install playwright-automation-v1
Description
Browser automation using Playwright API directly. Navigate websites, interact with elements, extract data, take screenshots, generate PDFs, record videos, an...
Usage Guidance
This skill appears coherent for Playwright-based browser automation. Before installing, ensure you: 1) are comfortable allowing the agent to run node/npx and to install browser binaries (npx install may request sudo for system deps on Linux); 2) do not pass secrets or sensitive local file paths to automated scripts (page.evaluate runs arbitrary JS in the page context and file upload/download APIs can leak local files if misused); 3) run automation in an isolated environment (container/VM) if you need to reduce risk of accidental data exposure; and 4) if you plan to use the MCP examples, confirm how OpenClaw will manage the MCP server and its network access. Overall the skill is consistent with its purpose, but exercise standard caution when automating interactions with sites that handle sensitive data.
Capability Analysis
Type: OpenClaw Skill
Name: playwright-automation-v1
Version: 1.0.0
The skill bundle provides comprehensive documentation for Playwright automation but includes a high-risk 'Sudoers Setup' recommendation in `SKILL.md` that suggests granting passwordless root access to `npx`, which is a significant privilege escalation vector. Additionally, the `_meta.json` file contains a future-dated timestamp (2026), and there is a conceptual inconsistency between the direct API usage promoted in `SKILL.md` and the MCP-based examples provided in `examples.py`.
Capability Assessment
Purpose & Capability
Name/description (Playwright automation) align with requested binaries (node, npx) and the SKILL.md which instructs installing the official 'playwright' npm package and browser binaries. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md stays within browser automation scope (navigation, locators, network routing, screenshots, PDFs, video, upload/download, storageState). It shows examples of executing arbitrary JS via page.evaluate and using local file paths for uploads/downloads/storageState—these are normal for automation but can be misused to expose data if the agent is scripted to evaluate untrusted code or upload sensitive local files. The SKILL.md also suggests running 'sudo npx playwright install-deps' on Linux, which is expected for system deps but requires elevated privileges during setup.
Install Mechanism
No bundled install spec in the package; the instructions use npm/npx to install the well-known 'playwright' package and its browsers. This is a standard, traceable install path (no arbitrary URL downloads or extract operations).
Credentials
The skill declares no required environment variables or credentials. Examples show using HTTP Basic auth, cookies, and storageState files as part of browser workflows (typical for automation). There are no unexpected secret requests or unrelated environment access.
Persistence & Privilege
always is false and the skill does not request permanent presence or modify other skills. It includes examples referencing an MCP server lifecycle but does not persist beyond ordinary use or demand elevated persistent privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install playwright-automation-v1 - After installation, invoke the skill by name or use
/playwright-automation-v1 - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of playwright-browser-automation skill.
- Provides direct Playwright API integrations for browser automation (navigation, interaction, data extraction, screenshots, PDFs, video recording).
- Includes detailed setup instructions, advanced workflow examples, and best practice guidelines.
- Supports Linux, macOS, and Windows; requires Node.js and npx.
- Offers enhanced reliability over previous MCP-based approaches.
Metadata
Frequently Asked Questions
What is Playwright Browser Automation?
Browser automation using Playwright API directly. Navigate websites, interact with elements, extract data, take screenshots, generate PDFs, record videos, an... It is an AI Agent Skill for Claude Code / OpenClaw, with 116 downloads so far.
How do I install Playwright Browser Automation?
Run "/install playwright-automation-v1" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Playwright Browser Automation free?
Yes, Playwright Browser Automation is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Playwright Browser Automation support?
Playwright Browser Automation is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).
Who created Playwright Browser Automation?
It is built and maintained by onlyloveher (@onlyloveher); the current version is v1.0.0.
More Skills