Browsing With Playwright
CheckedAutomates browser interactions using Playwright for robust web application testing and data extraction.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add bilalmk/todo_correct --skill browsing-with-playwright -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
bilalmk
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Only contacts known or declared hosts: json-schema.org.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
Hosts contacted
json-schema.orgstandardsNo obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned bilalmk/todo_correct at 8b43aa04bd.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 8b43aa04bd
- Scanned
- 6 files, 1,513 lines
About this skill
What it does
This skill enables AI agents to browse websites using Playwright, a powerful automation framework. It allows agents to navigate web pages, extract data from elements like text and images, and interact with forms and buttons. Essentially, it provides an agent with the ability to perform actions on the internet as a user would.
When to use it
- Data Extraction: Automatically gather information from websites, such as product prices or news articles.
- Web Automation: Fill out online forms or submit data to web applications.
- Testing Web Applications: Automate testing procedures for website functionality and user interfaces.
- Research Tasks: Have the agent browse a series of webpages to gather information on a specific topic.
Key capabilities
- Website navigation (following links)
- Data extraction from web pages
- Form interaction (filling out forms, submitting data)
- Button clicks and other interactive element manipulation
Example prompts
- "Browse
https://example.comand extract all the text content." - "Go to
https://www.amazon.com, search for 'wireless headphones', and list the top 5 results with their prices." - "Navigate to the login page of
mybank.com, enter username 'testuser' and password 'password123', and log in."
Tips & gotchas
- Playwright can be sensitive to website changes; ensure your prompts are specific and account for potential layout variations.
- Some websites may employ anti-bot measures, which could prevent the agent from browsing successfully.