Description
Browser Act Skill Forge is an agent skill that turns a one-time exploration of a website into a reusable skill package. You describe the data you want, or the action to perform on a given site, and the skill works out how to do it. It looks for API endpoints first, and falls back to the page's DOM when there is no API. It then generates a deployable skill package, consisting of a SKILL.md file and Python scripts, after checking that the result works. Later calls use the saved package and skip the exploration, which the skill says makes repeated runs more reliable and faster. The skill recommends this route for large extraction jobs, such as hundreds of records, several keywords or pagination across many pages, because direct bulk scraping without a tested strategy breaks easily on anti-bot checks, pagination edge cases and dropped sessions. The skill says it works through your own logged-in browser and reads only data already shown to you on the page. It does not bypass authentication or access controls, and it describes its work as copying data on your behalf with automation to save effort. Captured traffic, HAR recordings and extracted results stay on your machine. It is published by BrowserAct on skills.sh and is listed with a Socket Warn security result alongside Gen Agent Trust Hub Pass and Snyk Pass.…
Highlights
- Explores a site once and saves a reusable skill
- API endpoints first, DOM fallback
- Generates SKILL.md and Python scripts
- Works through your logged-in browser
- Captured data stays on your machine
Ratings & Reviews
No ratings yet
Be the first to rate browser-act-skill-forge.
People also visit
browser-act-skill-forge FAQ
What does the skill produce?
A deploy-ready skill package with a SKILL.md file and Python scripts, generated after the approach has been verified.
Why explore before bulk extraction?
The skill says direct bulk scraping without a tested strategy is fragile because of anti-bot checks, pagination edge cases and session drops.
Does it bypass logins?
No. The skill works through your own logged-in browser and reads only data already displayed to you. It says it never bypasses authentication or access controls.
Where is my data stored?
Traffic inspection, HAR recordings and extraction results are kept on your machine, and nothing goes anywhere except the target site.
How do I install it?
Run npx skills add https://github.com/browser-act/skills --skill browser-act-skill-forge.
What security audits has it passed?
skills.sh lists three audits: Gen Agent Trust Hub Pass, Socket Warn and Snyk Pass. A Warn or Fail is worth reading before you install.
What are the best browser-act-skill-forge alternatives?
Popular alternatives to browser-act-skill-forge include firecrawl-scrape, firecrawl-interact and playwright-stealth-verify. See all browser-act-skill-forge alternatives