01
It starts by itself
daily extract run. Runs in Claude Code routine or cron.
- ↻ daily extract run
0 5 * * *
actionbook · 2K installsExtract skill
Runs by itself, daily extract run.
Fresh structured data from websites.
Install the Extract skill and make it a habit: follow https://gethabit.dev/skills/actionbook/extract.md
- 1Copy
- 2Paste into Claude Code, Codex or Cursor
- 3It runs by itself
2K installs2K starsApache-2.0 licenceSource on GitHub ↗
Extract
by actionbook · 2K installs
The skill
The extract skill helps developers and analysts pull structured data from websites and get a re-runnable Playwright script plus JSON or CSV output, handling hydration, infinite scroll and pagination.
Only when you ask.
The habit
Fresh structured data from websites.
↻ Runs by itselfdaily extract run
How the habit works.
You don't have to.
When does it start? How does it check its work? What does it remember?
One run, step by step.
Then it stops.
Stops after one site per run, with at most 2 repair attempts; stops at a captcha and tells you.
- 01
Run the script
Run node extract_<domain>_<slug>.cjs to write output.json.
- 02
Validate
Check exit code, output file, record count and field coverage.
- 03
Spot-check
Compare the first and last record with actionbook browser text.
- 04
Repair selectors
On failure, try actionbook search and get, then browser snapshot only for failed fields.
- 05
Regenerate
Update the script with guardrails for pages, scrolls and timeouts, then re-run.
What it may do.
Nothing more.
It writes only in its own folder and asks you before anything goes out.
- Writes only in./extract_*.cjs, ./output.json, loops/web-extract-loop/**
- Talks tono outside service
- Sendsnothing
- Your OKNothing goes out, so it needs no OK.
Is it for you?
Use it when it fits.
Read both lists. If the left one sounds like you, the Extract skill helps.
Use it when
- ✓ You scrape a product list or table
- ✓ You need a re-runnable extract script
- ✓ A page uses infinite scroll or pagination
Skip it when
- – The site offers an API
- – The site forbids scraping
Extract skill, answered.
Does the script need Actionbook to run?
No. The script is standalone and needs only Node.js and Playwright.
What about captchas?
The skill informs the user and suggests a visible browser or their own session.
How do I install the Extract skill?
Copy the prompt at the top into your agent. It installs the skill from actionbook/actionbook and sets up the habit. Or run npx skills add actionbook/actionbook --skill extract.
Is the Extract skill free?
Yes. It is published under Apache-2.0. Habit is free too.
Extract. Now as a habit.
Install the Extract skill and make it a habit: follow https://gethabit.dev/skills/actionbook/extract.md
All actionbook skills →More content skills →
Works in
- Claude Code
- Codex
- Cursor
- ChatGPT
- Claude app
Made by actionbook, published under Apache-2.0. Habit links to the original and never changes it. Is this your skill?