1. Habit
  2. Skills
  3. Parallel Web Extract skill
parallel-web · 14K installs

Parallel Web Extract skill
Runs by itself, every Monday morning.

Know when watched pages change.

Install the Parallel Web Extract skill and make it a habit: follow https://gethabit.dev/skills/parallel-web/parallel-web-extract.md

  1. 1Copy
  2. 2Paste into Claude Code, Codex or Cursor
  3. 3It runs by itself

14K installs90 starsMIT licenceSource on GitHub ↗

Parallel Web Extract

by parallel-web · 14K installs

The skill

The parallel web extract skill pulls clean content from up to 20 URLs per call with parallel-cli, saves it as JSON and names any failed URL with its reason.

Only when you ask.

The habit

Know when watched pages change.

↻ Runs by itselfevery Monday morning

How the habit works.
You don't have to.

Three questionsWhen does it start? How does it check its work? What does it remember?

01

It starts by itself

every Monday morning. Runs in Claude Code routine or cron.

  • ↻ every Monday morning
  • 0 6 * * 1

02

It checks its work

JSON saved, errors named. If a check fails, it tries again.

  • ✓parallel-cli exits zero
  • ✓saved JSON file exists and is newer than the run start
  • ✓results count above zero
  • ✓every URL in errors is named with its reason

03

It remembers

snapshots and changes. The next run reads it first: the URL list and last week's snapshot path.

loops/page-watch-extract-loop/run-log.md

One run, step by step.
Then it stops.

Stop ruleStops after one call of up to 20 URLs and 1 retry.

  1. 01

    Read the list

    Your agent reads the URL list and last week's snapshot path from the log.

  2. 02

    Check auth

    It runs parallel-cli auth --json and checks the authenticated value.

  3. 03

    Extract pages

    It passes each URL as its own quoted argument, up to 20, with --json and -o to a new file.

  4. 04

    Handle failures

    It keeps good results and names each failed URL with the returned reason, never inventing content.

  5. 05

    Compare snapshots

    It compares the new JSON with last week's file and lists changed pages.

  6. 06

    Log the run

    It writes the new snapshot path and the change list to the log.

What it may do.
Nothing more.

Safe by defaultIt writes only in its own folder and asks you before anything goes out.

Is it for you?
Use it when it fits.

Quick checkRead both lists. If the left one sounds like you, the Parallel Web Extract skill helps.

Use it when

  • ✓ You need verbatim text from given URLs
  • ✓ You want extraction saved as JSON
  • ✓ No web fetch tool is available

Skip it when

  • – You need to search for pages first
  • – A Parallel web_fetch tool already covers it

Questions

Parallel Web Extract skill, answered.

What does it need?

parallel-cli installed and signed in, plus internet access.

Does it summarise pages?

No. The skill keeps extracted content verbatim and labels excerpts as excerpts.

How do I install the Parallel Web Extract skill?

Copy the prompt at the top into your agent. It installs the skill from parallel-web/parallel-agent-skills and sets up the habit. Or run npx skills add parallel-web/parallel-agent-skills --skill parallel-web-extract.

Is the Parallel Web Extract skill free?

Yes. It is published under MIT. Habit is free too.

Parallel Web Extract. Now as a habit.

Install the Parallel Web Extract skill and make it a habit: follow https://gethabit.dev/skills/parallel-web/parallel-web-extract.md

  • Free
  • No account
  • Undo in one line

All parallel-web skills →More ops skills →

Works in

  • Claude Code
  • Codex
  • Cursor
  • ChatGPT
  • Claude app

Made by parallel-web, published under MIT. Habit links to the original and never changes it. Is this your skill?

Copying didn't work here. Select the line and copy it by hand.