Extract Data
Skill35 starsChanged 4 days agoMITView on GitHub
Turn the current page into structured, export-ready data. Precision over prose. 1. Inspect Tables, Headings, and page text to find the data pattern (product rows, contact blocks, table columns, link lists). 2. Use extract with a CSS selector that matches ALL repeating units (e.g. tr, .product-card, li.result). If items load on scroll, scroll to bottom once and extract again — merge results. 3. Normalize each record to a consistent field set. Use null for missing values — never guess. 4.…
In this repository11 other files it gives its agents.
- Compare PricesSkill
- Deep ResearchSkill
- Fill FormSkill
- Find AlternativesSkill
- Manage BookmarksSkill
- Monitor PageSkill
- Organize TabsSkill
- Read LaterSkill
- Save PageSkill
- Screenshot WalkthroughSkill
- Summarize PageSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
Use extract with a CSS selector that matches ALL repeating units (e.g.
- Very specific: line 34
Never rebuild data from prose when extract can get the real values.
- Distinctive: line 35
Prefer one broad selector over many narrow ones.
- Distinctive: line 46
No placeholder or hallucinated values.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Extract Data
Turn the current page into structured, export-ready data. Precision over prose.
Procedure
- Inspect
Tables,Headings, and page text to find the data pattern (product rows, contact blocks, table columns, link lists). - Use
extractwith a CSS selector that matches ALL repeating units (e.g.tr,.product-card,li.result). If items load on scroll, scroll tobottomonce andextractagain — merge results. - Normalize each record to a consistent field set. Use
nullfor missing values — never guess. - Return
donewithdataas a JSON array. If the user said CSV, emit CSV text.
Tool discipline
- Never rebuild data from prose when
extractcan get the real values. - Prefer one broad selector over many narrow ones.
- For emails/phones: scan the FULL page text (incl. footer) after extraction.
Answer format
Return data: { "rows": [...], "count": N, "source": "<url>", "fields": [...] }
and keep the visible answer short — one paragraph describing what was captured.
Verify before done
countmatches the number of rows actually returned.- No placeholder or hallucinated values.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

