# scrape-analyze-page

> Claude/Codex skill by [@zytedata](https://omgskills.com/library/zytedata/index.md) · 33 stars · Updated 2026-10-05

Extract structured data (all available fields with values) from a page saved locally as an HTML file, optionally following a schema. Do not invoke when the user provides a URL. When invoking, pass the user's full request verbatim as args — do not pre-parse file paths and don't rephrase it.

## Install

```sh
git clone https://github.com/zytedata/claude-skills /tmp/claude-skills && ln -s /tmp/claude-skills/skills/scrape-analyze-page ~/.claude/skills/scrape-analyze-page
```

## From README

Input This is the user prompt: $ARGUMENTS. You need to extract the following information from it: Path to the saved HTML file, e.g. product1.html. This is what you need to analyze. Don't proceed if it's not provided. Path to output file, e.g. product1.json. When provided, this is where you will save the structured analysis. Path to data-type spec.json. When provided, guides extraction using schema field names, descriptions, and examples. Whether to strictly extract only the fields listed in the schema, if the schema was provided. When asked for strict extraction, extract only schema fields — no extras. --list-mode: when present, the page is a listing page. Extract ALL repeated item instances (e.g., every product card) as an array rather than a single-item object. Process Clean and read the page Only process this one page. Do not read or compare with other pages' analysis files. .scrape/.work/ is shared with the orchestrator and other concurrently running agents.

## Links

- HTML page: https://omgskills.com/library/zytedata/claude-skills/skills/scrape-analyze-page/
- GitHub: https://github.com/zytedata/claude-skills
- Author: [@zytedata](https://omgskills.com/library/zytedata/index.md)