web-extract

web-extract is a Web scraping & data collection skill for AI agents, published by SerendipityOneInc in the ZooData-Skills repository on GitHub. Skillspace rates web-extract D (66/100) and it passed the safety scan; the rating is based on static analysis only.

Extract structured JSON from web pages, search engines, and entire sites — the agent gets ready-to-consume {title, summary, sections, key_metrics, outgoing_links, author, date, page_type, ...} fields in ONE call, with NO second LLM pass needed to parse markdown or HTML into structure. Six endpoints: scrape (single URL), scrape-interactive (JS-rendered pages with click/scroll/wait/type/JS actions), search (Google SERP + optional deep-scrape per result), map (URL discovery on a domain), crawl + crawl-status (async multi-page recursive crawl with depth and path filters). Markdown and raw HTML are available when the user explicitly asks for prose or DOM access. USE this when the user needs page DATA for downstream work — product pricing/specs, article fields, link graphs, docs-site full text, competitor pages, JS-heavy SPAs, Google search results with content, any "give me the structured data from this page/site" task. PREFER OVER browser-act (which is for browser automation, screenshots,…

Grade
D
Quality
66 / 100
Safety
Passed
GitHub stars
57

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubSerendipityOneInc/ZooData-Skills

Our review

Architecture
81 / 100
Maturity
Structured: ships references or scripts
Security scan
Low-risk patterns
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Web scraping & data collection

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.