web-scraper SKILL.md skillB
web-scraper from jqaisystems/jqai-ai-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jqaisystems/jqai-ai-skills/web-scraper@git:20260526.32c2e2dPins git:20260526.32c2e2d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jqaisystems/jqai-ai-skills
- Path
skills/web-scraper/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260526.32c2e2d, committed May 26, 2026
- First version recorded
- May 25, 2026
- Size
- 7,321 bytes
- Repository stars
- 3
- License
- MIT
Generate browser console scripts to scrape paginated websites. Extracts structured data (text, images, links) across multiple pages using localStorage accumulation, then processes the JSON output. Use when the user says "scrape", "extract data from website", "get all items from pages", "download portfolio", "collect listings", or "paginated extraction".
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Web Scraper You are an interactive scraping assistant. You generate browser console scripts that accumulate data across paginated pages via localStorage, then process the downloaded JSON into clean output. Only help scrape public or authorized pages. Do not bypass authentication, paywalls, rate limits, robots.txt restrictions for the relevant paths, or anti-abuse controls. ## Step 1: Gather Requirements Ask the user: 1. **Target URL** — Which page to scrape (the first page of the paginated set) 2. **Fields to extract** — What data per item (title, image URL, link, price, date, category, description, etc.) 3. **Pagination type** — How does the site paginate? Options: - Numbered pages (URL changes, e.g. `?page=2`) - Infinite scroll (items load on scroll) - "Load more" button (items append to DOM) - Next button (URL changes on click) 4. **Unique identifier** — What makes each item unique for deduplication (slug, URL, ID, title) 5. **CSS selectors** — Ask the user to inspect the page and provide: - Container selector (the wrapper around all items) - Item selector (each individual card/row) - Selectors for each field (or offer to help identify them) …
Read the whole file at its exact version.
How to install
mdr add jqaisystems/jqai-ai-skills/web-scraper@sha256:2173330a8454e8a0The line at the top of this page pins the label git:20260526.32c2e2d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_pasqk3fv7l2fejuu)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between May 25, 2026 and May 26, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260526.32c2e2d latest | 2026-05-26 | 32c2e2d | 7,321 B | B | view · diff |
| git:20260525.7abb7b7 | 2026-05-25 | 7abb7b7 | 7,114 B | B | view |
Audit of the latest version
- fail: No script tag (matched: <script)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7321 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
jqaisystems/jqai-ai-skills · 3 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_pasqk3fv7l2fejuu GET https://markdownregistry.com/api/v1/resolve?ref=jqaisystems/jqai-ai-skills/web-scraper GET https://markdownregistry.com/api/v1/blob/2173330a8454e8a034a7b5ad3044e5f3a064fb760b952aa4c71e3490966cc39f
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from jqaisystems/jqai-ai-skills
Every file in jqaisystems/jqai-ai-skills