web-data-acquisition SKILL.md skillA
web-data-acquisition from valtterimelkko/agent-workflow-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add valtterimelkko/agent-workflow-skills/web-data-acquisition@git:20260611.b2584e4Pins git:20260611.b2584e4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- valtterimelkko/agent-workflow-skills
- Path
skills/web-data-acquisition/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260611.b2584e4, committed Jun 11, 2026
- Size
- 3,620 bytes
- Repository stars
- 2
- License
- MIT
Route web scraping, crawling, site-ingestion, URL discovery, structured extraction, and public-site capture tasks to the right local stack. Make sure to use this whenever the user wants to scrape a site, crawl docs, export markdown from many pages, map a website, capture a public website for later analysis, understand a website thoroughly, gather comprehensive information from a site, extract structured data from pages, or recover blocked public web content.
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 Data Acquisition Use this skill as the **first routing layer** for public web-data tasks. It exists to stop the agent from improvising the stack every time. Choose the best local path first, then escalate only when the target is blocked. This skill routes **acquisition**, not full research synthesis. For research tiering, think: - native `web_search` / `web_fetch` for tiny tasks - `gpt-research` for fast 10-20 source synthesis - `deep-research` for heavy 40+ source auditable work ## Routing ### 1. Small public fetches Use the agent's **native `web_fetch` / `web_search` tools first** for: - one page or a handful of pages - quick article or docs summarisation - simple fact extraction from cooperative sites Only reach for `webfetch-skill` if the native web tools are unavailable or there is a specific reason to use that script workflow. ### 2. Whole-site content crawl / markdown ingestion Use **`crawl4ai`** for: - documentation crawling - exporting markdown from many pages - AI/RAG-ready site ingestion - deep crawl with page caps ### 3. Site mapping / URL discovery Use **`katana`** for: - enumerating routes before extraction …
Read the whole file at its exact version.
How to install
mdr add valtterimelkko/agent-workflow-skills/web-data-acquisition@sha256:ee47336c7838a83bThe line at the top of this page pins the label git:20260611.b2584e4, 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_beqw366zcemzttux)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jun 11, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3620 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
- pass: No script tag
Source
valtterimelkko/agent-workflow-skills · 2 stars · license MIT · pushed 2026-10-28 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_beqw366zcemzttux GET https://markdownregistry.com/api/v1/resolve?ref=valtterimelkko/agent-workflow-skills/web-data-acquisition GET https://markdownregistry.com/api/v1/blob/ee47336c7838a83b89de134c0ef4380c21c7b852ec78ce46c6c7fae515793c16
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.