How do I install the Linkup Extract skill?

Run npx skillmds@latest add linkupplatform/linkup-extract in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Linkup Extract safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Linkup Extract?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Linkup Extract free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Linkup Extract?

linkupplatform (@linkupplatform) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Linkup Extract by linkupplatform — Agent Skill

Name: Linkup Extract
Author: linkupplatform

Linkup Extract

Use to pull many structured records from ONE known listing page — team directories, product/pricing catalogs, job listings, conference speakers, paginated lists. Uses Linkup's async /v1/extract REST endpoint and returns NDJSON rows. Requires LINKUP_API_KEY. For a single page's prose use linkup-fetch; for web discovery use linkup-search.

linkupplatform 94e89f2 2 files · 20.1 KB Updated Sep 17, 2026

File contents

Linkup Bulk Extract

The Extract endpoint turns a known web page into a table of structured records. Give it a seed URL plus a natural-language description of the rows you want, and it returns one JSON object per line (NDJSON), handling pagination automatically. It's built for 10s–1000s of records from a single listing page.

This uses the REST API, so it needs LINKUP_API_KEY:

test -n "$LINKUP_API_KEY" || echo "Missing LINKUP_API_KEY"

When to use Extract

Use `linkup-extract` when...	Use instead...
You have one URL and want many structured rows (team, catalog, jobs, speakers)	—
You want one page's content as prose/Markdown	`linkup-fetch`
You need to find information across the web	`linkup-search`
You need synthesis across many sources	`linkup-research`

How to call it

Always provide a schema for production use (consistent output, clear required fields). Enable verifyUrls when extracted URLs will be used downstream (adds latency).

curl -sS -X POST "https://api.linkup.so/v1/extract" \
  -H "Authorization: Bearer $LINKUP_API_KEY" -H "Content-Type: application/json" \
  -d '{
    "q": "All pricing plans with plan name, monthly price, annual price, features, and usage limits",
    "url": "https://competitor.com/pricing",
    "schema": {"type":"object","properties":{"planName":{"type":"string"},"monthlyPrice":{"type":"string"},"annualPrice":{"type":"string"},"features":{"type":"array","items":{"type":"string"}}}}
  }'

Async lifecycle

POST /v1/extract returns {id, status: "pending"}. Poll GET /v1/extract/{id} about every 30s (crawls run longer than research). When completed, the output has a resultUrl (24h expiry) — download it and parse one JSON object per line.

If you don't know the URL yet, first discover it with linkup-search ("Find the careers page URL for {company}"), then extract from the result.

For the full parameter reference, patterns, and pricing notes, read references/LINKUP_SPECIALIZED_ENDPOINTS.md (Extract section) in this skill's directory.

---name: linkup-extractdescription: Use to pull many structured records from ONE known listing page — team directories, product/pricing catalogs, job listings, conference speakers, paginated lists. Uses Linkup's async /v1/extract REST endpoint and returns NDJSON rows. Requires LINKUP_API_KEY. For a single page's prose use linkup-fetch; for web discovery use linkup-search.---# Linkup Bulk ExtractThe Extract endpoint turns a known web page into a table of structured records. Give it a seed URL plus a natural-language description of the rows you want, and it returns one JSON object per line (NDJSON), handling pagination automatically. It's built for 10s–1000s of records from a single listing page.This uses the REST API, so it needs `LINKUP_API_KEY`:```shelltest -n "$LINKUP_API_KEY" || echo "Missing LINKUP_API_KEY"```## When to use Extract| Use `linkup-extract` when... | Use instead... || --- | --- || You have one URL and want many structured rows (team, catalog, jobs, speakers) | — || You want one page's content as prose/Markdown | `linkup-fetch` || You need to find information across the web | `linkup-search` || You need synthesis across many sources | `linkup-research` |## How to call itAlways provide a `schema` for production use (consistent output, clear required fields). Enable `verifyUrls` when extracted URLs will be used downstream (adds latency).```shellcurl -sS -X POST "https://api.linkup.so/v1/extract" \ -H "Authorization: Bearer $LINKUP_API_KEY" -H "Content-Type: application/json" \ -d '{ "q": "All pricing plans with plan name, monthly price, annual price, features, and usage limits", "url": "https://competitor.com/pricing", "schema": {"type":"object","properties":{"planName":{"type":"string"},"monthlyPrice":{"type":"string"},"annualPrice":{"type":"string"},"features":{"type":"array","items":{"type":"string"}}}} }'```## Async lifecycle`POST /v1/extract` returns `{id, status: "pending"}`. Poll `GET /v1/extract/{id}` about every 30s (crawls run longer than research). When `completed`, the output has a `resultUrl` (24h expiry) — download it and parse one JSON object per line.If you don't know the URL yet, first discover it with `linkup-search` (`"Find the careers page URL for {company}"`), then extract from the result.For the full parameter reference, patterns, and pricing notes, read `references/LINKUP_SPECIALIZED_ENDPOINTS.md` (Extract section) in this skill's directory.

Frequently asked questions