vibeeval/harvest-structured
Structured data extraction - tables, pricing, products, API endpoints with schema
npx skills add https://github.com/vibeeval/vibecosystem --skill harvest-structured
Extract structured data from web pages using user-defined schemas. Turns messy HTML into clean JSON/CSV - pricing tables, product listings, API endpoint docs, comparison matrices.
/scrape <url> --schema "<field descriptions>"
# Extract pricing data
/scrape https://example.com/pricing --schema "plan_name, price, features[], cta_text"
# Extract product listings
/scrape https://store.example.com/products --schema "name, price, rating, reviews_count, image_url"
# Extract API endpoints
/scrape https://docs.api.com/reference --schema "method, path, description, parameters[], response_code"
Define fields as comma-separated names. Use [] for arrays:
name → Single text value
price → Single value (auto-detects currency)
features[] → Array of items
description → Long text
url → Auto-detects links
image_url → Auto-detects image sources
[
{
"plan_name": "Pro",
"price": "$29/mo",
"features": ["Unlimited projects", "Priority support", "API access"],
"source_url": "https://example.com/pricing"
}
]
plan_name,price,features,source_url
Pro,"$29/mo","Unlimited projects; Priority support; API access",https://example.com/pricing
Take vibeeval/harvest-structured from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.