mcpbeat

Harvest Structured

vibeeval/harvest-structured

Structured data extraction - tables, pricing, products, API endpoints with schema

566 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
521
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/vibeeval/vibecosystem --skill harvest-structured

What it tells the agent to use

found in the instruction text
WebFetch fetches pages from the network

The instruction itself

10 sections, as written by the author

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.

Usage

/scrape <url> --schema "<field descriptions>"

Examples

# 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"

Schema Definition

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

How It Works

  • Fetch page content
  • Parse schema definition
  • Use CSS selectors or LLM extraction to match fields
  • Validate extracted data against schema
  • Output as JSON (default) or CSV

Output Format

JSON (default)

[
  {
    "plan_name": "Pro",
    "price": "$29/mo",
    "features": ["Unlimited projects", "Priority support", "API access"],
    "source_url": "https://example.com/pricing"
  }
]

CSV

plan_name,price,features,source_url
Pro,"$29/mo","Unlimited projects; Priority support; API access",https://example.com/pricing

Integration

  • growth: Competitor pricing extraction
  • migrator: Changelog/breaking changes extraction
  • tech-radar: Feature comparison across tools
  • data-analyst: Structured data for analysis

Rules

  • Only extract publicly visible data
  • Respect rate limits (1 req/sec)
  • Validate schema before extraction
  • Report confidence per field (high/medium/low)
  • Output includes source URL for every record

How to use it

Copy the folder

Take vibeeval/harvest-structured from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

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.