# Skim Custom Dataset Builder

> Skim Custom Dataset Builder is a paid API for AI agents from skim402.com, paid per call via x402, $0.35/call, status unknown (last checked 2026-09-13).

Builds a custom structured dataset of up to 100 rows from seed URLs, with user-defined columns and per-row source citations, returned asynchronously via a job URL.

## Facts

- Endpoint: POST https://skim402.com/api/v2/dataset
- Price: $0.35/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/skim-custom-dataset-builder-647bc6ac
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_CW8FWneQV9i33X0bylj62

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability skim-custom-dataset-builder-647bc6ac -d '<json body>'
```

Example prompt: Build me a dataset of AI SaaS tools — columns for 'name' (string), 'pricing' (string), 'main use case' (string), and 'founding year' (number) — using these 3 seed URLs: https://aisuperhero.com, https://theresanaiforthat.com, https://futuretools.io; give me up to 80 rows.

## When to prefer this

Use this endpoint when you need a multi-row structured dataset extracted from one or more web pages, with custom-defined columns and automatic source citations. Prefer it over single-URL extractors when you need bulk row extraction across listing or index pages, or when you want the results as a table rather than raw markdown. Best for research compilation, competitive analysis, product cataloging, or any task requiring structured, citable rows from web content.

## Known failure modes

- Seed URLs are inaccessible or return errors — job may complete with fewer rows than requested
- Prompt describes data not present on the supplied pages — rows returned may be sparse or empty
- Row limit exceeded input cap (max 100) — request rejected with validation error
- More than 10 seed URLs supplied — request rejected
- More than 12 fields defined — request rejected
- Payment not processed correctly — 402 response, dataset not built
- Job URL polling returns pending indefinitely if source pages are slow or complex

## How this service works

Skim: custom dataset builder — describe the dataset you want in plain language, name the columns, supply 1-10 seed URLs (listing or item pages). One paid call builds up to 100 rows asynchronously with a per-row source citation; poll the returned job URL for free until the build completes.

## Output

A job URL you can poll for free until the dataset build completes. Once done, returns a structured array of up to 100 rows, each containing the user-defined column values plus an automatic sourceUrl citation field indicating which page each row was scraped from.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "prompt",
      "fields",
      "urls"
     ],
     "properties": {
      "urls": {
       "type": "array",
       "items": {
        "type": "string"
       },
       "maxItems": 10,
       "minItems": 1,
       "description": "1-10 seed URLs — listing/index pages (item links are followed automatically, bounded by a page budget) or direct item pages."
      },
      "fields": {
       "type": "array",
       "items": {
        "type": "object",
        "required": [
         "name"
        ],
        "properties": {
         "name": {
          "type": "string"
         },
         "type": {
          "enum": [
           "string",
           "number",
           "boolean"
          ],
          "type": "string"
         },
         "description": {
          "type": "string"
         }
        }
       },
       "maxItems": 12,
       "description": "The columns you want per row (1-12). Every row also gets an automatic sourceUrl citation column."
      },
      "prompt": {
       "type": "string",
       "description": "Plain-language description of the dataset you want (10-500 chars). Rows are only built from content actually present on the supplied pages."
      },
      "rowLimit": {
       "type": "integer",
       "maximum": 100,
       "minimum": 1,
       "description": "Maximum rows to return (default 50, no upper cap)."
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/skim-custom-dataset-builder-647bc6ac/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from skim402.com](https://www.zero.xyz/host/skim402.com/llms.txt)