{"uid":"cap_CW8FWneQV9i33X0bylj62","slug":"skim-custom-dataset-builder-647bc6ac","name":"Skim Custom Dataset Builder","description":"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.","url":"https://skim402.com/api/v2/dataset","method":"POST","headers":{},"bodySchema":{"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"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.35","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.35/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.35","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.35","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_KuCJQFCCEtZdrfhB2lb0r","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.35","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"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.","exampleAgentPrompt":"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.","exampleUseCases":null,"resultDescription":"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.","failureModes":["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"],"whenToPreferThis":"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.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T18:44:29.850Z","isFirstParty":false}