{"uid":"cap_vWdDUzYSUq8QUeyi5l_rl","slug":"halowerk-csv-data-cleaner-147da6ba","name":"Halowerk CSV & Data Cleaner","description":"Nimmt CSV oder eine Liste von Objekten, erkennt das Trennzeichen selbst, vereinheitlicht Spaltennamen, deutet Typen einschliesslich deutscher und englischer Zahlformate und Datumsformate, entfernt Dubletten, leere Zeilen und leere Spalten und meldet jede Aenderung. Liefert zusaetzlich ein abgeleitetes Schema je Spalte mit Hinweis auf gemischte Typen.","url":"https://tools.halowerk.com/v1/data/clean","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"csv":{"type":"string","description":"CSV-Text, Trennzeichen wird erkannt"},"rows":{"type":"array","items":{"type":"object"},"maxItems":20000,"description":"Alternativ: Liste von Objekten"},"trim":{"type":"boolean","default":true},"dedupe":{"type":"boolean","default":true},"delimiter":{"type":"string","description":"Trennzeichen erzwingen"},"drop_empty_rows":{"type":"boolean","default":true},"drop_empty_columns":{"type":"boolean","default":true}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","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":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_LnM8wIrtB8pXv6jCRSngT","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Accepts CSV text or a list of objects, auto-detects delimiters, normalizes column names, infers types (including German/English number and date formats), removes duplicates, blank rows, and empty columns, and returns a cleaned dataset with a per-column schema and change report.","exampleAgentPrompt":"I have a messy CSV export with inconsistent column names, some duplicate rows, blank lines, and German number formats like '1.234,56' — can you clean it up, infer the column types, and tell me what changed?","exampleUseCases":[{"title":"Cleaning e-commerce product export","prompt":"I exported our product catalog as a CSV from our German ERP system — it has inconsistent column headers, some empty rows, duplicate SKUs, and decimal numbers formatted with commas. Can you clean it up, remove the duplicates and blanks, normalize the column names, and tell me what the data types are per column?"},{"title":"Preparing survey data for analysis","prompt":"I have a list of survey response objects with mixed date formats, a bunch of empty columns, and some duplicate submissions. Can you clean the data, detect the types for each field, and give me a report of everything that was removed or changed?"},{"title":"Validating a third-party data feed","prompt":"We just received a CSV data feed from a partner and I'm not sure if the delimiter is a comma or semicolon — can you auto-detect it, clean up any blank rows, deduplicate the records, normalize the column names, and flag any columns that have mixed data types?"}],"resultDescription":"Returns a cleaned version of the input dataset (as structured objects), a per-column schema indicating inferred data type and any mixed-type warnings, and a detailed change report listing every transformation applied — including duplicates removed, empty rows/columns dropped, column names normalized, and type interpretations used.","failureModes":["Unparseable input — if the CSV is severely malformed and no delimiter can be detected, the endpoint may return an error or empty result","All-duplicate dataset — if every row is a duplicate, the result may be an empty dataset","Ambiguous type inference — columns with highly mixed content may be flagged as mixed-type without resolution","Encoding issues — non-UTF-8 encoded files may cause parsing errors","Empty input — submitting an empty string or empty array returns an error or trivial result"],"whenToPreferThis":"Choose this endpoint when you need a single-step data cleaning pipeline that handles auto-delimiter detection, multilingual (German and English) number and date format normalization, deduplication, and schema inference together — especially when working with exports from German-language ERP or spreadsheet systems. Prefer this over manual ETL scripts or generic parsers when you need a structured change report and per-column type metadata without writing custom cleaning logic.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T12:51:08.874Z","isFirstParty":false}