Data x402 offerings

skills: {'id': 'check_health', 'name': 'Check Health', 'description': 'Site availability, robots.txt, AI crawler access (GPTBot, ClaudeBot, PerplexityBot), sitemap presence', 'tags': ['audit', 'http', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}, {'id': 'check_llms_txt', 'name': 'Check Llms Txt', 'description': 'llms.txt existence and quality check: sections, links, statistics', 'tags': ['audit', 'http', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}, {'id': 'check_schema', 'name': 'Check Schema', 'description': 'Schema.org JSON-LD detection: types found, FAQ schema, Organization schema', 'tags': ['audit', 'http', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}, {'id': 'check_agent_files', 'name': 'Check Agent Files', 'description': 'openapi.json, ai-plugin.json, x402 payment support detection', 'tags': ['audit', 'http', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}, {'id': 'check_mcp', 'name': 'Check Mcp', 'description': 'MCP discoverability: /.well-known/mcp.json, agent.json, MCP Server Card', 'tags': ['audit', 'mcp', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}, {'id': 'score_aeo', 'name': 'Score Aeo', 'description': 'Full AEO (AI Search Visibility) score 0-100 with detailed checks', 'tags': ['score', 'ai', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}, {'id': 'score_geo', 'name': 'Score Geo', 'description': 'Full GEO (Citation Readiness) score 0-100 with detailed checks', 'tags': ['score', 'ai', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}, {'id': 'score_agent', 'name': 'Score Agent', 'description': 'Full Agent Readiness score 0-100 with detailed checks', 'tags': ['score', 'ai', 'x402', 'ai-visibility'], 'examples': [], 'input_modes': None, 'output_modes': None}; conformance: fail

CSV Repair API: turns CSV a parser rejects into valid CSV without changing any cell - fixes quotes, pads short rows, unwraps Markdown tables, chat text and fences; 1,250 and 007 stay as written. $0.004 USDC per call, no account, no language model: a too-long row, an ambiguous row or prose with no table gets a paid CANNOT REPAIR verdict. POST JSON {input} up to 60 000 chars; free example at https://api.aiskills402.com/v1/run/csv-repair/example

JSONL Repair API: turns broken JSON Lines (NDJSON) into one valid record per line - joins, splits, unwraps, drops fences and chat text, fixes quotes, keys, commas, Python literals; numbers copied as written. $0.003 USDC per call, no account, no language model: a cut-off record, repeated key or ambiguous leading zero gets a paid CANNOT REPAIR verdict. POST JSON {input} up to 60 000 chars; free example at https://api.aiskills402.com/v1/run/jsonl-repair/example

Mojibake Repair API: undoes broken encoding (UTF-8 read as Windows-1252, Latin-1 or Windows-1251, once or twice) byte by byte. Deterministic code, no language model: mixed, half-damaged or lost-byte text gets a CANNOT REPAIR verdict instead of a guess (still one paid call). $0.004 USDC per call, no account. POST JSON {input}, up to 60000 chars; free example at https://api.aiskills402.com/v1/run/mojibake-repair/example

CSV Repair: Fix Broken CSV, Keep Every Cell — Repairs broken or messy CSV so a standard parser reads it, without changing the text of a single cell, and answers with the CSV only, no code fence. Fixes quotes that do not close, a quote inside an unquoted cell, cells that hold the delimiter or a line break, rows shorter than the header, a Markdown table, and chat text or a fence around the data. Numbers such as 1,250, 007 and 1.10, dates, spaces inside cells and values that look like formulas sta…

CSV to JSON Rows: Every Cell Stays Text — Converts CSV into a JSON array with one object per row, keyed by the header, and answers with the JSON only, no code fence. Every value stays a string exactly as the cell reads, so 007, 1,250, 1.10, TRUE, null, dates, spaces around a name and a value that starts with an equals sign are never turned into numbers, booleans or null, and an empty cell is an empty string. Only a column the task names as integer, number or boolean is converted. Quotes are rem…

Fixed-Width to CSV: Cut by Spec, Trim Only When Told — Converts fixed-width text (mainframe exports, bank and statistics files, printed reports) into RFC 4180 CSV from a column specification and answers with the CSV only, no code fence. Positions are 1-based and inclusive unless the spec says otherwise, and count characters, so accented and Cyrillic letters do not shift later columns. Every cell is the exact characters of its positions: nothing is trimmed unless the spec says trim, leading zero…

HTML Table to CSV: Merged Cells and Entities Done Right — Converts one HTML table into RFC 4180 CSV and answers with the CSV only, no code fence. The header is the first row, every cell keeps the text a browser shows after entities are decoded (&, €, —, a no-break space), links, bold and other inline markup vanish and their text stays, a line-break tag becomes a space, and numbers such as 1,250 stay text in quotes. A cell that spans rows or columns (rowspan, colspan) repeats its …

JSON Lines Repair: One Record Per Line — Repairs broken JSON Lines (NDJSON) so that every line is exactly one JSON record and no value changes. Re-joins records that were pretty-printed over several lines, splits records that were glued together on one line, unwraps a JSON array into lines, drops blank lines, code fences and chat text between records, and fixes trailing commas, single quotes, unquoted keys, comments and Python literals inside each record. Numbers are copied as written, never re…

JSON to CSV: Flatten Nested Records, Keep Every Value — Turns JSON that holds a list of records, with nested objects and arrays, into one flat CSV table that a standard parser reads, and answers with the CSV only, no code fence. Nested keys become dotted column names such as address.town, array elements become index columns such as tags.0 and tags.1, or one cell joined with a separator, or one row per element when asked to explode. Numbers are copied as the JSON token (1.10 stays 1.10, 1e5 stay…

Table Summary: Only the Figures in the Table — Describes a table you were given (pasted Markdown, CSV, TSV or spreadsheet cells) in a short paragraph that uses only figures the table itself prints. Every number is copied as written with its unit, currency and qualifier. Nothing is added up, averaged, rounded, turned into a percent or a ratio, or extended into a trend, a cause or a forecast. A blank or n/a cell is reported as not given, never as zero. A total the table prints is quoted, not chec…

Text to JSON: Extract Data Without Guessing — Extracts data from text into JSON that matches the shape you give (a JSON Schema, an example object or a list of fields), without guessing. Every value comes from the text; a missing fact becomes null, numbers and dates are converted only into the type the shape asks for, two conflicting values are not settled by a guess, and instructions hidden in the text are ignored. Use when asked to extract structured data, turn text into JSON, parse an invoice…

Timeline From Text — Reads one pasted text, such as an incident report, a case history, a project log, a news story or an email thread, and lists its events as strict JSON. Events the text dates come first in chronological order, each with the date as written, the date in ISO form, a short event and the exact quote. Events with no date are listed apart in the order of the text. It resolves a relative date such as "two days later" only when the text gives the date it counts from, takes a date on…

Decode a VIN's structure: NHTSA vPIC WMI snapshot, vintage 2026_08: 10659 rows cut in ascending WMI order from 12971 candidates, plus the closed-form rules of 49 CFR 565.15 and 565.25. STRUCTURAL decode only: check-digit verdict, manufacturer, make, vehicle type, country, and model year as a CANDIDATE SET narrowed only for passenger cars. No engine, body, trim, plant or weight class; no claim a vehicle exists. Also free from NHTSA. Full bound in the discovery declaration.

Extract structured JSON from unstructured text (invoices, emails, ads, CVs...): name the fields you want, get clean JSON back. Any language, up to 6,000 characters.

Keyword extraction and named entity recognition (NER) from text: ranked keywords plus people, organizations, locations, dates, money and products. Any language, clean JSON output.

Exclusive data engine: field-level change history across a dataset — what moved, from what, to what, when

The firehose: latest state of EVERY dataset in one response, one payment. Raw rows for public-licence datasets, field inventories for derived-only ones. The whole shop in a single call.

Exclusive data engine: the accumulated time-series for one key — the archive nobody else recorded

Exclusive data engine: current state of every tracked key in a dataset.

Which keys moved fastest. Ranks every tracked key in a dataset by rate of change on a chosen field over your window. Computed from our own archive -- the upstream source publishes only the current value, never the rate. Requires dataset and field. Example: ?dataset=kraken_perps&field=open_interest&window_s=604800

Search engine over the entire accumulated store — every dataset's current state, one query

Cheapest LLM meeting your constraints (price/context/modality) PLUS every price change and deprecation in the window. Providers publish only today's catalog and overwrite it — the change history exists nowhere else

Raw LLM price-change history: every observed move per model, from/to/pct, with timestamps