Loading...
Loading...
Found 29 Skills
NCAP five-star crash ratings for a model year, make and model: overall, frontal, side and rollover, with recall, complaint and investigation counts. Called as GET /v1/nhtsa/safety-ratings, it takes modelYear, make, model and returns found, variants, truncated. Crash-test scores are per body style and drivetrain, not per model, so an agent comparing vehicles needs the tested variant rather than a remembered headline number. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.004, paid in USDC on Base over x402.
The UTC offset, abbreviation and DST state a zone was on at any moment from 1970, with the surrounding transitions, and resolution of ambiguous or nonexistent local times. Called as GET /v1/tz/offset-at, it takes timezone, instant, localTime and returns timezone, utcOffset, isDst, resolution. An agent scheduling or reconciling timestamps must know that 01:30 on a fall-back night happens twice and 02:30 on a spring-forward night never happens at all; fixed offset arithmetic silently books the wrong hour. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.004, paid in USDC on Base over x402.
Parses a BCP 47 language tag into language, extlang, script, region, variant, extension and private-use subtags, validates each against the IANA registry, and returns the canonical form. Called as GET /v1/lang/bcp47, it takes tag and returns valid, canonical, language, errors. Locale strings arrive from users, feeds and file names, and a wrong one silently mis-routes content rather than failing. Checking a tag properly means holding a 730KB registry and implementing the RFC 5646 grammar; almost nobody does either, so tags like en-UK and zh-CN-Hans ship broken. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.003, paid in USDC on Base over x402.
Create, debug, or modify QStash workflows for data updates and social media posting in the API service. Use when adding new automated jobs, fixing workflow errors, or updating scheduling logic.
美股市场全量数据服务。编排美股所有细粒度 skill：实时行情、K线、基础数据、技术指标。 当用户提及"美股""纽交所""纳斯达克""苹果""特斯拉"且未明确指定数据维度时触发。
Pulls DOIs, arXiv ids, PMIDs, PMCIDs and ISBNs out of free text, deduplicated and normalized, with the character offset of each first occurrence. Called as POST /v1/text/extract-citations, it takes text, kinds and returns count, citations, byKind. An agent handed a references section, an email or a PDF dump has to find the identifiers before it can look any of them up, and a model asked to do it by reading invents DOIs that resolve to nothing. The catalog already answers `crossref.doi-metadata` and `pubmed.citation-search`; neither could tell you what to ask them about. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.003, paid in USDC on Base over x402.
Fetch a public web page and return it as clean Markdown with its title. Capped at 2 MB. Called as GET /v1/doc/url-to-markdown, it takes url and returns sourceBytes, title, markdown, characters. This is the third-highest-demand category observed on-chain: an agent given a link needs the readable text, not the markup, and cannot run a browser itself. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.003, paid in USDC on Base over x402.
Fetch a public URL and return its title, description, preview image, site name and canonical URL from its meta tags. Called as GET /v1/doc/url-metadata, it takes url and returns bytes, found, title, description. A publishing, chat or bookmarking agent asked to render a link preview needs the card fields without shipping an HTML parser or a headless browser into its runtime. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.003, paid in USDC on Base over x402.
Insert, delete, replace, extract, locate or measure at exact character offsets, counting by grapheme, code point or UTF-16 unit, with the affected range reported in both the chosen unit and UTF-16. Called as POST /v1/text/char-edit, it takes text, op, unit, index and returns op, unit, text, inputLength. Character-indexed string edits are a measured failure mode for language models (arXiv:2409.15452), and the index a model reasons about is rarely the index a runtime uses: a skin-toned emoji is one grapheme, two code points and four UTF-16 units, so an offset is wrong until the unit is named. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.003, paid in USDC on Base over x402.
Score text from -1 (strongly negative) to +1 (strongly positive) with a label, handling negation, intensifiers and emphasis. Called as POST /v1/text/sentiment, it takes text and returns score, label, matches, positiveTerms. A support-triage or review-monitoring agent must decide whether a message is a complaint before it routes or escalates it, and a model call for one number costs more than this and is not reproducible. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.004, paid in USDC on Base over x402.
Convert an HTML document supplied in the request body to clean Markdown, stripping scripts and styles. Called as POST /v1/doc/html-to-markdown, it takes html and returns markdown, characters, inputBytes. A research agent handed raw HTML must reduce it to readable text before it can reason over it, and passing full markup through a model wastes most of the context window. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.004, paid in USDC on Base over x402.
加密货币市场全量数据服务。覆盖 K线、持仓、爆仓、资金费率、多空比、CVD/买卖、ETF、 市场指标（恐惧贪婪/AHR999等）、新闻、巨鲸追踪、大额订单、排行榜、订单簿、资金流等。 当用户提及"BTC""比特币""以太坊""加密货币""合约""资金费率""爆仓""持仓量""恐惧贪婪指数"时触发。