Is this domain legitimate? WHOIS age, DNS resolution, scam/phishing search results, and HTTP headers for a quick trust assessment. Brand protection skill pack: one x402 payment runs 4 underlying tools (whois, dns-lookup, search, http-headers); partial-success per step.

Turn a wall of dirty text - chat logs, scraped pages, user-generated content, log dumps - into something safe to store, search, and pipe into the next step. Measure first, redact PII before anything else touches the data, then dedupe, sort, extract entities, surface keywords, and grade the readability of what's left. Text hygiene skill pack: one x402 payment runs 7 underlying tools (text-stats, redact, dedupe-lines, sort-lines, extract-entities, keywords, readability); partial-success per step.

Dated crypto catalysts (unlocks, mints, listings, macro) with a long/short bias and 0-1 magnitude each.

Base gas price — Live Base mainnet gas price from JSON-RPC.

Realized volatility for an asset: daily and annualized %, plus a low/normal/high/extreme bucket and the 24h high/low/range. Use to size positions and set expectations. Backward-looking (realized), not implied/option vol.

Generate an image from a text prompt at a flat price per picture, no token math and no subscription: the OpenAI images request shape in, base64 PNG or JPEG out, with an automatic fallback model so a provider outage does not become your error. Use it when an agent needs a picture cheaply and predictably.

Fuzzy-search Japanese (JP) train stations by name — accepts kanji, kana, or romaji and tolerates the 駅/station suffix. Returns matching stations with their operators and lines. Use to resolve a station name to a canonical record.

Multi-timeframe RSI oversold check (1h/4h/1d, weighted) returning a boolean + the blended RSI. Use to confirm an oversold condition across timeframes rather than trusting a single chart. RSI-based, not a buy signal on its own.

Convert kanji-mixed Japanese (JP) text to hiragana, katakana, or romaji (Hepburn/Nippon/Passport), with a per-token breakdown of surface form, reading, and part-of-speech. Backed by the kuromoji morphological analyzer. Use to generate ruby readings, build search indexes, or preprocess text for speech synthesis.

Turn any PDF or image URL into structured data - metadata, extracted text, sliced page ranges, OCR for scanned docs, decoded barcodes / QR codes - without falling back to a vision LLM guess. Built for the messy 30% of documents where pdf-to-markdown alone returns nothing useful. Document intelligence skill pack: one x402 payment runs 7 underlying tools (pdf-info, pdf-to-markdown, pdf-extract-pages, image-ocr, barcode-decode, pdf-merge, images-to-pdf); partial-success per step.

Search audiobookbay.lu for audiobooks. Returns up to ~12 result entries with slugs that can be passed to /api/audiobooks/details for magnet links.

Check whether a domain's TLS/SSL certificate is valid, trusted, and not expiring before connecting to it. Performs a live handshake and returns a 0–100 score and tier (VALID/WEAK/EXPIRING/EXPIRED/UNTRUSTED/INVALID) with chain trust, days-to-expiry, signature algorithm, TLS version, and cipher quality. Use before submitting credentials, posting to a webhook, or following a payment link, to catch expired, self-signed, or MITM-risk certificates.

Look up a product by its UPC/EAN barcode number via Open Food Facts (open data): name, brand, category, quantity, and nutrition grade. Pairs with /api/barcode-decode (image → number → product).

Search public Certificate Transparency logs for every cert issued to a domain. Two independent public CT search services are queried, the second only if the first is slow or fails, and `source` names the one that answered (their coverage windows differ). Returns the cert list plus a deduped subdomain set extracted from the SANs - the fastest way to enumerate subdomains for a security audit. No key required.

Payment memos attached to B20 transfers: pairs each Memo(address,bytes32) log with its Transfer at the previous log index (same tx, same token). Give a tx hash for one transaction, or scan a block window. Returns memoHex always and memoText when printable UTF-8.

ERC-20 metadata plus B20 signals for any Base address: name, symbol, decimals, total supply, best-effort paused/cap, bytecode size, and whether the address carries the factory-issued 0xB200 prefix. Works on plain ERC-20s too (isB20 comes back false).

Plan a multi-stop journey deterministically: geocode each stop, sum the pairwise haversine distances, estimate arrival times by adding driving hours per leg, count business days from today to each arrival, and pull the weather forecast at every US stop. Six tools - three pure-CPU (math + time), three egress (geocoding + weather) - covering the deterministic skeleton of every road-trip / sales-tour / delivery-route planning problem.

Global crypto market snapshot: total market cap, total 24h volume, BTC dominance, ETH dominance, active coin count, active exchange count, and 24h market-cap change %. Returned in a chosen vs_currency (default usd). Data provided by CoinGecko.

Every transaction receipt in one block, fetched as a single upstream read and summarized: tx count, succeeded vs failed, total gas used, total fees, log count, contract creations, tx-type mix - plus compact per-transaction rows (hash, from, to, status, gas used, effective gas price, fee, log count) capped at 300. Block analytics, failed-tx hunting, or 'who paid what in block N' without N separate receipt calls.

Resolve a name or ticker to coin ids: full-text search returning matching coins (id, symbol, name, market cap rank, ordered by rank), exchanges (id, name, market type) and categories (id, name), plus NFT collections. `limit` per group 1-50 (default 10). The id resolver for every other coin tool: an agent holding "PEPE" or "render" gets the canonical id here before calling coin-profile, coin-ohlc or coin-history. Cached in-process for 5 minutes. Data provided by CoinGecko.