eltociear-skill-audit.hf.space

Run a chat completion against an open-weight 20B-class model — plain prompt in, text out, with automatic failover across independent inference backends so a single call still answers when any one provider is down or rate-limiting

Fetch a URL and grade its HTTP security headers (HSTS, CSP, X-Frame-Options, etc.)

What does the open web say about this query? Ranked title/url/snippet results for agents, served through an automatic multi-engine failover chain so a single call still answers when any one backend is blocked, rate-limited or timing out from a datacenter IP.

Turn messy text — or any URL's page content — into structured JSON matching the shape you ask for, so an agent can consume a web page as data instead of prose

How high above sea level is this point? Ground elevation in metres for a place name or a coordinate pair

What are this country's headline economics? World Bank time series for GDP, GDP per capita, population, inflation, unemployment, life expectancy, CO2 per capita or internet penetration, by plain-English alias or raw indicator code

Which earthquakes have just happened? Recent USGS events worldwide or within a radius of a named place, with magnitude, depth, tsunami flag and felt reports

Turn a place name into coordinates, country, admin region, timezone, elevation and population — the lookup every other location-aware call needs first

How breathable is the air in this place right now? Current PM2.5, PM10, ozone, NO2, SO2, CO and dust plus both the US and European AQI, and the US AQI band ('Good', 'Unhealthy') so the number is directly actionable. Takes a place name, not coordinates

Which days are public holidays in this country? Full year of national and regional holidays with local names and a past/upcoming flag — date arithmetic an agent cannot infer from a calendar alone

Fetch a URL and return its main content as clean Markdown (boilerplate stripped)

Resolve a domain's DNS records (A/AAAA/MX/NS/TXT/CNAME) and flag basic email/security posture

Fetch up to 10 URLs concurrently and return each as clean Markdown (bulk rate)

Enumerate a site's URLs from robots.txt + sitemap.xml (sitemap-index aware) — map a domain before crawling it

Scan an entire public GitHub repo for malicious AI-skill/supply-chain patterns

Vet an x402 server or any URL for scam/phishing/trust in ONE call: transport, content-safety, domain, metadata + x402-compliance sub-scores, each with transparent evidence

Crawl a site from a start URL (same-domain, breadth-first) and return each page as clean Markdown

Fetch a PDF by URL and return its text as Markdown-ish plain text, page by page

Extract structured metadata from a page: title, description, OpenGraph, JSON-LD, headings, links

Parse an RSS/Atom feed into structured items (title, link, published, summary) — or auto-discover the feed from a site URL

Audit text for malicious AI-skill patterns