hail-claim-verification — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited hail-claim-verification (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Goal: produce a defensible corroborated / partially corroborated / not corroborated verdict for a hail claim at a specific location and date, with the evidence and its distance/time from the claimed loss.
Reminder: SHEARLINE data is informational and preliminary (NWS/spotter reports), not a legal adjudication or the final NCEI Storm Events record. State that in the output.
lat, lon (decimal degrees,CONUS only; longitude is negative in the US).
YYYY-MM-DD. If theclaimant gives a local date/time near midnight, check the adjacent UTC day too.
get_historical_storm_reports(lat, lon, date, radius_km=40)
data.counts.hail and the data.reports entries with category: "hail".magnitude (inches), time_utc, and distance_km /direction from the claim location.
get_mrms_severe(lat, lon, radius_km=40)
data.hail_mesh.max_mesh_in is the radar Maximum Estimated Size of Hail in thelast hour, with the distance/bearing of the maximum. (MRMS only retains ~24–48 h, so this step applies to recent claims only; for older dates rely on step 1.)
radius_km=80 to see whether a hail swath passed nearby (hail is highly localized; a report 30 km away is weak support).
hours of the claimed time, of comparable or larger size.
smaller size than claimed.
pre-2005 dates aren't covered, and an empty old-date result is not proof of a quiet day).
Hail-claim verification — <address> (<lat>, <lon>), <date> UTC
Verdict: <corroborated | partially corroborated | not corroborated>
Evidence:
- <n> hail report(s) within 40 km; largest <size>" at <time_utc>, <dist> km <dir>
- [if recent] MRMS MESH max <x>" (<dist> km <dir>) in the last hour
Nearest report to the loss: <size>" at <time_utc>, <dist> km <dir>
Caveats: preliminary NWS/spotter + radar data; not the final NCEI record;
hail is localized so distance matters.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.