Clean

Gate a fine-tuned checkpoint before it ships, then plan its export. Paste the drift-suite table (baseline and checkpoint per benchmark, item counts, seed reruns), the target-task metric, the data checks and the paired-arena tally: free in your browser, the four-stage gate runs with the <=1 / 2-5 / >5 pt drift budget, 95% half-widths, REJECT (uncertain), a Wilson arena interval and a canary for production, ending in PROMOTE, REJECT or RERUN with one remediation; for a PROMOTE, the export format for your hardware and workload with sizes. A metered run writes the promotion report or the export plan with commands and a smoke test. Built on the SkillSafe skills @wshobson/checkpoint-promotion and @wshobson/quantized-export.

promote-desk.skillsafe.ai
PricingUsage-based + 10% creator margin
Billed model rate$2.20 in / $13.20 out per 1M tokens
Creator margin+10%
Effective rate$2.40 in / $14.40 out per 1M tokens
Security scanClean — skill and frontend scanned
Model gpt-terra
Created2026-10-29
Updated2026-11-04

Every public app is built from a security-scanned skill and must pass a clean scan — skill and frontend — before it can be listed. Have a skill of your own? Turn it into an app — or read the step-by-step walkthrough.

Share