Repository Issues

karminski/adversarial-verification-skill

An **adversarial verification** skill for general-purpose agents—especially weaker models—that tries to *break* completed work before you report success, reducing skipped checks, hallucinated results, shallow execution, and context drift.

View on GitHub
Stars
 (1 star)
Forks
 (0 forks)
Indexed issues
 (0 indexed issues)
open beginner issues
 (0 open beginner issues)
Latest indexed
Jul 20, 2026
Last GitHub push
Apr 1, 2026
License
No license data
Contributing guide
No contributing guide
Code of conduct
No code of conduct
Dominant language
No language data
PR merge metrics
 (PR metrics pending)
Beginner labels
No beginner labels indexed

Issues

0 open indexed issues

RSSAtom

No open indexed issues found for this repository.