Menu
SkillsMP a collecté 6 skills depuis jun0-ds/sonmat. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 6 skills collectés sur 6.
Main-side verification checks — pre-commit test / sensitive-file blocking, discipline conformance, novel-trap detection. Pure verify-and-flag; persistence of findings is scribe's job, intent-artifact match is witness's.
Langue du texte source : anglais
범용 자율 루프 — 기획→정의→실행→평가→판단→기록→반복. 에스컬레이션 판단 포함.
Langue du texte source : anglais
Punch list — completeness and residue check before delivery. Finds what's missing that should exist (omission) and what's left behind that shouldn't (refactor residue). Reconstructs intent, overlays domain checklist, scans for stale references.
Langue du texte source : anglais
Post-work persistence layer — observes completed work and writes what should outlive the session. Bridge notes, journal, progress, project rules discovered from user corrections, novel traps detected by guard, witness verdicts.
Langue du texte source : anglais
Devil's advocate for reasoning — discovery-led counter-arguments against interpretations, plans, and irreversible decisions. Locates the load-bearing assumption via CCT, then drives depth into the one axis where the claim is actually thin.
Langue du texte source : anglais
Trigger-reactive discovery-led depth — when a System 1 signal surfaces (blast radius, shared code, infra, auth, migration), pull depth into side-effect, dependency, assumption, and rollback checks. Not a mode; a reaction.
Langue du texte source : anglais