All authors
Claude Skills by jun0-ds
github.com/jun0-ds6 skills0 installs5 views
- Autoloop범용 자율 루프 — 기획→정의→실행→평가→판단→기록→반복. 에스컬레이션 판단 포함.Votes: 0GitHub stars: 6
- Devil요청된 계획·해석·판단에서 목적 달성을 좌우하는 가정을 검토하고 다음 선택에 도움이 되는 반론을 제시한다.Votes: 0GitHub stars: 6
- GuardMain-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.Votes: 0GitHub stars: 6
- InspectTrigger-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.Votes: 0GitHub stars: 6
- PunchPunch 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.Votes: 0GitHub stars: 6
- ScribePost-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.Votes: 0GitHub stars: 6