agentic-jujutsu

SKILL.md

Quantum-ready, self-learning version control designed for multiple AI agents working simultaneously without conflicts.

| new JjWrapper() | Create wrapper instance | JjWrapper | | status() | Get repository status | Promise | | newCommit(msg) | Create new commit | Promise | | log(limit) | Show commit history | Promise | | diff(from, to) | Show differences | Promise | | branchCreate(name, rev?) | Create branch | Promise | | rebase(source, dest) | Rebase commits | Promise |

| startTrajectory(task) | Begin learning trajectory | string (trajectory ID) | | addToTrajectory() | Add recent operations | void | | finalizeTrajectory(score, critique?) | Complete trajectory (score: 0.0-1.0) | void | | getSuggestion(task) | Get AI recommendation | JSON: DecisionSuggestion |

Contrôle de version à auto-apprentissage et résistant aux quantiques pour les agents IA avec l'intelligence ReasoningBank et la coordination multi-agents Source : chrislemke/stoffy.

Voir l'original