jujutsu-workflow
Use when a coding agent works in a repository where Jujutsu (jj) is available (a .jj/ directory) — running jj commands, making speculative edits, splitting changes, recovering with the operation log (jj undo / jj op restore), handing off a PR to Git/GitHub/GitLab, updating a PR after review, or coordinating parallel agents. Uses jj as the local change-management layer while keeping Git as the canonical remote, PR, CI, and audit interface. Also use to avoid jj's agent footguns (pager/editor hangs, commit absorption, colocated git/jj desync) or to replace fragile git reset/checkout/stash/rebase recovery with reversible jj operations.
- Version
- 0.3.2
- License
- (MIT AND CC-BY-SA-4.0). See LICENSE-MIT and LICENSE-CC-BY-SA-4.0
- Compatibility
- Verified against jj 0.42.0 and 0.43.0. Re-check flags with `jj <cmd> --help` on other versions.
Pinned to revision 2a38be2e3c29, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/jujutsu-workflow/SKILL.md
- skills/jujutsu-workflow/references/agent-safety.md
- skills/jujutsu-workflow/references/command-map.md
- skills/jujutsu-workflow/references/git-interop.md
- skills/jujutsu-workflow/references/parallel-agents.md
- skills/jujutsu-workflow/references/pr-handoff.md
- skills/jujutsu-workflow/references/recovery-playbook.md
- skills/jujutsu-workflow/references/why-jj-for-agents.md
- skills/jujutsu-workflow/scripts/detect_jj_state.sh
- skills/jujutsu-workflow/scripts/verify_handoff.sh
Every link opens the file at its source, pinned to the revision this page describes.