jj-stacked-pr
Manage pi-jj stacked PR workflows safely. Use when the user wants jj stack status, PR planning, or publishing/updating stacked PRs with GitHub.
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 16
- Forks
- 9
01 前言 Front Matter
- name
- jj-stacked-pr
- description
- Manage pi-jj stacked PR workflows safely. Use when the user wants jj stack status, PR planning, or publishing/updating stacked PRs with GitHub.
03 SKILL.md 正文
JJ Stacked PR Flow
Use this skill for stack-aware PR workflows in repos using the pi-jj extension.
Goals
- Inspect stack state before publishing.
- Prefer safe dry-run behavior first.
- Publish/update stacked PRs only after explicit user confirmation.
Preferred execution path
Use the jj_stack_pr_flow tool first (it executes the matching command directly by default):
action: "status"→/jj-stack-statusaction: "plan"(optional) →/jj-pr-plan ...when the user wants explicit base/head mapping reviewaction: "publish", dryRun: true→/jj-pr-publish --dry-run ...- Ask user to confirm real publish
action: "publish", dryRun: false(optionaldraft) →/jj-pr-publish ...action: "sync"→/jj-pr-sync ...to refresh PR state/labels- after all PRs are merged, optional closeout:
action: "close"→/jj-stack-close --dry-runthen/jj-stack-close
Safety rules
- Do not publish non-dry-run unless user explicitly asks.
- If repo is not initialized for jj, run
action: "init"(or ask user first if uncertain). - If publish fails due to auth, instruct user to run
gh auth login. - After publish, summarize PR numbers/URLs and next actions.
Fallback (if tool unavailable)
Run slash commands directly in this order:
/jj-stack-status
# optional when user wants explicit plan output
/jj-pr-plan [--remote origin]
/jj-pr-publish --dry-run [--remote origin]
# after explicit approval
/jj-pr-publish [--draft] [--remote origin]
/jj-pr-sync [--remote origin]
# after all PRs are merged (optional cleanup)
/jj-stack-close --dry-run [--remote origin]
/jj-stack-close [--remote origin]
04 同仓库更多 Skills
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
unslop
Cut AI tells from any writing.
typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /skill:technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
teach
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
tdd
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.