agentleFS
Sign inStart free
OutThisLifeOutThisLife/brooklyn-skills/skills/ticket-ship/SKILL.md

ticket-ship

Skill207 starsChanged 4 months agoMITView on GitHub

Take a tracker ticket through to shipped: find or start the PR, drive it to mergeable, update the ticket state, draft the stakeholder message. Use for Jira/Linear (or acli) tickets assigned to you.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Don't send it unless asked.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ticket → Ship

The ticket-shaped parts of shipping. The PR mechanics live in their own skills — this is what a tracker adds on top.

Steps

  1. Read the ticket and its latest comments, then list existing PRs before starting (acli, Jira, Linear, gh). With acli, request --fields summary,description,status,comment,issuelinks --json: the default view omits comments, which can contain reopened QA scope. Read the existing PR diff as well as its body; follow-up commits can invalidate the body's implementation claims.
  2. Confirm the correct base branch(es) before starting — some orgs need a release branch plus the default (stacked-pr). Never assume; verify the org's rule.
  3. Find the existing PR or start one (work → pr-update), then drive it mergeable (pr-ready) and polish before handoff (clean).
  4. Read the repository's ticket/label guidance before selecting a handoff state; don't substitute generic workflow names. In MR, use .claude/skills/create-pr/SKILL.md and teams.md for label rules. For an existing DOTCOMPB PR returned by QA and then fixed, the user's retest handoff is In Test with Pending QA Review, not a reset to In Code Review. Preserve the ticket-driven Needs UI Review label. Report CI/deployment blockers separately; In Test does not mean merge-ready. Link the PR and add a factual retest update when the user requests the handoff.
  5. Draft the stakeholder update — Slack or a ticket comment, short, no-tropes. Don't send it unless asked.

Don't

  • Assume the base branch.
  • Mark the ticket done while CI is red or review threads are open.
  • Let the ticket and the PR tell different stories about the state of the work.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free