agentleFS
merllinsbeardmerllinsbeard/merlin-skills/skills/ship/SKILL.md

gstack-ship

Skill1 starsChanged 6 months agoMITView on GitHub

Merlin-adapted ship gate for spec-kit/create-goal work. Use when implementation and QA evidence are ready and the user asks to package, commit, push, release, or deploy.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Use when the user says the work is ready to ship, asks to create a PR, push changes, tag a release, or deploy.

    line 13
  2. Very specific:

    Do not use when implementation is still incomplete.

    line 15
  3. Distinctive:

    Before mutating release state, verify:

    line 29
  4. Distinctive:

    If any gate fails, stop and report the blocker.

    line 38
  5. Distinctive:

    Run the minimum relevant checks again if they are cheap.

    line 43
  6. Distinctive:

    Update release metadata only when appropriate for the repo.

    line 44
  7. Distinctive:

    Commit with explicit path selection.

    line 45
  8. Distinctive:

    Verify the remote state after pushing or releasing.

    line 47

≈ “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

gstack-ship

Ship only after the spec/goal has proof. This skill is adapted from gstack ship, but it is standalone: do not call gstack runtime helpers, telemetry, review specialists, gbrain, or deploy automation unless the repo already owns that command.

When To Use

Use when the user says the work is ready to ship, asks to create a PR, push changes, tag a release, or deploy.

Do not use when implementation is still incomplete. Route to gstack-qa, tdd, or diagnose first.

Inputs

Inspect, in order:

  1. User's newest ship instruction.
  2. Current branch, git status, and git diff.
  3. Active specs/<feature>/GOAL.md, tasks.md, plan.md, and spec.md when present.
  4. Latest QA report or verification evidence.
  5. Repo instructions in AGENTS.md, README.md, release docs, CI config, package scripts, and deploy docs.

Ship Gate

Before mutating release state, verify:

  1. The work matches the active spec/goal or the user explicitly scoped a diff-only ship.
  2. Relevant tests and checks pass.
  3. gstack-qa evidence exists or the user explicitly waived QA.
  4. The diff contains no unrelated changes you would accidentally commit.
  5. Version, changelog, release notes, and docs are updated when the repo's release policy requires them.
  6. The user has allowed the requested side effect: commit, push, PR, tag, release, merge, or deploy.

If any gate fails, stop and report the blocker.

Workflow

  1. Summarize the exact diff that will ship.
  2. Run the minimum relevant checks again if they are cheap.
  3. Update release metadata only when appropriate for the repo.
  4. Commit with explicit path selection. Never use git add ..
  5. Push, tag, create PR, create GitHub Release, merge, or deploy only when requested or clearly part of the current repo's established ship flow.
  6. Verify the remote state after pushing or releasing.

Output

End with:

Ship Result: shipped | ready-not-pushed | blocked
Commit: <sha or none>
Remote: <branch/tag/pr/release/deploy URL or none>
Verification: <commands and evidence>
Residual risk: <short list or none>

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.