agentleFS
omdenkar2-uiomdenkar2-ui/all-in-one/skills/aio-ship/SKILL.md

aio-ship

Skill0 starsChanged 31 days agoMITView on GitHub

Deliver a verified backend change locally, through a requested PR, or to an authorized deployment target. Use for shipping after implementation/review or refreshing a PR description; follows exact-head CI and reports pending or blocked states truthfully.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Local: verify artifact presence, content/hash and reproducibility when relevant.

    line 12
  2. Very specific:

    Deployment/release: use AIO Release for an authorized target, built artifact, configuration/migration/rollback prerequisites and observed …

    line 14

≈ “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

AIO Ship

Deliver to the destination the user actually requested. Read delivery procedure. Shipping does not itself authorize merge, public release, destructive migration, or unrelated external messages. Preserve standing authorization and avoid repeated approval gates.

Resolve delivery mode from the accepted request: local artifact, PR, or an explicitly authorized deployment. For implementation delivery, verify the exact source and required review/check evidence with AIO Verify in implementation scope. Delivery may honestly be pending at this preflight. Once the requested destination is observed, completion scope can check the final receipt; an outer controller retains that final gate when present. A description-only request uses the actual diff and available evidence without claiming checks that have not run. Prepare a concrete build, scoped diff and reviewer-ready description before any genuinely required final authorization.

  • Local: verify artifact presence, content/hash and reproducibility when relevant. Record paths and limitations. No remote configured means truthful local delivery, never an invented PR or failed attempt to publish elsewhere.
  • PR: use AIO Commit for canonical owned changes; inspect actual repository/head/base/remote and matching PR presence. Create only when requested/inherited shipping intent authorizes it. After successful creation, attach the PR with the host artifact tool. Use AIO CI for exact-head required checks and feedback follow-through within the requested watch budget.
  • Deployment/release: use AIO Release for an authorized target, built artifact, configuration/migration/rollback prerequisites and observed health. Launch-store review applies only when mobile submission is in scope.
  • Description-only: draft the title/body from the actual diff and evidence; edit the remote description only if requested. Do not commit/push because a PR URL was provided.

Return distinct observed states: local delivered, PR created with CI passed/pending/failed/attention, deployment healthy/failed/unknown, or blocked. A PR URL is not green CI; merge-ready is not merge authorization. When called by Complete Destruction, return delivery evidence and residuals to its single controller rather than rerunning implementation or closing its receipt independently.

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.