Ship
Take a finished local change through verification, UI checks, pull-request publication, CI and review follow-up, and the user-authorized merge outcome. Use when implementation is complete and the user says "ship it" or "get this merged," or as the final stage of $build. Do not use to implement new feature scope.From its SKILL.md
npx -y skills add magarcia/skills --skill shipAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.8 KB, 299 tokens by cl100k_base, as published. Nobody here has run it
Ship
Read the applicable AGENTS.md. Require a finished, cleaned diff or commits ahead of the intended base. If there is nothing to ship, ask for the missing scope.
- Run
$verifyto prove the behavior end to end and sweep relevant edge cases. - Run
$designwhen the diff touches a user-facing surface. - Run
$docsfirst when an externally produced change altered architecture, interfaces, commands, configuration, or documented workflows. - Run
$prto stage the confirmed scope, commit, push, and open the PR through the GitHub-backed publishing workflow. - Run
$babysitto monitor CI and review feedback through the terminal condition authorized by the user.
A blocking finding stops the pipeline. Fix it only when the requested scope authorizes that work, re-run the failed stage, and continue. Never carry a known-broken change forward.
- If
$verifyfinds a required behavior missing during$build, return to$implementwith a failing test and the no-commit constraint established by$build. In standalone$ship, report the missing implementation instead of expanding feature scope. - Re-run relevant tests after any stage changes code.
- Use collaboration subagents for noisy independent verification or monitoring work when available, and pass concise reports between stages.
- A request limited to opening a PR does not authorize merge. Enable auto-merge or merge directly only under
$babysit's explicit authorization rules.
What ships with it: 1 file
178 B alongside SKILL.md
agents/
- openai.yaml178 B
Gives 0 of the 12 instructions most ship operate skills give in 299 tokens
Counted across 779 of the 1,178 authors here whose files we hold, read 2026-08-07
- Document a rollback plan before deploymentin 41 of 779, across 22 files
- Update the changelogin 21 of 779, across 19 files
- Run the test suitein 20 of 779
- Create an annotated git tagin 20 of 779
- Clean up feature flags after full rolloutin 18 of 779, across 10 files
- Verify deployment health after launchin 18 of 779, across 10 files
- Test both feature flag statesin 17 of 779, across 9 files
- Verify the working tree is cleanin 17 of 779
- Make database migrations backward-compatiblein 16 of 779, across 8 files
- Set up error monitoring before launchin 15 of 779, across 7 files
- Monitor metrics at each rollout stagein 14 of 779, across 5 files
- Create a GitHub releasein 14 of 779
Said here and by no other author read
- read the applicable AGENTS.md
- require a finished diff ahead of the base
- ask for missing scope if nothing is ready
- run verify to prove behavior end to end
- run design when the diff touches user-facing surfaces
- run docs when architecture or interfaces change
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.