Ship
Execute one reviewed action with exact candidate binding, explicit authority, rollback readiness, and independent readback.From its SKILL.md
npx -y skills add menot-you/n-soul --skill shipAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 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
1.9 KB, 348 tokens by cl100k_base, as published. Nobody here has run it
Ship
Use only when implementation and required review are complete. Shipping means producing the intended real-world result and proving it, not merely preparing a command. The surface stays one action, one verification, one rollback path, one result.
Inputs to lock
- Exact reviewed candidate identifier and immutable digest when available.
- Target environment and action.
- Green required checks and review verdict.
- Authority for the action.
- Rollback command, data recovery need, and stop conditions.
- Independent post-action verification.
Method
- Re-read candidate, target, current state, and authority immediately before the action.
- Confirm the candidate being executed is byte-for-byte the reviewed candidate.
- Confirm required checks are green and no new change invalidated review.
- Verify credentials, target, backups, capacity, and rollback without exposing secrets.
- State the action boundary: what will change and what will not.
- Execute one action once.
- Read back authoritative state and run the independent smoke check.
- If the result is ambiguous, determine whether the target changed before any retry.
- On failed acceptance, stop further rollout and use the prepared rollback when its trigger is met.
- Record candidate, target, proof, result, rollback status, and any remaining gap.
Stop conditions
Stop before the action on candidate drift, failed check, missing authority, unknown target, unavailable rollback, or missing verification. Stop after the action on ambiguous state or failed acceptance; never repeat blindly.
Completion requires observed target state and independent verification. A merged branch is not a release; a completed release job is not proof of user reachability. Close with the result, proof, rollback status, and remaining blocker only.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most ship operate skills give in 348 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
- lock the reviewed candidate identifier and digest
- verify required checks are green before acting
- verify authority, target, and rollback readiness
- state the action boundary explicitly
- execute one action once
- read back authoritative state after the action
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.