tmusser/ai-engineering-skills / skills/ship-mini
ship-mini
VerifiedRun a lightweight activation GO or NO-GO gate only when verified work is about to gain material real-world side effects, autonomy, permissions, or production/shared-state impact.
Ship Mini
Purpose
Decide whether verified work is safe and authorized to activate in a real operating environment.
verify-contract owns correctness and evidence. ship-mini does not re-verify the implementation; it owns the additional operational question: should this verified thing be allowed to act on the world now?
When to use
Use after verification when activation introduces one or more material operational risks:
- production or shared-state writes
- scheduled, autonomous, or unattended execution
- sending, publishing, triggering jobs, or other external side effects
- new or expanded tool permissions
- secrets, credentials, PII, or sensitive-data access
- destructive or difficult-to-reverse actions
- a required human approval boundary
- a meaningful rollback, audit, or owner-notification requirement
Skip ship-mini for ordinary local or interactive changes whose effects remain reviewable and reversible. A user-facing change, shared report, dashboard update, model result, or successful verify-contract does not require ship-mini merely because it may be released or seen by others.
Do not create SHIP.md when no material activation risk exists.
Inputs
VERIFY.mdstatus and evidence reference- What will be activated and where
- Allowed tools / actions
- Forbidden tools / actions
- Target environment or shared state
- Destructive or irreversible operations
- Secrets, credentials, PII, or sensitive-data scope
- Dry-run or staged activation path when relevant
- Human approval gates
- Audit logging
- Rollback / disable path
- Owner notification
- Stop conditions
- Optional operator profile
Autonomy boundary
Workflow
- Confirm the implementation already has sufficient verification evidence. Reference
VERIFY.md; do not replay correctness checks merely becauseship-miniis invoked. - Classify activation risk:
NONE— no material side effect, autonomy, permission, data, or rollback boundary exists. Stop without creatingSHIP.md.PRESENT— one or more material activation risks exist. Continue.
- Name the exact activation surface: what will run, write, send, publish, trigger, access, or mutate, and in which environment.
- Record allowed and forbidden actions, permission/data boundaries, destructive operations, and required human gates.
- If an operator profile is available, apply its
Autonomy boundaryas an additional ceiling.propose-onlyorhuman-gate-side-effectsmay require an earlier human gate.bounded-executiondoes not grant activation permission; it only means the profile itself adds no stricter gate inside already-authorized bounded work. - Confirm the smallest practical dry-run or staged activation path when one exists.
- Confirm rollback or disable path before irreversible or shared-state effects are enabled.
- Confirm audit logging, owner notification, and stop conditions when unattended or externally visible effects are possible.
- Resolve any
REVIEW_REQUIREDverification item that affects activation safety. A functionalFAILcannot be shipped. - Create or update
SHIP.mdwith the activation decision and only the operational evidence needed forGO/NO-GO.
Do not rerun tests, builds, lint, data-quality checks, or model validation unless activation changed the environment or inputs in a way that invalidates the existing verification evidence.
Activation gate
Status: GO | NO-GO
GOonly when verification is trustworthy for the activated state and every material activation boundary is explicit enough to operate safely.- An operator profile may make the activation gate stricter, but it cannot authorize a side effect, permission, or deployment that the task and runtime did not already allow.
NO-GOwhen a required approval, permission boundary, data boundary, rollback path, audit path, owner notification, or stop condition is unresolved.NO-GOwhen verification isFAIL.REVIEW_REQUIREDverification may proceed only after a human explicitly resolves or accepts the item and it does not hide a functional failure.
Outputs
When activation risk is PRESENT:
SHIP.md- GO / NO-GO decision
- Activation surface
- Operational blockers
- Accepted operational risks
- Human gates
- Rollback / disable path
- Audit / notification / stop conditions when relevant
When activation risk is NONE:
- No
SHIP.md - Continue from verification to the next appropriate workflow step
Stop conditions
- Activation risk is
NONE; skip the skill artifact. GOis recorded with operational boundaries explicit.NO-GOis recorded because a material activation boundary remains unresolved.
Anti-patterns
- Running
ship-miniafter every successfulverify-contract. - Re-running correctness checks already captured in
VERIFY.mdwithout evidence they became stale. - Treating ordinary release, sharing, or visibility as activation risk by itself.
- Creating
SHIP.mdwhen no material side effect or operational boundary exists. - Shipping autonomous or external side effects without approval, rollback, audit, or stop conditions appropriate to the risk.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |