/ratchet-ship
Release runbook that takes verified local work to a green deploy — full local preflight, diff and secret review, push per the repo's convention, watch CI to completion, run the smoke checklist, and leave rollback notes. Use when the user says "ship it", "ratchet ship",
$ npx -y skills add afrizzal/ratchet --skill ratchet-ship --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/ratchet-ship
Context preview
The summary Claude sees to decide when to auto-load this skill.
Release runbook that takes verified local work to a green deploy — full local preflight, diff and secret review, push per the repo's convention, watch CI to completion, run the smoke checklist, and leave rollback notes. Use when the user says "ship it", "ratchet ship",
Verified, resumable engineering loops for Claude Code. A ratchet only turns forward. Every unit of work is gated by acceptance criteria and locked in as one atomic commit — the loop never slides back, never wanders off-spec, and never loses its place.
Repo: afrizzal/ratchet
Other skills on ratchet.
- /ratchet-audit
Deep multi-agent audit of the current codebase that ends in an executable artifact — ratchet/AUDIT.md (understanding + findings) and ratchet/BACKLOG.md (prioritized items with evidence, minimal specs, and runnable acceptance criteria, in ratchet:v1 format). Use when the user
Open skill - /ratchet-backlog
Create, validate, extend, groom, and migrate ratchet BACKLOG.md files — from TODO/FIXME comments, GitHub issues, a PRD/notes file, or plain conversation. Enforces the ratchet:v1 and ratchet:v2 contracts, especially the core invariant "no acceptance criteria, no item"; v2 adds
Open skill - /ratchet-loop
Execute a ratchet BACKLOG.md in a verified engineering loop — pick the next eligible item, implement exactly its spec, run its acceptance criteria until green (bounded attempts), lock it in as one atomic commit, update the ledger, repeat until the backlog is dry or a stop
Open skill - /ratchet-recommend
Turn a ratchet BACKLOG.md + Ledger into a prioritized, model-routed execution plan (ratchet/NEXT.md) — what to do next, who should do each item (an autonomous cheap model, a supervised cheap model, a senior model, or a human decision), in what order, and with what verification.
Open skill