are-we-done
[Adam''s Skills] Deterministic close-out gate for a session or work tree. Sweeps a fixed set of sources — the todo list, this…
[Adam''s Skills] [skips confirmation] The unattended form of /ship-it. Gets this conversation''s work merged and deployed to every environment the repo has, production included — and does NOT stop to confirm when the release also carries unreleased work by other developers or
Claude Code
$ npx -y skills add adamlinscott/claude-skills --skill ship-it-now --agent claude-code
Codex
$ npx skills add adamlinscott/claude-skills --skill ship-it-now -a codex -y
Cursor
$ npx skills add adamlinscott/claude-skills --skill ship-it-now -a cursor -y
Gemini CLI
$ npx skills add adamlinscott/claude-skills --skill ship-it-now -a gemini-cli -y
GitHub Copilot
$ npx skills add adamlinscott/claude-skills --skill ship-it-now -a github-copilot -y
OpenCode
$ npx skills add adamlinscott/claude-skills --skill ship-it-now -a opencode -y
Windsurf
$ npx skills add adamlinscott/claude-skills --skill ship-it-now -a windsurf -y
name: ship-it-now description: '[Adam''s Skills] [skips confirmation] The unattended form of /ship-it. Gets this conversation''s work merged and deployed to every environment the repo has, production included — and does NOT stop to confirm when the release also carries unreleased work by other developers or other agent sessions. Identical to /ship-it in every other respect: same grounding in branches, PRs and environments, same verification, same merge-conflict policy. Takes no arguments by default; an optional scope override such as "only staging" limits which environments it deploys to. Invoke with /ship-it-now when you already know what is on the target branch and do not want to be asked.' disable-model-invocation: true allowed-tools: Bash, Read, Grep, Glob, AskUserQuestion, Agent
Same skill as `/ship-it`, with the ride-along confirmation gate turned off.
**Read `../ship-it/SKILL.md`, relative to this file, and follow it in full** — with exactly these two changes:
1. **Section 4 does not gate.** Do not call AskUserQuestion about other people's changes and do not wait for an answer. Still *print* the short summary of whose work is riding along, before the deploy, so it is on the record — then continue straight through to production.
2. **Say so up front.** The first line of your output names what this is: shipping to production without confirmation. The user typed `-now`; they should still see what that bought them.
Everything else is unchanged, and deliberately so. Grounding in section 1 still happens in full — skipping confirmation is not permission to skip *knowing*. The merge-conflict policy in section 6 still stops for a genuine divergence of intent; that gate protects the code, not the user's attention, and `-now` does not lift it. Verification in section 5 is still required: an unattended ship is exactly the case where nobody else is watching whether it landed.
If `../ship-it/SKILL.md` is not readable from here, stop and tell the user to install `/ship-it` alongside this one. Do not improvise the workflow from this file: everything that makes shipping unattended safe — the grounding, the verification, the conflict policy — lives over there.
Each skill lives under skills//SKILL.md, and each agent under agents//.md. These are the single source of truth: an install script links them into ~/.claude/skills/ and ~/.claude/agents/ so Claude loads them in every session, on every machine.
[Adam''s Skills] Deterministic close-out gate for a session or work tree. Sweeps a fixed set of sources — the todo list, this…
[Adam''s Skills] DEPRECATED — superseded by /build-it. Do not use for new work. Surfaced the load-bearing assumptions behind a…
[Adam''s Skills] DEPRECATED — superseded by /where-are-we. Do not use for new work. Printed a plain-English re-entry briefing for…
[Adam''s Skills] Build a piece of work, from wherever it is written down — a ticket number or URL, a plan or spec file, the plan…
[Adam''s Skills] Check whether the installed copy of this skills collection is behind its remote, and offer to update it. Runs a…
[Adam''s Skills] Audits a repository''s Claude context-injection setup — CLAUDE.md, CONTEXT.md, docs/, .claude/agents/, and the…
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress…
Set up the owner profile so a personal agent knows who it works for (first-run setup, \"get to know me\"), or distill colleague,…