agentleFS
nuncaeslupusnuncaeslupus/literary-critic/.claude/skills/ship/SKILL.md

ship

Skill0 starsChanged 6 days agoMITView on GitHub

Confirms a change is production-ready — compatibility, tests, observability, rollback. Use when the user wants release sign-off. Not for PR review (review).

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ios-sync, open-gstack-browser and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Saqlain-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 6 projects that use this

  • seek888Skill

    open-gstack-browser

    Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".

    Also in 10 projects that use this

  • ayudaySkill

    setup-deploy

    Configure deployment settings for /land-and-deploy. Detects your deploy platform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom), production URL, health check endpoints, and deploy status commands. Writes the configuration to CLAUDE.md so all future deploys are automatic. Use when: "setup deploy", "configure deployment", "set up land-and-deploy", "how do I deploy with gstack", "add deploy config".

    Also in 19 projects that use this

  • ShreyRaviSkill

    landing-report

    Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots are currently claimed by open PRs, which sibling Conductor workspaces have WIP work likely to ship soon, and what slot /ship would pick next. No mutations — just a snapshot. Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next". (gstack)

    Also in 9 projects that use this

  • zebbernSkill

    debug-fix

    Find and fix a bug or issue — from any source (GitHub issue, error message, user report, or observed behavior)

    Also in 4 projects that use this

  • ramybarsoumSkill

    document-release

    Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when asked to "update the docs", "sync documentation", or "post-ship docs". Proactively suggest after a PR is merged or code is shipped.

    Also in 23 projects that use this

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 181 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If drift → decide: acceptable or split into separate PR?

    line 20
  2. Distinctive:

    If scope grew significantly → does the risk assessment need updating?

    line 21
  3. Very specific:

    If the README carries a hero image, does it still match what ships?

    line 22
  4. Distinctive:

    All acceptance criteria satisfied?

    line 27
  5. Very specific:

    Every task's Gate is recorded and met — the gate-check skill's run_gate.py --input status/plan.md answers it.

    line 28
  6. Distinctive:

    Every spec or plan the branch changed has a reader built from its current text (exit 1 is No-Go: regenerate the reader it names, hand the …

    line 32
  7. Distinctive:

    If partial delivery → is the partial state safe and functional?

    line 37
  8. Very specific:

    Before ticking anything, load references/template.md and walk its Compatibility, Tests,

    line 41
  9. Very specific:

    When producing the ship output, fill in references/template.md (loaded at Step 3).

    line 62

“Common” is measured: kept by at least 6 in 10 of the 181 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ship Workflow

CANARY: ship-loaded-2026-06-15-3b7e91c2d84fa056

Reads status/specification.md to know what should be shipping. Confirms scope coverage, compatibility, tests, observability, and rollback before the merge.

Steps

Step 1: Confirm final scope

  • Intended vs actual scope. Any drift? Any missing pieces?
  • If drift → decide: acceptable or split into separate PR?
  • If scope grew significantly → does the risk assessment need updating?
  • If the README carries a hero image, does it still match what ships? Load references/readme-hero.md when it might not, or when drawing one.

Step 2: Confirm objective coverage

  • Does the change solve the stated problem?
  • All acceptance criteria satisfied?
  • Every task's Gate is recorded and met — the gate-check skill's run_gate.py --input status/plan.md answers it.

    Exit 1 is No-Go. Exit 0 still leaves each manual (?) gate to a human verdict; one not yet confirmed is No-Go. Exit 2 (no Gate column or usage error): confirm the plan path, then fall back to the acceptance criteria only for a plan that predates gates.

  • Every spec or plan the branch changed has a reader built from its current text (exit 1 is No-Go: regenerate the reader it names, hand the HTML over, and commit it with the document):

    python3 claude-arsenal/scripts/reader_check.py branch
  • If partial delivery → is the partial state safe and functional?

Steps 3–6: Compatibility, tests, observability, deployment

Before ticking anything, load references/template.md and walk its Compatibility, Tests, Observability and Mitigation and rollback checklists against the change; tick only what has evidence. For tests, a gate receipt for this tree or green CI on the PR head is the evidence — run the full suite only when neither covers the tree.

Step 7: Adversarial reviewer gate

Reuse the verdict on record when it covers the merge-ready tree; run a new round only if commits landed after the last reviewed tree. Protocol and exits: claude-arsenal:core:init § references/pre-pr-review.md.

  • CLEAR (reused or new) → record it in the ship output (§ 3 Adversarial review row) and proceed to Step 8.
  • BLOCK → show the findings verbatim and stop. A finding judged a false positive may be overridden by recording which, why, and what was checked in the same row; once every blocking finding is overridden this way, the BLOCK is cleared: proceed to Step 8. Otherwise resolve it and re-run from Step 1.
  • No verdict or a moved tree → re-run.

Step 8: Produce ship output

When producing the ship output, fill in references/template.md (loaded at Step 3).


Abbreviation

Abbreviated ship = Step 2 + the Tests checklist from Steps 3–6 + Step 7 + Go/No-Go, where the host repo's CLAUDE.md allows it. Step 7 may be skipped only when that file carries <!-- ship: adversarial-review=skip --> and the change is docs-only or config-only; every code change runs it.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.