agentleFS
iwe-orgiwe-org/dev-workspace/.claude/skills/ship/SKILL.md

ship

Skill11 starsChanged 2 days agoMITView on GitHub

Close the loop when work ships — sync the specs the plan touched, mark the plan done and archive its link, flip the feature doc to implemented, close the bug, and link the work into the unreleased page; also cuts a release when asked. Use when the user says "ship <plan>", "mark <plan> done", "the <feature> work is finished", or "cut release X.Y.Z".

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

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 181 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Record in the release: Add an inclusion link to the feature doc under ## Added in data/releases/unreleased.md (bug fixes under ## Fixed, …

    line 45
  2. Very specific:

    Create data/releases/unreleased.md again, exactly:

    line 61
  3. Very specific:

    If the user gives the release's test count and suite time, add a row for the version to data/releases/metrics.csv.

    line 94
  4. Distinctive:

    Never invent verification results — if tests weren't run, say so and run them or ask.

    line 110

“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 finished work

Shipping is a state change across the whole graph, not one frontmatter flip. Specs sync first — a plan is not done while the specs it invalidated still describe the old behavior.

Steps

  1. Confirm. Identify the plan and check its ## Verification section against reality (test output, the diff, a manual check) — the verify skill (.claude/skills/verify/SKILL.md) is the thorough form of this step, and a clean verify is the best possible input to shipping. If verification can't be confirmed, stop and say what's missing — don't mark done on hope.
  2. Sync specs. Walk the plan's ## Spec changes list. For each entry, update the data/spec/ doc to describe the behavior that actually shipped (create the doc if it doesn't exist yet, link it from data/spec.md, and replace the back-ticked name in the plan with a real link). Requirement / Scenario format; update scenarios that the change falsified.
  3. Flip the plan. iwe update -k data/plans/<key> --set stage=done --set completed=<today>, then move its link out of ## Active in data/plans.md to data/plans-archive.md, under ## Done and the ### YYYY-MM heading of this month (create it, newest month first). If a milestone plan lists it, move that link to the milestone's ## Shipped section too. Loose ends the plan mentions without promising are no reason to leave it open: turn each into a backlog task or a bug, link it from the plan, and close the plan. (Abandoned or superseded instead of shipped? --set stage=cancelled --set status=deprecated, add a first line to the body pointing to its successor or giving the reason, move its link to ## Cancelled in data/plans-archive.md, and stop here.)
  4. Update the feature. Set the feature doc to stage: implemented, remove a status left over from an earlier stage, and list its guard tests in tests — the tests that fail when its behaviour breaks (create the doc from the plan's Context if it doesn't exist, linked from data/features.md). No such test exists? Say so to the user rather than inventing one; the schema rejects implemented without tests, and that gap is worth a backlog task. Fixed a bug instead? Write its ## Fix section (Change, Guard, Shipped), set stage: done and completed, and move its link from data/bugs.md to ## Fixed in data/bugs-archive.md.
  5. Record in the release. Add an inclusion link to the feature doc under ## Added in data/releases/unreleased.md (bug fixes under ## Fixed, linking the bug doc).
  6. Cut a release (only when asked, e.g. "cut release 0.2.0"). The accumulator page becomes the release page, and a new accumulator replaces it:
    • iwe rename data/releases/unreleased data/releases/<X.Y.Z> — every link to the page follows it.
    • iwe update -k data/releases/<X.Y.Z> --set version=<X.Y.Z> --set date=<today> --set stage=released --unset status --set 'description="Version <X.Y.Z>: <what it carries>."' — a released page is no longer a draft, and its description names the release instead of the accumulator. Keep both pairs of quotes: the value holds a colon.
    • Edit the page body: retitle the heading from # Unreleased to # <X.Y.Z>, replace the italic paragraph about the accumulator with one sentence saying what the release carries, and drop a ## Added, ## Changed or ## Fixed heading that has nothing under it.
    • Create data/releases/unreleased.md again, exactly:

      ---
      type: release
      description: The accumulator page for work merged but not yet released.
      version: unreleased
      stage: unreleased
      status: draft
      generated:
        by: <your agent>/<your model>
        at: <ISO 8601 now>
      ---
      
      # Unreleased
      
      *Work that has shipped to main but not yet to users. The ship skill adds an
      inclusion link here for every feature or fix as it lands; cutting a release
      renames this file to the version number and starts a fresh one.*
      
      ## Added
      
      ## Fixed
    • In data/releases.md the renamed link still reads Unreleased. Change it to [<X.Y.Z>](releases/<X.Y.Z>.md) and add [Unreleased](releases/unreleased.md) on a line of its own above it, so the accumulator stays on top and the versions follow newest first.
    • The rename also moved links that meant the accumulator rather than this release. List what links to the new page (iwe find --references data/releases/<X.Y.Z> -f keys) and point any such link back at releases/unreleased.md; a bug's ## Fix that says where the fix shipped is right as it is, once its wording names the version.
    • If the user gives the release's test count and suite time, add a row for the version to data/releases/metrics.csv; never estimate them.
  7. Log it. Append a bullet to data/log.md under a ## YYYY-MM-DD group for today (create the group if it isn't there, newest group first), one line per state change, each linking the document it describes — - **Update**: [Focus sessions](features/focus-sessions.md) implemented. A release cut gets its own line linking the release page.
  8. Validate. iwe normalize, then iwe schema validate — must pass. If the workspace is a git repository, commit with a message describing the state change, e.g. ship: focus-sessions done, timer spec synced, 0.2.0 cut.

Rules

  • Specs sync before the stage flips — never the other way around.
  • A plan whose milestone aggregator lists it: check whether it was the last child; if so, tell the user the milestone is complete.
  • Never invent verification results — if tests weren't run, say so and run them or ask.
  • Release pages link feature and bug docs, not plans.
  • Closing moves a link, never a file and never the link away from the graph: every closed plan and bug stays listed in its archive hub.

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.