Finishing pass for any Print Farm Manager change. An agent skill from joeltelling/print-farm-manager.

MITAuto-check passedDevelopment

Install Ship

skills CLI
$ npx skills add joeltelling/print-farm-manager --skill ship -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install joeltelling/print-farm-manager ship --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/joeltelling/print-farm-manager.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ship .claude/skills/ship && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ship
GitHub stars
207
Token cost
~1.2k tokens
SKILL.md length
618 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Finishing pass for any Print Farm Manager change. An agent skill from joeltelling/print-farm-manager.

  • Works in 7 steps: Inventory the change → Sync pairs → Tests → …
  • A change is functionally done and needs to be landed properly
  • SKILL.md covers Phase 1: Inventory the change, Phase 2: Sync pairs, Phase 3: Tests and Phase 4: Docs, plus 3 more sections
  • Calls git and npm

What it does

Ship is an agent skill from joeltelling/print-farm-manager. Finishing pass for any Print Farm Manager change. Runs tests, syncs docs and CHANGELOG, checks sync pairs, verifies dash-free prose, and commits in house style. Use when a change is functionally done and needs to be landed properly.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Changelog and release notes. It works with Git and npm. The repository describes itself as: Self-hosted print farm manager for multi-brand 3D printer fleets — Prusa, Bambu, Elegoo, Klipper. Live fleet monitoring, automated job dispatch, no cloud. The licence is MIT.

When your agent uses it

  • A change is functionally done and needs to be landed properly
  • Tasks that involve Changelog and release notes

Example prompts

  • “/ship”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Inventory the change
  2. Sync pairs
  3. Tests
  4. Docs
  5. Dash check
  6. Commit
  7. Report

What it can do on your machine

Read from SKILL.md and the folder at commit b5bb0a2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git and npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ship loads about 1.2k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 618 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from joeltelling/print-farm-manager at commit b5bb0a2, republished under its MIT licence (© joeltelling). 618 words, ~1,248 tokens.

Download SKILL.mdSave it as .claude/skills/ship/SKILL.md (or your agent's skills folder).
name
ship
description
Finishing pass for any Print Farm Manager change. Runs tests, syncs docs and CHANGELOG, checks sync pairs, verifies dash-free prose, and commits in house style. Use when a change is functionally done and needs to be landed properly.

Ship a Change

The change is written; this skill makes it landable. Work through every phase. Do not skip a phase because the change "is small": the small changes are the ones that skip docs.

Phase 1: Inventory the change

  1. git status and git diff (plus git diff --staged if anything is staged). Build a mental list of every touched file and what changed in it.
  2. If the diff contains changes you did not make and cannot explain, stop and ask Joel before proceeding. Never sweep unknown edits into a commit.
  3. Classify the change: bug fix, feature, endpoint change, driver work, client-only, docs-only. This decides which quality bar in CLAUDE.md applies.

Phase 2: Sync pairs

Check the "Sync pairs" table in CLAUDE.md against the touched files. Concretely:

  • Touched scheduler eligibility SQL? Check routes/parts.js dispatch-status mirrors it.
  • Added a table or column? Check server/routes/backup.js handles it in export and restore, and server/tests/backup-restore.test.js seeds and asserts it.
  • Touched a route's request or response shape? Check docs/api.md and the route's test.
  • Touched driver registration anywhere? Check all six touchpoints (see /add-connector).
  • Touched install steps in one of README.md / docs/installation.md? Check the other.

Fix any drift now, as part of this change.

Phase 3: Tests

  1. Run npm test. The full suite must pass: no new skips, no "unrelated" failures waved through. If a failure is genuinely pre-existing, verify with git stash && npm test && git stash pop and report it to Joel with the exact output rather than papering over it.
  2. Does the change have its own test?
    • Bug fix: there must be a regression test that fails without the fix. If missing, write it now (in-memory SQLite, factory-mounted route, supertest; transport-mocked for drivers).
    • New endpoint: success + validation failure + not-found cases.
    • Behavior change: the old asserted behavior must be updated intentionally, not deleted to make the suite pass.
  3. If any client file changed: npm run build must succeed.

Phase 4: Docs

  1. Update the relevant component doc in docs/ (server.md, database.md, api.md, poller.md, web-app.md, multi-brand.md, filaments.md, installation.md). Match the existing format exactly: database.md uses full DDL blocks with aligned inline comments; api.md uses ### VERB /path headings with fenced JSON examples and status-code prose.

  2. Prepend a docs/CHANGELOG.md entry at the top (below the # Changelog heading and rule):

    markdown
    ## YYYY-MM-DD: short imperative title
    
    One or more paragraphs: what changed and why. For bug fixes, name the
    real-world trigger ("Hit on a real farm machine after ..."). Mention new
    dependencies or configuration.
    
    ### Changes
    - `path/to/file.js`: what changed there.
    - `docs/whatever.md`: documented X.

    Use today's real date. Use a colon after the date, not a dash (the heading style is being standardized dash-free going forward).

  3. If a new docs/ file was created, add its row to the docs/README.md index table.

  4. If the change affects install or first-run behavior, update README.md and docs/installation.md. These serve strangers now; steps must be copy-pasteable and complete.

Show full SKILL.md (207 more words)Show less

Phase 5: Dash check

Run the check on every changed file that contains prose (docs, comments, UI strings, commit message draft):

bash
git diff HEAD --unified=0 | grep -Pn '^\+.*[\x{2013}\x{2014}]'

Any hit on a line you added must be rewritten with a comma, colon, parentheses, or plain hyphen. Legacy dashes on untouched lines stay.

Phase 6: Commit

  1. Stage exactly the files that belong to this change. Never git add -A blindly; check for strays (scratch files, server/gcode/ test artifacts, server/data/).

  2. Message format:

    type(scope): imperative summary under 72 chars
    
    Body: why the change was needed and anything non-obvious about how.
    Real-world context beats restating the diff.
    
    Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

    Types in use: feat, fix, docs, chore, test, ci. Scope is the module (scheduler, bambu, client, backup, update.bat).

  3. One concern per commit. If the diff contains two unrelated changes, split them.

  4. Commit to a branch if on main and the change is more than trivial, unless Joel said to commit straight to main. Do not push unless asked.

Phase 7: Report

Summarize for Joel in this order: what shipped, test results (suite count and pass state), which docs were updated, anything flagged (pre-existing failures, assumptions, unvalidated hardware behavior, sync pairs you had to fix). If hardware validation is pending, say so explicitly.

© joeltelling, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/ship of joeltelling/print-farm-manager.

Open the folder on GitHubat commit b5bb0a2

Compare with similar skills

Ship next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ship compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ship this skilljoeltelling/print-farm-manager207—~1.2kAutomated safety check: PassMIT
Verdaccio Pull Request Workflowverdaccio/verdaccio18k—~1.9kAutomated safety check: PassMIT
Hunk Release Workflowmodem-dev/hunk9.6k—~3.8kAutomated safety check: PassMIT
AionUi Version BumpiOfficeAI/AionUi33k—~2.1kAutomated safety check: PassApache-2.0
ZCF Release AutomationUfoMiao/zcf6.1k—~3.4kAutomated safety check: PassMIT
Git Changes ReporterNo-Trade-No-Life/Yuan352—~1.2kAutomated safety check: PassMIT

Similar skills

  • Takes a change through a verdaccio pull request: branch, local checks, changeset, title and body, labels, CI and review rounds, and ports to other release lines.

    18k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Hunk Release Workflow

    modem-dev/hunk

    Maintainer workflow for preparing, publishing, verifying and curating Hunk releases, with confirmation gates before tags, publishes and public edits.

    9.6k GitHub stars~3.8k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • AionUi Version Bump

    iOfficeAI/AionUi

    Automates an AionUi release: checks the latest AionCore release and its artifacts, updates package.json, writes the changelog, opens a PR and tags the release.

    33k GitHub stars~2.1k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Automates a version release with changesets: analyzes code changes, writes a bilingual CHANGELOG, bumps the version and commits through a release branch and pull request.

    6.1k GitHub stars~3.4k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Git Changes Reporter

    No-Trade-No-Life/Yuan

    生成结构化 git 变更报告(JSON + Markdown)。使用此技能当用户提到"git 变更"、"commit 摘要"、"代码审查"、"release note"、"近期改动"、"每日摘要",或需要分析指定 commit 区间的代码变更。包含三元组结构(设计意图、核心代码、影响范围)的语义化报告,适用于代码审查、发布说明、团队同步、CI/CD 等场景。

    352 GitHub stars~1.2k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed
  • ClawRouter Release Checklist

    BlockRunAI/ClawRouter

    Walks the agent through every ClawRouter release step in order, from the version bump and changelog entry to build, tests, npm publish, git tag and GitHub release.

    6.6k GitHub stars~1.4k tokensUpdated 3 days ago
    DevelopmentAuto-check passed

More from joeltelling/print-farm-manager

  • Add Connector

    joeltelling/print-farm-manager

    Scaffold, register, test, and document a new printer brand driver (connector) end to end.

    207 GitHub stars~1.9k tokensUpdated 2 days ago
    Auto-check passed
  • PR Review

    joeltelling/print-farm-manager

    Review a community pull request against Print Farm Manager's specific failure modes: adjacent-code drift, part-count integrity, driver contract compliance, docs completeness.

    207 GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Ship

What does Ship do?

Finishing pass for any Print Farm Manager change. An agent skill from joeltelling/print-farm-manager. Ship is an agent skill from joeltelling/print-farm-manager. Finishing pass for any Print Farm Manager change.

When should I use Ship?

Ship fits situations like: A change is functionally done and needs to be landed properly; tasks that involve Changelog and release notes.

How do I install Ship in Claude Code?

Run `npx skills add joeltelling/print-farm-manager --skill ship -a claude-code`. Or copy the skill folder (.claude/skills/ship in joeltelling/print-farm-manager) into .claude/skills/ship in your project. Claude Code loads it when a task matches its description.

How do I install Ship in Codex?

Run `npx skills add joeltelling/print-farm-manager --skill ship -a codex`. Or copy the skill folder (.claude/skills/ship in joeltelling/print-farm-manager) into .agents/skills/ship in your project. Codex loads it when a task matches its description.

Can I use Ship in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add joeltelling/print-farm-manager --skill ship -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ship, .gemini/skills/ship, .github/skills/ship and .opencode/skills/ship in your project.

What does Ship need to run?

Going by SKILL.md and its folder, Ship needs the command-line tools its instructions call (git and npm).

Does Ship access the network?

SKILL.md contains no URLs. Its commands use git and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Ship safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ship use?

Ship is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ship use?

About 1.2k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ship?

Skills that share tags, products or a category with Ship: Verdaccio Pull Request Workflow (verdaccio/verdaccio, 18k stars), Hunk Release Workflow (modem-dev/hunk, 9.6k stars), AionUi Version Bump (iOfficeAI/AionUi, 33k stars) and ZCF Release Automation (UfoMiao/zcf, 6.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ship?

joeltelling (a GitHub user) maintains it in joeltelling/print-farm-manager, which has 207 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 6, 2026.

Source: joeltelling/print-farm-manager on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.