Ops Ship logo

Ops Ship

Organization
Lifecycle-Innovations-Limited
ops-ship

OPS on-demand: This skill should be used when the user asks to "ship ops plugin", "merge all PRs and…

Overview

PublisherLifecycle-Innovations-Limited
Repositoryclaude-ops
Skill nameops-ship
Stars
543
Forks
64
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Lifecycle-Innovations-Limited on GitHub. Read the source before you install it.

Installation

Install the Ops Ship AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Lifecycle-Innovations-Limited/claude-ops/tree/main/claude-ops/skills/ops-ship
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Lifecycle-Innovations-Limited/claude-ops.git /tmp/claude-ops
mkdir -p .claude/skills
cp -r /tmp/claude-ops/claude-ops/skills/ops-ship .claude/skills/ops-ship
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ops Ship in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ops Ship on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ops Ship is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

OPS ► SHIP — merge-all-PRs → release → update, in one command

Load ops-rules before acting. Public repo (no personal data). Outbound: one draft → one approval → one send. If AskUserQuestion / Workflow are missing, follow Rule 10 in ops-rules (Hermes: numbered options / two-turn Telegram card; delegate_task).

The whole release chain in a single shot:

  1. Sweep — admin squash-merge every open, non-draft PR targeting the base branch (default main), overriding required checks/reviews (gh pr merge --admin). A failed merge aborts before the release — no partial ship.
  2. Release — delegates to bin/ops-release: bump plugin.json + marketplace.json registry + package.json + CHANGELOG, open the release PR, admin-merge to main, tag vX.Y.Z.
  3. Update — runs the installed ops-update to pull the new version onto this box (skip with --no-update).

ops-ship = sweep + /ops:ops-release + /ops:ops-update in one. For just the publish step use /ops:ops-release; for just the pull step use /ops:ops-update.

⚠️ It admin-merges EVERY open non-draft PR — review the sweep first

By design the sweep is aggressive: it admin-merges all open non-draft PRs on the base branch, bypassing required checks (red CI, missing reviews) — exactly what you want for a trusted solo/own-org repo, dangerous if an unrelated or half-baked PR is open. So always dry-run first and show which PRs it will merge before applying (Rule 5 — bulk merge + outward-facing release + tag is high-impact and hard to reverse). It only skips drafts.

⚠️ Run it from the REPO CHECKOUT, not the cache

Like ops-release, ops-ship resolves its targets relative to its own path and needs REPO_ROOT/.claude-plugin/marketplace.json, which the plugin cache lacks. Run the copy inside a git checkout of the repo:

bash
SHIP=""
for d in ~/Developer/repos/claude-ops ~/Projects/claude-ops-workspace/claude-ops ~/Projects/claude-ops/claude-ops "$HOME"/Projects/*/claude-ops; do
  if [ -f "$d/.claude-plugin/marketplace.json" ] && [ -x "$d/claude-ops/bin/ops-ship" ]; then
    SHIP="$d/claude-ops/bin/ops-ship"; break
  fi
done
[ -n "$SHIP" ] || { echo "no claude-ops checkout with marketplace.json found"; exit 1; }

How to run it

1. Dry-run — show the sweep + the version bump

bash
"$SHIP" --type patch --dry-run

Present: the list of open PRs it will admin-merge, the version bump (current → new), the manifests touched, and the CHANGELOG block. (--notes defaults to a bullet list of the merged PR titles; pass --notes "…" to override.)

2. Confirm

Use AskUserQuestion before applying (this merges PRs AND publishes):

Ship: admin-merge N open PR(s) on main, then release <CUR> → <NEW> + tag?
  [Ship it]
  [Dry-run only]
  [Cancel]

3. Apply

bash
"$SHIP" --type patch                 # or --version X.Y.Z, --notes "…", --no-update

Stream the step output (sweep → release → update). On success it ends with the new tag and the reload reminder. Surface the final line verbatim:

Restart Claude Code (or run /reload-plugins) to load v.

Flags

FlagEffect
--type patch|minor|majorSemver bump for the release (default patch).
--version X.Y.ZExact target version instead of bumping.
--notes "…"CHANGELOG body. Defaults to a bullet list of the merged PR titles.
--base BRANCHBase branch for the PR sweep only (must be main; ops-release always publishes to main).
--no-updateDon't run ops-update afterwards (publish only).
--dry-runReport only — list PRs + the bump, change nothing. Always run this first.

Notes

  • PRs target main and are squash-merged with --admin (own-org PRs can't be self-approved; admin bypasses the review/required-check gates).
  • REST quota: the sweep and ops-release use gh (GitHub REST). If REST is exhausted (HTTP 403 rate-limit), wait for the reset window — ops-ship aborts before releasing if any merge fails rather than partial-shipping.
  • Publish ≠ loaded. The running session won't see the new version until ops-update (pull, run automatically unless --no-update) and /reload-plugins (load).
  • Siblings: /ops:ops-release (publish only), /ops:ops-update (pull only).

Frequently asked questions

What does the Ops Ship AI skill do?

OPS on-demand: This skill should be used when the user asks to "ship ops plugin", "merge all PRs and…

Why use Ops Ship on TypingMind?

Because you install it once and use it with any model. Ops Ship is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ops Ship in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Lifecycle-Innovations-Limited/claude-ops/tree/main/claude-ops/skills/ops-ship. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ops Ship?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ops Ship?

As many as you like. As long as a model supports skills, you can use Ops Ship with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ops Ship AI skill free?

Yes. It is published on GitHub by Lifecycle-Innovations-Limited under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇