Ring:Shipping Changes logo

Ring:Shipping Changes

Organization
LerianStudio
ring:shipping-changes

End-to-end git orchestrator: branch → commit → push → PR, with a full plan presented before any execution. Detects base branch and scope allowlist once and propagates to all phases. Use when ready to ship a complete unit of work. Skip if only one phase is needed: commit-only → ring:committing-changes, PR-only → ring:opening-pull-requests.

Overview

PublisherLerianStudio
Repositoryring
Skill namering:shipping-changes
Stars
215
Forks
28
Bundled files
Instructions only
LicenseApache-2.0
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 LerianStudio on GitHub. Read the source before you install it.

Installation

Install the Ring:Shipping Changes 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.
  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/LerianStudio/ring.git /tmp/ring
mkdir -p .claude/skills
cp -r /tmp/ring/default/skills/shipping-changes .claude/skills/lerianstudio-ring-shipping-changes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ring:Shipping Changes 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 Ring:Shipping Changes 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 Ring:Shipping Changes 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.

End-to-end shipping workflow: detect base branch and scope policy once, present a complete plan, then execute branch → commit → push → PR in sequence, confirming at each phase. Uses ring:committing-changes and ring:opening-pull-requests internally — their rules and anti-patterns apply in full.

⛔ HARD STOP — PRESENT PLAN BEFORE EXECUTING ANY MUTATING COMMAND

Read-only discovery commands (git fetch, git ls-remote, git status, git diff, git log) are allowed before approval — they are needed to build the plan.

MUST complete Phase 0 detection, analyze the current state, and present a complete plan to the user before running any mutating git or gh command (git checkout -b, git add, git commit, git push, gh pr create). Executing mutating commands without approval is FORBIDDEN.


Phase 0 — Detect Base Branch and Scope Policy

MUST complete both detections before analyzing changes or drafting anything. These values are resolved once and propagated to all subsequent phases.

0A — Detect Base Branch

bash
# Probe A — GitHub API default (fallback: git remote show origin | grep 'HEAD branch' | awk '{print $NF}')
gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name'

# Probe B — PR template hint: read .github/pull_request_template.md for explicit branch name

# Probe C — develop existence
git ls-remote --heads origin develop

Apply precedence in order — first match wins:

PrioritySourceRule
1 — highestPR templateExplicit branch name in .github/pull_request_template.md — overrides everything
2develop + userProbe C finds develop AND differs from Probe A → ask user to confirm which target
3 — fallbackGitHub APIUse value from Probe A
4NeitherSTOP — ask the user

Why not develop-first: a repo may have a stale develop branch while the real PR target is main. The GitHub API is the authoritative source; develop existence triggers a confirmation step instead of a silent assumption.

0B — Detect Scope Policy

Check in this order:

  1. .github/workflows/pr-validation.yml (primary)
  2. .github/workflows/pr-title.yml
  3. .github/workflows/commitlint.yml
  4. .github/workflows/semantic-pull-request.yml
  5. Root configs: commitlint.config.{js,cjs,mjs,ts}, .commitlintrc*

Extract the allowed scope list and any type restrictions.

SituationRequired Action
Policy found, scope is clearUse only scopes from the allowlist
Policy found, scope is ambiguousSTOP and ask the user which allowed scope to use
No policy file foundMUST still include a scope — ask the user what scope to use

Phase 0C — Analyze Current State

bash
git status
git branch
git diff
git log --oneline -5

Use this output for the plan.


Phase 0D — Present Full Plan for Approval

Present everything before touching git:

Shipping Plan — waiting for your approval
──────────────────────────────────────────
Base branch:    develop   (from: git ls-remote)
Scope policy:   .github/workflows/pr-validation.yml → scopes: [api, auth, docs, ci]
Chosen scope:   auth

Phase 1 — Branch
  Current branch: main → will create: feat/add-oauth2-refresh
  Command: git checkout -b feat/add-oauth2-refresh origin/develop

Phase 2 — Commit
  Files to stage:
    - src/auth/oauth.ts (modified)
    - src/auth/oauth.test.ts (modified)
    - docs/auth/oauth-setup.md (modified)
  Proposed commits:
    1. feat(auth): add OAuth2 refresh token support
    2. docs(docs): update OAuth2 setup guide

Phase 3 — Push
  Command: git push -u origin feat/add-oauth2-refresh

Phase 4 — Pull Request
  Title:   feat(auth): add OAuth2 refresh token support
  Base:    develop
  Command: gh pr create --title "..." --body "..." --base develop

Approve and execute? [Yes / Modify / Cancel]

MUST wait for explicit user approval. Do NOT begin Phase 1 until approved.


Phase 1 — Branch

1.1 — Check current branch

If already on a feature branch (not $BASE, not main when $BASE=develop):

javascript
AskUserQuestion({
  questions: [{
    question: "You're already on a feature branch. How should I proceed?",
    header: "Branch",
    options: [
      { label: "Use current branch", description: "Continue on this branch" },
      { label: "Create new branch", description: "Create a new branch from origin/$BASE" }
    ]
  }]
});

1.2 — Create branch (if needed)

Branch naming convention: <type>/<description> in kebab-case.

bash
git fetch origin --quiet
# Check for duplicate
git ls-remote --heads origin <type>/<description>

# If no duplicate:
git checkout -b <type>/<description> origin/$BASE

If a branch with the same name already exists on remote, ask the user for a different name.

Types: feat, fix, chore, refactor, docs, test, perf


Phase 2 — Commit

Delegate to ring:committing-changes with the resolved $BASE and scope policy as context.

MUST propagate $BASE to ring:committing-changes — Step 7 of that skill uses origin/$BASE..HEAD for commit batch scoping. Without it, the skill falls back to @{u} or re-detects the base, which works but is redundant when $BASE is already known here.

The following rules from ring:committing-changes apply in full:

  • $BASE is already resolved — pass it explicitly so Step 7 skips re-detection
  • Scope MUST come from the allowlist resolved in Phase 0B
  • Scope MUST be included in every commit message — never omit
  • Commits MUST be atomic and logically grouped
  • Trailers via --trailer "X-Lerian-Ref: 0x1", NEVER inside -m
  • GPG sign with -S (no fallback — if no key, stop and instruct user to configure one)

Phase 3 — Push

bash
git push -u origin <current-branch>

Show the user:

  • Branch name
  • Number of commits being pushed
  • Short summary of those commits

Confirm success before proceeding to Phase 4.

NEVER use --force or --force-with-lease unless the user explicitly requests it.


Phase 4 — Pull Request

Delegate to ring:opening-pull-requests with the resolved $BASE and scope policy as context.

The following rules from ring:opening-pull-requests apply in full:

  • PR title MUST carry type(scope): description with scope from allowlist
  • Body MUST fill the repo's PR template
  • MUST verify base branch after gh pr create
  • MUST retarget with gh pr edit <number> --base $BASE if base is wrong
  • MUST return PR URL after confirmed success

Arguments

If an argument is provided (e.g., /ring:shipping-changes feat/add-oauth2), parse it as <type>/<description> for the branch name and skip the branch-naming question.


Anti-Patterns (FORBIDDEN)

  • Do NOT execute any git or gh command before presenting the plan and getting approval
  • Do NOT hardcode --base develop or --base main — always use $BASE resolved in Phase 0A
  • Do NOT skip Phase 0B scope detection — missing scope breaks PR validation
  • Do NOT omit scope in commit messages or PR title
  • Do NOT invent scopes not in the allowlist — ask the user if unclear
  • Do NOT use --force on push unless the user explicitly asks
  • Do NOT skip the post-PR-create base verification (delegated to ring:opening-pull-requests)
  • Do NOT proceed to the next phase if the current phase fails — stop and ask the user

Anti-Rationalization Table

RationalizationWhy It's WRONGRequired Action
"I know the base branch, I can skip detection"Any repo can change. Detection takes 2 seconds and prevents irreversible mistakes.MUST detect with git ls-remote
"I'll present the plan after I start"The plan exists so the user can catch mistakes before they happen.MUST present plan BEFORE any execution
"Scope detection is only for PRs"Commit messages also need the allowlist scope — they're validated together.MUST detect scope before Phase 2
"The user approved the plan, I can skip confirmations per phase"Phases can fail independently. Each phase confirms its own success.MUST confirm success at each phase
"I'll use the same scope as last time"Each repo may have a different allowlist. Re-detect for every invocation.MUST detect scope from the current repo
"Branch creation failed but I'll continue"Subsequent phases depend on the branch existing.MUST stop and ask the user on any failure
"Force push is fine since it's a feature branch"--force rewrites history. Only do this on explicit user request.MUST NOT force push without explicit request

Frequently asked questions

What does the Ring:Shipping Changes AI skill do?

End-to-end git orchestrator: branch → commit → push → PR, with a full plan presented before any execution. Detects base branch and scope allowlist once and propagates to all phases. Use when ready to ship a complete unit of work. Skip if only one phase is needed: commit-only → ring:committing-changes, PR-only → ring:opening-pull-requests.

Why use Ring:Shipping Changes on TypingMind?

Because you install it once and use it with any model. Ring:Shipping Changes 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 Ring:Shipping Changes in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LerianStudio/ring/tree/main/default/skills/shipping-changes. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ring:Shipping Changes?

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 Ring:Shipping Changes?

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

Is the Ring:Shipping Changes AI skill free?

Yes. It is published on GitHub by LerianStudio under the Apache-2.0 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 👇