Release logo

Release

CommunityPopular
Shpigford
release

Determine the next version, update the marketing site, and run the full release pipeline.

Overview

PublisherShpigford
Repositorychops
Skill namerelease
Stars
1.9K
Forks
124
Bundled files
Instructions only
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 Shpigford on GitHub. Read the source before you install it.

Installation

Install the Release 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/Shpigford/chops/tree/main/.claude/skills/release
  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/Shpigford/chops.git /tmp/chops
mkdir -p .claude/skills
cp -r /tmp/chops/.claude/skills/release .claude/skills/release
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Release 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 Release 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 Release 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.

Cut a new release of Chops. Determines the version from git history, updates the marketing site, and runs the release script.

Instructions

Step 1: Verify prerequisites

  1. Confirm .env exists in the project root. If it does not, stop and tell the user: "Missing .env file. Copy .env.example to .env and fill in APPLE_TEAM_ID, APPLE_ID, and SIGNING_IDENTITY_NAME."
  2. Confirm the notarytool keychain profile AC_PASSWORD works:
    bash
    xcrun notarytool history --keychain-profile "AC_PASSWORD" >/dev/null 2>&1
    If it fails, stop and tell the user to run:
    bash
    xcrun notarytool store-credentials "AC_PASSWORD" --apple-id "<APPLE_ID>" --team-id "<TEAM_ID>" --password "<app-specific-password>"
  3. Confirm the working tree is clean (git status --porcelain). If there are uncommitted changes, stop and tell the user to commit or stash first.
  4. Confirm you are on the main branch. If not, stop and tell the user to switch to main first.

Step 2: Determine the next version

  1. Get the latest tag:
    bash
    git tag -l 'v*' | sort -V | tail -1
  2. Get commits since that tag:
    bash
    git log <latest_tag>..HEAD --oneline --format='%s'
  3. If there are zero commits since the last tag, stop and tell the user there is nothing to release.
  4. Apply semver logic to the current latest version:
    • If any commit message starts with feat: or feat( → minor bump (e.g. 1.1.0 → 1.2.0)
    • If all commits are fix:, chore:, docs:, or similar → patch bump (e.g. 1.1.0 → 1.1.1)
    • If any commit contains BREAKING CHANGE or uses a !: suffix → ask the user what version to use
    • If the commit messages are ambiguous or do not follow conventional commits, use mcp__conductor__AskUserQuestion to ask:
      • question: "Commits since the last release don't clearly indicate the version bump. What version should this release be?"
      • header: "Release version"
      • multiSelect: false
      • options with labels: "Patch (X.Y.Z+1)", "Minor (X.Y+1.0)", "Major (X+1.0.0)", "Custom"

Step 3: Confirm the version

Always confirm the version before proceeding. Use mcp__conductor__AskUserQuestion:

  • question: "Release as v? Commits included:\n"
  • header: "Confirm release"
  • multiSelect: false
  • options:
    • "Yes, release v"
    • "Use a different version"
    • "Cancel"

If the user picks "Use a different version", ask them for the version number. If they pick "Cancel", stop.

Step 3.5: Update CHANGELOG.md

  1. Check if CHANGELOG.md has an ## [Unreleased] section with content (bullet points).
  2. If the ## [Unreleased] section is empty or missing, draft entries from commits since the last tag:
    • Rewrite each entry to be user-facing. Don't echo commit messages. Describe what changed from the user's perspective — what it enables, fixes, or improves.
    • Bad: "feat: add skills registry browser with multi-agent install"
    • Good: "Browse and install community skills directly from the app"
    • Keep entries succinct (one line each). No technical jargon, no commit prefixes.
    • Confirm the drafted entries with the user using mcp__conductor__AskUserQuestion.
  3. Rename ## [Unreleased] to ## [VERSION] - YYYY-MM-DD (today's date).
  4. Add a new empty ## [Unreleased] section above it.

Step 4: Update the marketing site version

  1. Edit site/src/pages/index.astro. Find the line containing class="requires" and replace it with:
    html
    <p class="requires">v<VERSION> &middot; Requires macOS Sequoia</p>
    where <VERSION> is the confirmed version.
  2. Commit this change along with the changelog:
    bash
    git add site/src/pages/index.astro CHANGELOG.md
    git commit -m "chore: update site version to v<VERSION>"
    git push

Step 5: Run the release script

bash
./scripts/release.sh <VERSION>

This handles: xcodegen → archive → export → DMG → notarize → staple → git tag → appcast → push → GitHub Release.

Let it run to completion. If it fails, report the error output to the user and stop. Do NOT retry automatically.

Step 6: Push and report

Ensure all commits are on the remote:

bash
git push

Tell the user:

  • The version that was released
  • Link: https://github.com/Shpigford/chops/releases/tag/v<VERSION>
  • Remind them to deploy the marketing site if needed (npm run build from site/)

Important Rules

  • ALWAYS confirm the version with the user before proceeding
  • NEVER run the release script if .env is missing or the working tree is dirty
  • NEVER skip the marketing site version update
  • If the release script fails, do NOT retry — report the error and stop
  • The release script handles git tagging and GitHub release creation — do not duplicate those steps

Frequently asked questions

What does the Release AI skill do?

Determine the next version, update the marketing site, and run the full release pipeline.

Why use Release on TypingMind?

Because you install it once and use it with any model. Release 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 Release in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Shpigford/chops/tree/main/.claude/skills/release. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Release?

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 Release?

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

Is the Release AI skill free?

It is published on GitHub by Shpigford. Check the repository for licensing terms. 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 👇