Release logo

Release

Community
onevcat
release

Build, sign, notarize, and publish a Prowl release.

Overview

Publisheronevcat
RepositoryProwl
Skill namerelease
Stars
647
Forks
66
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 onevcat 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/onevcat/Prowl/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/onevcat/Prowl.git /tmp/Prowl
mkdir -p .claude/skills
cp -r /tmp/Prowl/.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.

Release

Build, sign, notarize, and publish a Prowl release.

  1. Verify current branch is main: git branch --show-current
    • If not on main, abort and tell the user to switch first
  2. Verify working tree is clean: git status --porcelain
    • If dirty, list the changes and ask whether to proceed or abort
  3. Sync the docs to the code being released — before the version bump and tag:
    • First read docs-ai/001-fork-bootstrap-and-release-pipeline/release-runbook.md's Workflow UI release scope and Agent contract release check, and surface their status to the user. Follow the linked contract runbook: run the full --mode verify suite with the owner's configured model routes, then --mode publish --report PATH before bump/tag. Commit the generated receipt, version baseline, and matrix. Publication requires the original artifacts/result bundles and unchanged source, binaries, and routes within 24 hours; rerun after relevant changes. Report T1 headless results separately from D3 handoff acceptance in R2b and D2 review acceptance in R3; inventory alone is not a contract pass, and T1 success does not establish workflow release readiness.
    • Run the sync-docs skill. It diffs docs/.sync-meta.json's last_synced_commit against the current main HEAD (the code about to ship), updates any docs whose implementation changed, and sets last_synced_commit to the current HEAD — the exact commit being released, recorded before the bump/tag.
    • Commit the result as its own commit (only docs/**, which includes docs/.sync-meta.json; never git add .): e.g. git commit -m "Sync docs for <VERSION>". This is required: release.sh aborts on a dirty tree, and the doc commit must land on main now so it is an ancestor of the tag and ships inside the release.
    • Ordering is load-bearing: docs first, then bump + tag. Never tag first. The baseline points at the released code (the pre-doc-commit HEAD), not at the later doc/bump/CHANGELOG commits — that is correct and intentional (those commits touch no implementation files, so the next sync starts from a tight, accurate diff range).
    • If sync-docs reports "needs human decision" items, resolve or defer them before continuing.
    • Most releases change little or no implementation, so this step is usually a no-op doc-wise (just a baseline bump). Keep it cheap — see the sync-docs skill's cost notes.
    • Run the sync-l10n skill. Translations are not required in everyday work, so this is where they catch up: it translates new UI copy, removes catalog entries that no code uses, and triages new unlocalized literals. Commit the result as its own commit, also before the bump and tag: e.g. git commit -m "Sync localization for <VERSION>". When it reports "needs human decision" items, resolve or defer them before you continue. For an urgent hotfix the debt budget step can be skipped; the translate and prune steps cannot.
  4. Determine the version:
    • If $ARGUMENTS is provided, use it as the version (e.g., 2026.3.18)
    • Otherwise, default to today's date format and confirm with the user before proceeding
  5. Generate release notes: ./scripts/release-notes.sh <VERSION>
    • This script compares HEAD against the previous release tag, gathers commits and PR descriptions, and generates user-facing notes via LLM into build/release-notes.md.
    • Read the generated build/release-notes.md, show the content to the user, and wait for explicit confirmation. If the user wants changes, edit the file directly.
    • Alongside that maintainer-facing confirmation, report the agent contract check result and evidence location, including any blocked or untested runtimes. Keep this diagnostic summary out of the public release notes; apply the release runbook's scope policy.
    • Do NOT proceed to the next step until the user confirms the release notes.
  6. Run the release script: ./scripts/release.sh <VERSION>
    • The script reads build/release-notes.md (required — refuses to run without it).
    • It handles: version bump, build, sign, notarize, DMG, appcast, GitHub Release, and Prowl-Site update. If the tag already exists (e.g., from a prior interrupted run), it skips the bump step automatically.
  7. Report the GitHub release URL and remind the user to verify:
    • The DMG downloads and installs correctly
    • Sparkle update check works (launch app → Check for Updates)

Frequently asked questions

What does the Release AI skill do?

Build, sign, notarize, and publish a Prowl release.

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/onevcat/Prowl/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 onevcat. 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 👇