Release logo

Release

Organization
devoxx
release

Release a new version of the DevoxxGenie IntelliJ plugin — prompt for the target version, bump it in the build files, write a curated CHANGELOG.md entry and plugin.xml change-notes from the git/PR history since the last tag, build to verify, then commit, tag, and publish a matching GitHub release. Use this whenever the user wants to cut, ship, publish, or tag a new plugin release, bump the version for a release, or asks to "release vX.Y.Z" / "do a release" / "make a new version".

Overview

Publisherdevoxx
RepositoryDevoxxGenieIDEAPlugin
Skill namerelease
Stars
684
Forks
103
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 devoxx 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/devoxx/DevoxxGenieIDEAPlugin/tree/master/.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/devoxx/DevoxxGenieIDEAPlugin.git /tmp/DevoxxGenieIDEAPlugin
mkdir -p .claude/skills
cp -r /tmp/DevoxxGenieIDEAPlugin/.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 a new DevoxxGenie plugin version

This skill cuts a complete plugin release: version bump → curated changelog → plugin change-notes → build → commit → tag → GitHub release. The goal is a release whose CHANGELOG.md, plugin.xml change-notes, and GitHub release body all tell the same story, written from the actual work done — not a raw dump of PR titles.

The release commit lands on the current default branch (master), matching how prior releases were cut here. Do not create a feature branch for a release.

Step 1 — Ask for the target version

Never assume the next version. Show the current version and ask the user what to release.

bash
grep -E '^version\s*=' build.gradle.kts | head -n1   # e.g. version = "1.7.4"

Offer patch / minor / major as a guide (e.g. current 1.7.4 → patch 1.7.5, minor 1.8.0, major 2.0.0) but let the user state the exact number. Use it verbatim as X.Y.Z (tags are vX.Y.Z).

Step 2 — Gather the history since the last release

Find the previous tag, then read what actually changed. You need the substance of each change, so look at PR titles and bodies/commits, not just subject lines.

bash
git describe --tags --abbrev=0                 # previous tag, e.g. v1.7.4
git log <prev-tag>..HEAD --oneline             # commits to summarise
gh pr list --state merged --base master --limit 30 \
  --json number,title,author,mergedAt,body     # PR detail + authors

Group changes into the sections the CHANGELOG already uses, by conventional-commit prefix:

PrefixCHANGELOG section
feat / addAdded
fixFixed
refactor / build / perf / style / chore (non-dep)Changed
docsDocumentation
testTests
chore(deps) / bump / upgradeDependencies

Collect the unique PR authors for a Contributors section (@login).

Write descriptive entries: explain what changed and why it matters for a user or maintainer, drawing on the PR body/diff — not just the raw commit subject. Keep the feat(scope): / fix(scope): lead so entries scan consistently, and append issue/PR/task references like (#1097) or (task-229, #1093). Omit empty sections.

Step 3 — Bump the version

  • build.gradle.kts: update the top-level version = "X.Y.Z" line (around line 18).
  • src/main/resources/application.properties is auto-regenerated by the build from the Gradle project version — do not hand-edit it; Step 6's build updates it.
  • plugin.xml has no <version> tag (it's injected by the Gradle IntelliJ plugin), so only its change-notes need editing — see Step 5.

Step 4 — Write the CHANGELOG.md entry

Insert a new section at the top of CHANGELOG.md, directly under the # Changelog header and above the previous version. Match the existing house style exactly:

markdown
## vX.Y.Z - YYYY-MM-DD

### Added
- feat(tips): rotating tip line under the prompt placeholder, fetched from a 24h-cached
  tips.json with a built-in fallback list (#1099)

### Fixed
- fix(scope): concise but complete description of the fix and its user-visible effect (#NNNN)

### Changed
- refactor(scope): what was restructured and why it's cleaner (#NNNN)

### Dependencies
- chore: upgrade <lib> A.B.C → X.Y.Z

### Contributors
- @stephanj

Use today's date (the current date is available in your context). Keep entries information- dense; a single fix can warrant a long sentence if the behaviour change is subtle (see the v1.7.4 credentials entry for the level of detail that's welcome).

Step 5 — Update plugin.xml change-notes

The Marketplace change-notes are a condensed view — the user-relevant highlights, one concise <LI> each. Insert a new block immediately after <change-notes><![CDATA[, above the existing <h2> for the prior version:

html
        <h2>vX.Y.Z</h2>
        <UL>
                    <LI>feat(tips): rotating tip line under the prompt input, fetched from a cached tips.json (#1099)</LI>
                    <LI>fix(scope): short user-facing summary (#NNNN)</LI>
                </UL>

Skip internal-only churn (test-only, pure-refactor, doc) here unless it matters to users. Keep the indentation consistent with the surrounding blocks.

Step 6 — Build to verify

The project requires JDK 21 (JDK 25 breaks the Gradle build). Set JAVA_HOME first:

bash
export JAVA_HOME=/Users/stephan/Library/Java/JavaVirtualMachines/azul-21.0.5/Contents/Home
./gradlew buildPlugin

This regenerates application.properties with the new version and produces build/distributions/DevoxxGenie-X.Y.Z.zip. Confirm the zip name matches the new version before continuing — a mismatch means the version bump didn't take.

Step 7 — Commit, tag, and push (confirm first)

Pushing and tagging are hard to undo and are outward-facing, so show the user the staged diff and the planned tag, and get an explicit go-ahead before running this step.

bash
git add build.gradle.kts src/main/resources/application.properties \
        src/main/resources/META-INF/plugin.xml CHANGELOG.md
git commit -m "chore: bump version to vX.Y.Z"
git tag -a "vX.Y.Z" -m "Release vX.Y.Z"
git push origin HEAD
git push origin "vX.Y.Z"

Step 8 — Create the GitHub release

The release body is the CHANGELOG section for this version. Prior releases bold the lead clause of detailed entries (e.g. - **fix(credentials): …** — …) for scanability; apply that lightly to the heaviest entries. Attach the built zip as the release asset.

Write the body to a temp file (avoids shell-escaping issues), then:

bash
gh release create "vX.Y.Z" \
  --title "vX.Y.Z" \
  --notes-file /tmp/release-notes-X.Y.Z.md \
  build/distributions/DevoxxGenie-X.Y.Z.zip

Finish by printing the release URL gh returns so the user can review it.

Notes

  • This skill stops at the GitHub release. Publishing to the JetBrains Marketplace is a separate, explicit step (PUBLISH_TOKEN=… ./gradlew publishPlugin) — only do it if the user asks.
  • If the working tree has unrelated uncommitted changes, surface that before staging so the release commit doesn't sweep them in.

Frequently asked questions

What does the Release AI skill do?

Release a new version of the DevoxxGenie IntelliJ plugin — prompt for the target version, bump it in the build files, write a curated CHANGELOG.md entry and plugin.xml change-notes from the git/PR history since the last tag, build to verify, then commit, tag, and publish a matching GitHub release. Use this whenever the user wants to cut, ship, publish, or tag a new plugin release, bump the version for a release, or asks to "release vX.Y.Z" / "do a release" / "make a new version".

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/devoxx/DevoxxGenieIDEAPlugin/tree/master/.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?

Yes. It is published on GitHub by devoxx 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 👇