Release logo

Release

Community
jrswab
release

Prepare code for release (version bumps, changelog, README updates) and create an annotated tag to trigger the GoReleaser workflow.

Overview

Publisherjrswab
Repositoryaxe
Skill namerelease
Stars
898
Forks
35
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 jrswab 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/jrswab/axe/tree/master/docs/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/jrswab/axe.git /tmp/axe
mkdir -p .claude/skills
cp -r /tmp/axe/docs/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.

Your job is to guide the user through a full release for this project. A release includes preparing the code (version bumps, README documentation, changelog), creating an annotated git tag with a v prefix (e.g. v1.5.0), pushing it to trigger the GoReleaser GitHub Actions workflow, setting release notes, and linking the GHCR Docker image.

Rules

  • Always create an annotated tag (git tag -a), never a lightweight tag.
  • Tag format is vMAJOR.MINOR.PATCH following Semantic Versioning.
  • The changelog MUST follow Keep a Changelog 1.1.0 format.
  • Valid changelog categories: Added, Changed, Deprecated, Removed, Fixed, Security.
  • All version strings MUST be updated before committing. There are three locations (listed in Reference). Run version tests after bumping to catch drift.
  • README.md MUST document any user-facing changes — new config fields, CLI flags, behavior changes, exit codes.
  • DO NOT push to master until the user confirms.
  • DO NOT push the tag until the user confirms.
  • DO NOT skip asking the user for the version number, tag annotation message, and changelog review.

Steps

  1. Gather context

    • Check the current branch and ensure it is clean (git status).
    • List existing tags (git tag --sort=-v:refname) to determine the next version.
    • Collect the commit log since the last tag (or all commits if this is the first release).
  2. Ask the user

    • What version number to use.
    • What the annotated tag message should say.
    • Whether the auto-generated changelog looks correct or needs edits.
  3. Categorize commits into Keep a Changelog sections:

    • Added — new features and capabilities.
    • Changed — changes to existing functionality.
    • Deprecated — features marked for removal.
    • Removed — features that were removed.
    • Fixed — bug fixes.
    • Security — vulnerability fixes.
    • Exclude commits prefixed with docs:, test:, ci:, or merge commits.
  4. Bump version strings

    • Update all three version locations listed in the Reference section.
    • Run go test ./cmd/ -run TestVersion -count=1 to verify the bump is consistent.
  5. Update README.md

    • Explore new feature implementations (via subagents if available) to understand config fields, flags, defaults, and behavior before writing documentation.
    • For each user-facing change, update the relevant README sections: Features list, Run Flags table, Agent Configuration example TOML, and add new sections as needed.
    • Add or update the Exit Codes table if new exit codes were introduced.
    • Do NOT guess at config fields or flag names — read the actual implementation first.
  6. Update CHANGELOG.md

    • Prepend the new release section under the # Changelog header.
    • Add a reference link at the bottom of the file using the Keep a Changelog format:
      • First release: [1.0.0]: https://github.com/jrswab/axe/releases/tag/v1.0.0
      • Subsequent releases: [1.1.0]: https://github.com/jrswab/axe/compare/v1.0.0...v1.1.0
  7. Commit and push prep changes

    • Stage all modified files and commit with message: Update changelog and version for vX.Y.Z
    • Push to master only after the user confirms.
  8. Verify

    • Run go build . to confirm the binary compiles.
    • Run go test ./cmd/ -run TestVersion -count=1 at minimum.
    • Confirm tests pass before proceeding to tag creation.
  9. Ask user to confirm tag creation

    • Show the tag name, annotation message, and commit hash.
    • Wait for explicit confirmation before creating the tag.
  10. Create the annotated tag on the prep commit.

  11. Push the tag to origin only after the user confirms. The v* tag push triggers the GoReleaser workflow which builds binaries and creates the GitHub release.

  12. Set release notes via gh

    • Extract the new version's section from CHANGELOG.md — everything between the ## [X.Y.Z] heading and the next ## heading, excluding the heading itself and trailing blank lines.
    • Append a Docker section to the extracted notes:
      ## Docker
      
      ```bash
      docker pull ghcr.io/jrswab/axe:X.Y.Z
      ```
      
      See the [GHCR package page](https://github.com/jrswab/axe/pkgs/container/axe) for all available tags.
    • Write the combined content (changelog section + Docker section) to a temporary file.
    • Poll gh release view vX.Y.Z every 10 seconds (up to 120 seconds) until the GoReleaser workflow creates the release.
    • Run gh release edit vX.Y.Z --notes-file <tmp-file> to set the release description.
    • Clean up the temporary file.
    • This is the authoritative source for release notes — do NOT rely on the workflow's awk extraction.

Reference

Project Files

  • GoReleaser config: .goreleaser.yml (auto-changelog is disabled)
  • Release workflow: .github/workflows/release.yml (builds binaries and Docker image; do NOT rely on it for release notes)
  • Changelog: CHANGELOG.md

Version Strings (all three must match)

  • cmd/root.go — const Version (source of truth)
  • internal/mcpclient/mcpclient.go — hardcoded Version: in mcp.NewClient call
  • cmd/version_test.go — test assertions for the version string

GHCR Image

Frequently asked questions

What does the Release AI skill do?

Prepare code for release (version bumps, changelog, README updates) and create an annotated tag to trigger the GoReleaser workflow.

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/jrswab/axe/tree/master/docs/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 jrswab 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 👇