Release Kanban Md logo

Release Kanban Md

Community
antopolskiy
release-kanban-md

Release kanban-md through its tag-triggered GoReleaser workflow, monitor CI, recover safely from failures, and publish user-facing GitHub release notes. Use when the user asks to release, tag, publish, or prepare release notes for kanban-md. Do not use for ordinary commits or unreleased changelog edits.

Overview

Publisherantopolskiy
Repositorykanban-md
Skill namerelease-kanban-md
Stars
226
Forks
34
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by antopolskiy on GitHub. Read the source before you install it.

Installation

Install the Release Kanban Md 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/antopolskiy/kanban-md/tree/main/.agents/skills/release-kanban-md
  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/antopolskiy/kanban-md.git /tmp/kanban-md
mkdir -p .claude/skills
cp -r /tmp/kanban-md/.agents/skills/release-kanban-md .claude/skills/release-kanban-md
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Release Kanban Md 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 Kanban Md 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 Kanban Md 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 kanban-md

Carry an explicitly requested release from preflight through a verified GitHub release. A request to inspect, plan, or draft a release does not authorize pushing a tag or editing a live release; perform remote mutations only when the user has asked to release or publish.

Release invariants

  • A version tag triggers the GitHub Actions release workflow, which uses GoReleaser to create the GitHub release and its artifacts.
  • Never run gh workflow run release; tag push already triggers the workflow and a manual dispatch can create a duplicate build.
  • Never run gh release create. Let GoReleaser create the release, then update its title and notes with gh release edit after CI succeeds.
  • Never move, delete, or reuse a tag that has been pushed. After a non-transient failure, fix the cause and choose a new, higher version.
  • Decide the version autonomously using semver: patch for fixes, minor for backward-compatible features, and major for breaking changes. Do not ask the user to confirm the version.
  • A release is complete only when the workflow is green, the generated release exists, its human-written notes are published, and the final release is verified.

1. Preflight

Work from a clean, up-to-date main containing exactly the changes intended for release. Do not discard, overwrite, or silently stash unrelated user changes.

bash
git branch --show-current
git status --short
git fetch origin --tags
git status --short --branch
git tag --sort=-version:refname | head -20
gh release list --limit 100

If main is dirty, diverged, or missing intended work, resolve that through the normal project development workflow before releasing. Run the release-appropriate verification, normally:

bash
make precommit

Do not tag a revision that fails required tests or lint.

2. Inspect changes and choose the version

Identify the previous release tag and review the user-visible changes, including outside contributions that may need attribution:

bash
git log vPREVIOUS..HEAD --oneline
git diff vPREVIOUS..HEAD --stat
git diff vPREVIOUS..HEAD

Choose vX.Y.Z according to semver and confirm that it does not already exist locally or remotely. The tag must identify the verified main commit.

3. Tag and push

Push main and the exact new tag. Do not use --tags, which can publish other local tags unintentionally.

bash
git push origin main
git tag vX.Y.Z
git push origin vX.Y.Z

4. Watch the release workflow

Find the run associated with the new tag and watch it to completion:

bash
gh run list --workflow release --limit 10
gh run watch <RUN_ID>

Confirm the selected run is for vX.Y.Z. Do not publish release notes before the workflow is green.

If the workflow fails:

  1. Inspect the failed logs with gh run view <RUN_ID> --log-failed.
  2. If the failure is clearly transient, rerun only the failed jobs with gh run rerun <RUN_ID> --failed, then watch the run again.
  3. If code, tests, lint, configuration, or packaging must change, stop the release attempt. Fix and merge the problem through the normal development workflow, verify main, choose a new higher semver, and push a new tag.

Do not delete the failed tag or partially generated release unless the user explicitly requests that separate cleanup.

5. Write and publish release notes

Once CI is green, read references/release-notes.md and draft the notes from the full diff, commits, and relevant pull-request authors. Release notes must explain what users can now do, not merely restate commit messages.

Publish from a notes file so shell quoting cannot corrupt Markdown:

bash
gh release edit vX.Y.Z \
  --title 'vX.Y.Z "Codename" — Short Theme' \
  --notes-file <RELEASE_NOTES_FILE>

6. Verify the finished release

bash
gh release view vX.Y.Z
gh run view <RUN_ID>

Confirm the workflow conclusion is successful, the release title and notes are correct, and GoReleaser attached the expected artifacts. Report the version, release URL, workflow result, and any recovery actions to the user.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Release Kanban Md AI skill do?

Release kanban-md through its tag-triggered GoReleaser workflow, monitor CI, recover safely from failures, and publish user-facing GitHub release notes. Use when the user asks to release, tag, publish, or prepare release notes for kanban-md. Do not use for ordinary commits or unreleased changelog edits.

Why use Release Kanban Md on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/antopolskiy/kanban-md/tree/main/.agents/skills/release-kanban-md. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Release Kanban Md?

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 Kanban Md?

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

Is the Release Kanban Md AI skill free?

Yes. It is published on GitHub by antopolskiy 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 👇