Release Please logo

Release Please

Organization
zenobi-us
release-please

Use when adopting or operating Release Please for automated versioning, changelog generation, and GitHub releases in single-package or manifest-mode repositories

Overview

Publisherzenobi-us
Repositorydotfiles
Skill namerelease-please
Stars
67
Forks
6
Bundled files
4
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.

  • 4 bundled files

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

  • Open source

    Published by zenobi-us on GitHub. Read the source before you install it.

Installation

Install the Release Please 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.
  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/zenobi-us/dotfiles.git /tmp/dotfiles
mkdir -p .claude/skills
cp -r /tmp/dotfiles/files/devtools/agent/bundles/developer/skills/devtools/release-please .claude/skills/release-please
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Release Please 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 Please 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 Please 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 Please

Lean operating guide for googleapis/release-please + googleapis/release-please-action.

Use this file for mode selection, quick setup, and guardrails. Use references for full examples, output contracts, and troubleshooting detail.

When to Use

Use this skill when you need:

  • Conventional Commit-driven version bumps and changelog generation
  • Automated Release PR creation and GitHub release tagging
  • Single-package or monorepo/manifest release orchestration
  • Migration off manual tags/changelog/version workflows

Choose a Mode

  • Single-package mode: one version stream from repo root.
  • Manifest mode: independent versions per path/package.

If you have more than one independently-versioned package, use manifest mode.

Manifest Identity Model

Keep these fields separate:

  • packages object key: repository-relative package path used for file discovery, manifest versions, and action output prefixes.
  • component: stable human-facing release identity and default tag prefix.
  • package-name: release-strategy package identity; many strategies discover it from package.json, Cargo.toml, or equivalent.
  • include-component-in-tag: whether tags include the component prefix; keep enabled for independently-versioned monorepo packages.

Example:

json
"packages/my-module": {
  "component": "my-module",
  "release-type": "node"
}

The package key stays packages/my-module; the default tag becomes my-module-v1.2.3.

Prerequisites (Quick)

  • Conventional Commits in default branch history (fix:, feat:, !/BREAKING)
  • Branch/workflow permissions sufficient for PR + release writes
  • Workflow trigger on your default release branch (main/master)

Recommended minimum workflow permissions:

  • contents: write
  • pull-requests: write
  • issues: write (optional but commonly useful)

Quick Start

A) Single-package (minimal)

Create .github/workflows/release-please.yml with googleapis/release-please-action@v4 on push to default branch.

B) Manifest mode

Add:

  • release-please-config.json
  • .release-please-manifest.json
  • workflow passing config-file + manifest-file

Lifecycle

  1. Merge Conventional Commit PRs.
  2. Release Please opens/updates the Release PR.
  3. CI validates release PR.
  4. Merge release PR.
  5. Action creates tag + GitHub Release.

Migration from Manual Releases

  • Stop manual changelog/tag edits on release-managed branch.
  • Seed manifest versions to currently released versions (manifest mode).
  • Choose stable component names before first managed release.
  • If changing an existing component name, plan tag-history migration; Release Please searches tags using the configured component.
  • Merge first Release PR and validate output shape usage in downstream workflow steps.

Common Failure Patterns (Summary)

  • No release PR: no releasable commits, wrong branch trigger, stale autorelease labels, or token/permission mismatch
  • Wrong bump: commit semantics mismatch with Conventional Commit expectations
  • Missing changelog entries: non-conventional squash titles/commit history
  • Manifest mismatch: package path keys don’t match actual directories
  • Release history not found: component changed but existing tags still use the old prefix
  • Workflow chain not firing: using GITHUB_TOKEN when downstream workflows require PAT/App token behavior

Guardrails

  • Enforce Conventional Commit linting in CI.
  • Keep release ownership explicit (who merges release PRs).
  • In monorepos, add package paths incrementally and assign stable, unique components.
  • Treat component renames as release migrations, not cosmetic config edits.
  • Avoid manual tags/changelog edits in release-managed paths.
  • Keep release PRs small and predictable.

Quick Verification Checklist

  • Workflow triggers on push to tracked branch
  • Permissions are explicitly set
  • Release PR appears after releasable commit
  • Merge creates expected component-prefixed tag and GitHub release
  • Manifest keys remain real repository paths
  • Downstream steps use path-prefixed action outputs, not component-prefixed output keys

References

Core upstream

Local references (read these for detail)

  • references/setup-examples.md
  • references/action-outputs.md
  • references/return-shapes.md
  • references/troubleshooting.md

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 Please AI skill do?

Use when adopting or operating Release Please for automated versioning, changelog generation, and GitHub releases in single-package or manifest-mode repositories

Why use Release Please on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zenobi-us/dotfiles/tree/master/files/devtools/agent/bundles/developer/skills/devtools/release-please. 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 Please?

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 Please?

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

Is the Release Please AI skill free?

Yes. It is published on GitHub by zenobi-us 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 👇