Bcut Release logo

Bcut Release

Community
JimLiu
bcut-release

Release BaoCut Electron desktop apps through GitHub Actions tags by default; use local/manual packaging only when explicitly requested. Also handles App version bumps, release continuation and portable signing backups; excludes craft skills and legacy standalone CLI releases.

Overview

PublisherJimLiu
Repositorybaocut
Skill namebcut-release
Stars
687
Forks
57
Bundled files
5
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.

  • 5 bundled files

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

  • Open source

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

Installation

Install the Bcut 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/JimLiu/baocut/tree/main/.agents/skills/bcut-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/JimLiu/baocut.git /tmp/baocut
mkdir -p .claude/skills
cp -r /tmp/baocut/.agents/skills/bcut-release .claude/skills/bcut-release
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bcut 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 Bcut 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 Bcut 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.

BaoCut desktop releases

This is the Electron v3 App (com.baocut.app). The older baocut-app skill is a reference, not this checkout's executable workflow. Keep this developer skill outside the App's craft skills/; do not invoke legacy GPUI/npm/Homebrew releases.

Select the workflow

User intentRead and follow
Ordinary release/publish request; no method specifiedTag release — default. Prepare the version and frozen source, then push its release tag; Actions builds/releases Mac arm64 and Windows CPU/CUDA/Vulkan.
Explicit local package/candidate, traditional or manual release, single-platform recovery/continuationTraditional release. Honor the requested platforms and local-only/public scope.
Signing identity, portable backups or GitHub credentials onlySigning/backups. Do not create a tag or publish.

Load only the reference needed for the selected intent. Do not ask users to choose between the two release methods when they have not specified one: use tag release. Do not silently fall back to traditional packaging after an Actions failure. A specific local-only or platform-only instruction overrides the default all-platform scope; follow the user's explicit method and limits.

Shared release constraints

  • Inspect git status before edits; preserve unrelated or concurrent work. Commit task-owned source changes before freezing a release. Follow repository commit, current-task push authorization and worktree cleanup rules; do not reuse push authorization from another task or request it again when already granted here.
  • apps/desktop/package.json owns the App version. Synchronize root version and lockfile through npm; do not bump Cargo or protocol versions for an App release.
  • Query actual releases/feeds before choosing a build. Builds strictly increase; already published tags/files are immutable.
  • Keep the tag and all platform artifacts tied to one full source SHA. Never ship dirty-source binaries, private signing materials or intermediate notary submissions.
  • For every new published version/build, follow release notes: inventory the full commit/PR range, summarize large ranges in batches, reconcile coverage and publish the consolidated changelog. A local candidate keeps the same notes locally; platform continuation reuses the existing version's range.
  • After every public release or platform continuation, check the download links using download links. The READMEs and baocut.com link to baocut.com/download/<id>, which follows GitHub Releases by itself. Do not edit the READMEs or redeploy the site for a release; verify that baocut.com serves the new build.
  • Report actual checks and skips. A tag push or credential check alone is not a completed release; publication requires successful jobs, public read-back, feeds, verified release notes and a passing baocut.com download check.

Complete public release

After all selected platforms have published, public assets and feeds have passed read-back, and the consolidated release notes are verified, mark the newest stable desktop release Latest in GitHub's Releases tab:

bash
gh release edit "$release_tag" --repo "$release_repo" --latest
gh api "repos/$release_repo/releases/latest" --jq '.tag_name'

Use the verified repository and tag for this task; the read-back must match that tag. Platform publishers preserve the previous Latest while validation and uploads are in progress, so this final step is required even when Actions succeeds. Local candidates, drafts and prereleases do not advance Latest. When continuing an older release, keep a newer published desktop version/build as Latest. Include the verified Latest tag in the completion report.

The desktop guide owns packaging mechanics; mode-specific references explain when to load it. Requests only to change release configuration must not create a release tag or publish.

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 Bcut Release AI skill do?

Release BaoCut Electron desktop apps through GitHub Actions tags by default; use local/manual packaging only when explicitly requested. Also handles App version bumps, release continuation and portable signing backups; excludes craft skills and legacy standalone CLI releases.

Why use Bcut Release on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/JimLiu/baocut/tree/main/.agents/skills/bcut-release. 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 Bcut 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 Bcut Release?

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

Is the Bcut Release AI skill free?

It is published on GitHub by JimLiu. 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 👇