Abu Plugin Builder logo

Abu Plugin Builder

Community
PM-Shawn
abu-plugin-builder

Create or edit a local Abu plugin in its dedicated creation conversation. Generate the package, then validate with plugin_prepare for user-reviewed installation.

Overview

PublisherPM-Shawn
RepositoryAbu-Cowork
Skill nameabu-plugin-builder
Stars
380
Forks
86
Bundled files
Instructions only
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 PM-Shawn on GitHub. Read the source before you install it.

Installation

Install the Abu Plugin Builder 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/PM-Shawn/Abu-Cowork.git /tmp/Abu-Cowork
mkdir -p .claude/skills
cp -r /tmp/Abu-Cowork/builtin-skills/abu-plugin-builder .claude/skills/abu-plugin-builder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Abu Plugin Builder 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 Abu Plugin Builder 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 Abu Plugin Builder 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.

First clarify the workflow and the smallest useful set of skills, connectors or agents. Creating a plugin does not require a marketplace.

Work only inside the current creation workspace. Never write to ~/.abu/plugin-packages, plugin-authors, plugin-operations or activation settings. Source edits do not change the installed version. Never install, enable or publish the plugin yourself.

Create .abu-plugin/plugin.json with a stable lowercase hyphenated name, version and a short description. Keep the name unchanged on edits. Skills go in skills/<name>/SKILL.md, with YAML name and description and Markdown instructions. Agents go in agents/<name>.md with YAML name/description and a nonempty system prompt; use unique names that do not shadow existing agents. Hooks and commands are not supported.

For a connector, declare mcpServers in the manifest or .mcp.json. Use stdio command, args, and env, or a supported HTTP URL. Never request credentials in chat, write them in source, invent secrets or copy credentials from another connector. For required credentials in env or headers, use ${config.API_TOKEN} placeholders (variable names: letters, digits, underscore). Abu renders these as secure fields in the installation preview. Do not use configuration placeholders in commands, arguments or URLs. Explain required user configuration. Do not run connector commands while generating or validating.

Before the first plugin_prepare call, state the exact package name you are about to use and tell the user it cannot be changed afterwards (it becomes the install key, package path and marketplace identity). Wait for the user's confirmation, then proceed. On later edits never propose a rename.

After writing files and obtaining that confirmation, call plugin_prepare with no arguments. Fix validation errors and repeat. Report the supported components and any unsupported parts. Tell the user to open Extensions → Plugins → Mine to preview and confirm installation/update. If the tool says this is not a plugin-creation conversation, ask the user to use Add → Create plugin; do not change author records or pass arbitrary paths.

When editing, always call plugin_prepare again after the final file change. Explain its status plainly: update-available means source changes are ready, but the running plugin is still the old version; direct the user to Extensions → Plugins → Mine → this plugin → Preview update → Update. unchanged means no update is needed. Never describe saved source as an installed update. Keep the final response short and tell the user the next UI action.

Frequently asked questions

What does the Abu Plugin Builder AI skill do?

Create or edit a local Abu plugin in its dedicated creation conversation. Generate the package, then validate with plugin_prepare for user-reviewed installation.

Why use Abu Plugin Builder on TypingMind?

Because you install it once and use it with any model. Abu Plugin Builder 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 Abu Plugin Builder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/PM-Shawn/Abu-Cowork/tree/main/builtin-skills/abu-plugin-builder. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Abu Plugin Builder?

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 Abu Plugin Builder?

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

Is the Abu Plugin Builder AI skill free?

It is published on GitHub by PM-Shawn. 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 👇