Workflow Creator logo

Workflow Creator

OrganizationPopular
QwenLM
workflow-creator

Create or update reusable Dynamic Workflow JavaScript files under .qwen/workflows. Use when the user asks to create, save, edit, or reuse a Dynamic Workflow, including requests started from the Web Shell Workflows page.

Overview

PublisherQwenLM
Repositoryqwen-code
Skill nameworkflow-creator
Stars
27.9K
Forks
3.1K
Bundled files
1
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.

  • 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 QwenLM on GitHub. Read the source before you install it.

Installation

Install the Workflow Creator 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/QwenLM/qwen-code.git /tmp/qwen-code
mkdir -p .claude/skills
cp -r /tmp/qwen-code/packages/core/src/skills/bundled/workflow-creator .claude/skills/workflow-creator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Workflow Creator 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 Workflow Creator 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 Workflow Creator 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.

Workflow Creator

Create and maintain saved Dynamic Workflows for the current workspace.

Boundary

  • This skill manages .qwen/workflows/<name>.js files used by the workflow tool and exposed as /<name> slash commands.
  • Do not create or edit qwen-workflow-design/*.yaml; those Task Flow definitions are a different feature.
  • Use project scope by default. Write to ~/.qwen/workflows only when the user explicitly asks for a workflow shared across projects.

Workflow

  1. Inspect the current task and any existing workflow with the requested name. Ask a question only when the goal, ordering, or write scope is materially ambiguous.
  2. Choose a lower-case name containing only letters, digits, and hyphens. It must start with a letter and be at most 41 characters.
  3. Create the smallest script that captures the requested phases, dependencies, and final result. Do not add speculative branches, retries, or agents.
  4. Read the saved file back and verify its name, metadata, phase order, dependency flow, and final return value. Do not execute it unless the user also asks to run it.
  5. Report the saved path and slash command. In Web Shell, tell the user to return to Workflows and refresh the Saved tab if it is already open.

Script contract

  • Start with a literal metadata declaration:
js
export const meta = {
  name: 'Release readiness',
  description: 'Inspect, validate, and summarize a release candidate',
};
  • Use the sandbox globals phase(title), log(message), agent(prompt, options?), parallel(thunks), pipeline(items, ...stages), workflow(nameOrRef, args?), args, and budget. The workflow-authoring skill is the full reference for them — load it before writing anything beyond a trivial script.
  • Scripts cannot import modules or access the filesystem, shell, environment, or network directly. Put required reads and actions in explicit agent prompts.
  • Give every agent a complete, scoped prompt and a concise label. State whether it may edit files.
  • Express real concurrency as parallel([() => agent(...), () => agent(...)]). Do not pass already-started promises to parallel.
  • Keep dependent work sequential and pass prior results explicitly.
  • Put variable user input in args instead of hard-coding one-off values.
  • End every successful path with an explicit return of the final result. A trailing expression is not a return value.
  • Do not use node --check for validation: valid workflow scripts may contain top-level await and return because the runtime wraps them in an async function.

Updates

  • Preserve unrelated behavior and metadata when editing an existing workflow.
  • Do not overwrite an existing workflow with a different design unless the user requested that update.
  • Do not delete or rename a workflow unless the user explicitly asks.

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 Workflow Creator AI skill do?

Create or update reusable Dynamic Workflow JavaScript files under .qwen/workflows. Use when the user asks to create, save, edit, or reuse a Dynamic Workflow, including requests started from the Web Shell Workflows page.

Why use Workflow Creator on TypingMind?

Because you install it once and use it with any model. Workflow Creator 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 Workflow Creator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/QwenLM/qwen-code/tree/main/packages/core/src/skills/bundled/workflow-creator. 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 Workflow Creator?

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 Workflow Creator?

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

Is the Workflow Creator AI skill free?

Yes. It is published on GitHub by QwenLM 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 👇