Create Workflow logo

Create Workflow

Community
ahmadrosid
create-workflow

Create and run user-triggered workflows with declared steps. Use when the user asks about a workflow or wants a verifiable recipe (fetch, compare, summarize) they can run on demand from chat or the dashboard.

Overview

Publisherahmadrosid
Repositorynakama
Skill namecreate-workflow
Stars
492
Forks
91
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Create Workflow 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/ahmadrosid/nakama/tree/main/packages/plugins/workflows/skills/create-workflow
  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/ahmadrosid/nakama.git /tmp/nakama
mkdir -p .claude/skills
cp -r /tmp/nakama/packages/plugins/workflows/skills/create-workflow .claude/skills/create-workflow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create Workflow 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 Create Workflow 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 Create Workflow 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.

When the user wants a workflow they can run on demand (for example "morning brief"), explain the step recipe clearly before saving.

Use plugin_workflows__create_workflow with kind (never type). Last step must be summarize with prompt (never instruction).

json
[
  { "id": "news", "kind": "tool", "tool": "web_fetch", "input": { "url": "https://news.ycombinator.com" } },
  { "id": "summary", "kind": "summarize", "prompt": "Write a brief from the receipts only." }
]
  • tool — assigned profile or MCP tool that can run locally; input must match that tool's schema. Use web_fetch for URLs. Do not use web_search — it only runs inside a provider chat turn.
  • template — substitutes values into text only. Writing “extract stories” in a template returns those instructions; it does not call AI, parse content, or produce structured JSON.
  • compare / assert — deterministic checks on prior receipts. compare.op is eq | near | contains. Do not use compare as free-text analysis
  • exactly one final summarize — turns the receipt bag into prose (no tools). It cannot be an intermediate extraction step or feed a later database step.

For extraction or analysis before a write, use an available tool that actually performs that work. Verify its input and output schema; do not invent a tool or output field. If no suitable tool is assigned, explain the missing capability instead of saving a recipe that cannot fulfill the request.

References use the tool's actual output shape: {{steps.fetch.content}}, not an assumed .output wrapper. Missing references stop the run. Explicit null values are allowed, so check required data with assert/compare steps before writes when applicable.

For a requested quantity such as five saved stories, check the extraction count and the database result with an assert/compare step. Inspect receipts before claiming success: a completed SQL call with changes: 0 does not prove stories were saved. Do not blindly rerun writes after a failure; inspect which writes already completed.

When the user names a profile to run as, confirm that profile and pass its agentId. Omit agentId to use the current chat profile.

When the user asks to run a saved workflow, use plugin_workflows__list_workflows to find it, then plugin_workflows__run_workflow. Pass input when the recipe uses {{input.*}} bindings.

When the user wants to change an existing workflow, use plugin_workflows__update_workflow.

Do not use workflows for clock-driven jobs — use create_automation for schedules.

Frequently asked questions

What does the Create Workflow AI skill do?

Create and run user-triggered workflows with declared steps. Use when the user asks about a workflow or wants a verifiable recipe (fetch, compare, summarize) they can run on demand from chat or the dashboard.

Why use Create Workflow on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ahmadrosid/nakama/tree/main/packages/plugins/workflows/skills/create-workflow. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Create Workflow?

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 Create Workflow?

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

Is the Create Workflow AI skill free?

Yes. It is published on GitHub by ahmadrosid 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 👇