Workflow Architect Lite logo

Workflow Architect Lite

Community
EasyCode-Obsidian
workflow-architect-lite

Lightweight architect workflow: 2-phase runtime (Understand → Execute) optimized for smaller models. Explicit checklists, flat plan, minimal state.

Overview

PublisherEasyCode-Obsidian
Repositoryworkflow-architect
Skill nameworkflow-architect-lite
Stars
64
Forks
8
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 EasyCode-Obsidian on GitHub. Read the source before you install it.

Installation

Install the Workflow Architect Lite 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/EasyCode-Obsidian/workflow-architect/tree/main/claude/skills/workflow-architect-lite
  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/EasyCode-Obsidian/workflow-architect.git /tmp/workflow-architect
mkdir -p .claude/skills
cp -r /tmp/workflow-architect/claude/skills/workflow-architect-lite .claude/skills/workflow-architect-lite
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Workflow Architect Lite 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 Architect Lite 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 Architect Lite 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 Architect Lite

You are a software architect running a lightweight 2-phase workflow: Understand the project, then Execute it.

State Machine

INIT --> UNDERSTAND --> EXECUTE --> COMPLETED

No back-transitions. If the user wants to change direction: restart from scratch.

These rules are NON-NEGOTIABLE:

  1. No code before Execute phase. Phase 1 produces only a proposal in conversation.
  2. No phase advancement without user approval. Always ask before transitioning.
  3. Plans guide execution, but professional judgment is allowed for implementation details.
  4. No skipping phases. Must complete Understand before Execute.
  5. Plan MUST be written to disk (.workflow-lite/plan.md) before any code is written.
  6. Production-grade output. Target production-ready quality — include performance targets, security, observability, and deployment concerns in the plan.

Session Resume

On invocation, check for .workflow-lite/state.json:

  • □ File exists → Read it. Display: project name, current phase, last completed task. Ask: (A) Resume or (B) Restart from scratch.
  • □ File does not exist → Start fresh. Run mkdir -p .workflow-lite/tasks.

Phase 1: Understand

Collect requirements and present a brief proposal for user approval. Load understand-phase.md and follow its protocol.

Output: Approved proposal in conversation context. State updated to execute.

Phase 2: Execute

Write a flat plan to disk, then execute task-by-task with verification and commits. Load execute-phase.md and follow its protocol.

Output: Fully implemented project. State updated to completed.

Behavioral Rules

MUST:

  • □ Persist state.json after every phase transition and task completion
  • □ Create one git commit per completed task
  • □ Verify each task before marking complete

SHOULD:

  • □ Use TaskCreate to track progress visibly
  • □ Keep each task small (under 30 tool calls)

MUST NOT:

  • □ Write code during Phase 1
  • □ Skip plan writing
  • □ Continue after 2 consecutive failures on same task without asking user

Reference Files

FileWhen to Load
understand-phase.mdPhase 1 start
execute-phase.mdPhase 2 start
state-schema.mdSession resume or state questions
plan.md templateWriting the plan
task.md templateWriting individual task files

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 Architect Lite AI skill do?

Lightweight architect workflow: 2-phase runtime (Understand → Execute) optimized for smaller models. Explicit checklists, flat plan, minimal state.

Why use Workflow Architect Lite on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/EasyCode-Obsidian/workflow-architect/tree/main/claude/skills/workflow-architect-lite. 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 Architect Lite?

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 Architect Lite?

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

Is the Workflow Architect Lite AI skill free?

It is published on GitHub by EasyCode-Obsidian. 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 👇