Tutorial logo

Tutorial

CommunityPopular
Q00
tutorial

Interactive tutorial teaching Ouroboros hands-on

Overview

PublisherQ00
Repositoryouroboros
Skill nametutorial
Stars
6K
Forks
605
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 Q00 on GitHub. Read the source before you install it.

Installation

Install the Tutorial 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/Q00/ouroboros.git /tmp/ouroboros
mkdir -p .claude/skills
cp -r /tmp/ouroboros/skills/tutorial .claude/skills/tutorial
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tutorial 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 Tutorial 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 Tutorial 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.

/ouroboros:tutorial

Interactive tutorial that teaches Ouroboros through hands-on experience.

Usage

ooo tutorial
/ouroboros:tutorial

Tutorial Flow

When this skill is invoked, guide the user through a learn-by-doing tutorial with progressive disclosure.


Phase 1: The Hook (30 seconds)

Start with enthusiasm and immediate value:

Welcome to the Ouroboros Tutorial!

In the next 5 minutes, you'll:
- Transform a vague idea into a precise specification
- See Ouroboros expose hidden assumptions you didn't know you had
- Generate a validated Seed ready for AI execution

Let's start with YOUR idea. What's something you've been wanting to build?

[Wait for user response - any project idea works]

Phase 2: The Interview Experience (2 minutes)

Once they share an idea, immediately start a simplified interview:

Great choice! Let me show you how Ouroboros thinks about this.

[Ask 3-4 targeted Socratic questions about their idea]
- "What's the primary problem this solves?"
- "Who are the main users?"
- "What's the one feature that would make this useful immediately?"

Notice something? Each question exposed an assumption you hadn't articulated.
This is the "aha moment" - requirements clarity BEFORE writing code.

Phase 3: The Quick Win (1 minute)

Generate a mini-seed to show immediate value:

Based on your answers, here's what we've uncovered:

[Display a simplified seed structure]

Goal: [their goal refined]
Constraints: [3 key constraints they mentioned]
Success Criteria: [2-3 clear metrics]

Ambiguity Score: 0.XX [show progress from vague to clear]

This seed is now ready for AI execution. No more "build me X" and hoping for the best!

Phase 4: Feature Discovery (1 minute)

Progressive disclosure of features:


Now that you've seen the core magic, here's what else Ouroboros can do:

Immediate Wins (Available Now):
- ooo unstuck    - 5 lateral thinking personas when you're blocked
- ooo seed       - Generate full specifications from interviews
- ooo evolve     - Evolutionary loop until ontology converges

Advanced Features (Setup Required):
- ooo run        - Execute with visual TUI dashboard
- ooo evaluate   - 3-stage quality verification
- ooo status     - Track project drift in real-time

Want to try any of these now? Or shall I show you the full workflow?

Phase 5: The Real Workflow (30 seconds)

Show the complete pipeline:


The Complete Ouroboros Workflow:

Idea → Interview → Seed → Route → Execute → Evaluate
  ↓        ↓         ↓       ↓        ↓         ↓
Vague    Clear    Frozen   Right    Build    Verified
      Assumptions   Spec    Model    Visibly     Quality

5 commands from idea to validated result:
1. ooo interview "your idea"        # Expose assumptions
2. ooo seed                        # Crystallize spec
3. ooo run                         # Execute with TUI
4. ooo evaluate                    # 3-stage verification
5. ooo status                      # Check drift

Ready to try your first real project?

Phase 6: Call to Action


Your First Real Project awaits!

Pick a path:

Path A: Start Fresh
  ooo interview "your actual project idea"

Path B: Learn More
  ooo help    # Full command reference

Path C: Setup Full Features
  ooo setup   # Enable TUI, evaluation, drift tracking

Which path interests you?

Tutorial Principles

  1. Immediate Value - Show something useful in the first 30 seconds
  2. Learn by Doing - Don't just explain, have them experience it
  3. Progressive Disclosure - Reveal features gradually, not all at once
  4. Quick Wins - Celebrate small milestones throughout
  5. Clear Next Steps - Always give them a specific action to take

Tutorial Checkpoints

Track progress through these checkpoints:

  • User shares an idea
  • User experiences the "aha moment" of exposed assumptions
  • User sees their first mini-seed generated
  • User understands the value proposition
  • User chooses a next step (path A, B, or C)

Common Tutorial Responses

"I don't have a project idea"

No problem! Let's use a classic example: a task management CLI.

[Continue tutorial with task management CLI example]

"This seems complicated"

It's actually simpler than it sounds. Let me show you the 3 commands you'll use 90% of the time:

1. ooo interview "idea"  # Clarify what you want
2. ooo seed             # Generate the spec
3. ooo run              # Build it

Everything else is optional power-user features.

"How is this different from just prompting Claude?"

Great question! The difference is:

Without Ouroboros:
  "Build me a task CLI" → Claude guesses → You realize it's wrong → Rewrite prompt → Repeat

With Ouroboros:
  Interview → Hidden assumptions exposed → Precise spec → Claude builds exactly what you want → First try

The interview saves you hours of iteration.

Success Metrics

A successful tutorial ends when:

  • User has experienced the interview process
  • User understands the seed specification concept
  • User knows their next step
  • User feels confident to try their real project

Tutorial Variations

For Technical Users

  • Emphasize the TUI dashboard and evolutionary loop
  • Show cost optimization features (PAL Router)
  • Highlight evaluation pipeline

For Non-Technical Users

  • Focus on the interview and clarification process
  • Emphasize the "translate ideas to specs" value
  • Minimize technical jargon

For OMC Users

  • Highlight key differences (TUI, specs, cost optimization)
  • Show migration path from OMC commands
  • Compare feature sets side-by-side

RFC #1392 State Breadcrumb Footer

Your final response MUST end with exactly one breadcrumb footer line:

◆ <current state> → next: <recommended action>

Derive <current state> from live session state via ouroboros_session_status when that MCP projection is available; otherwise derive it from this skill's actual outcome. Never use a linear Step N of M footer because Ouroboros is an evolutionary loop. When the next action is genuinely a choice, list 2-3 honest options in the next: clause. The breadcrumb line must be the last line of the response.

Frequently asked questions

What does the Tutorial AI skill do?

Interactive tutorial teaching Ouroboros hands-on

Why use Tutorial on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Q00/ouroboros/tree/main/skills/tutorial. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Tutorial?

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 Tutorial?

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

Is the Tutorial AI skill free?

Yes. It is published on GitHub by Q00 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 👇