/tutorial
Interactive tutorial teaching Ouroboros hands-on
Claude Code
$ npx -y skills add Q00/ouroboros --skill tutorial --agent claude-code
Codex
$ npx skills add Q00/ouroboros --skill tutorial -a codex -y
Cursor
$ npx skills add Q00/ouroboros --skill tutorial -a cursor -y
Gemini CLI
$ npx skills add Q00/ouroboros --skill tutorial -a gemini-cli -y
GitHub Copilot
$ npx skills add Q00/ouroboros --skill tutorial -a github-copilot -y
OpenCode
$ npx skills add Q00/ouroboros --skill tutorial -a opencode -y
Windsurf
$ npx skills add Q00/ouroboros --skill tutorial -a windsurf -y
SKILL.md
tutorial.SKILL.mdname: tutorial
description: "Interactive tutorial teaching Ouroboros hands-on"
disable-model-invocation: true
/ouroboros:tutorial
Interactive tutorial that teaches Ouroboros through hands-on experience.
Usage
ooo tutorial
/ouroboros:tutorial
Principles
1. Show something useful in the first 30 seconds. 2. Learn by doing: the user answers questions about their own idea. 3. Reveal features gradually. 4. Always end a phase with one specific next action. 5. Match the audience: technical users get the run, evaluate, and evolve details; non-technical users get the interview and plain language.
Flow (about 5 minutes)
1. **Hook.** Promise that in five minutes their vague idea becomes a precise specification, then ask what they want to build. If they have no idea, use a task-management CLI as the example. 2. **Interview.** Ask 3-4 Socratic questions about their idea (the problem it solves, the main users, the one feature that makes it useful now). Point out that each answer surfaced an assumption they had not stated. 3. **Mini-Seed.** Summarize their answers in Seed vocabulary:
Goal: <their goal, refined>
Constraints: <2-3 constraints they named>
Acceptance criteria: <2-3 checkable outcomes>
Do not invent an ambiguity score. Explain that `ooo interview` measures ambiguity and continues until it is low enough to freeze a real Seed. 4. **The workflow.** `Interview → Seed → Execute → Evaluate`, with evaluation feeding back into the next Seed generation:
ooo interview "your idea" # expose assumptions
ooo seed # freeze the Seed
ooo run # execute it
ooo evaluate # verify against the acceptance criteria
ooo status # check drift
`ooo unstuck` helps when blocked. `run`, `evaluate`, `evolve`, and `status` need the Ouroboros MCP server (`ooo setup`). 5. **Next step.** Offer: start a real project (`ooo interview "your actual project idea"`), the full reference (`ooo help`), or setup (`ooo setup`).
If the user asks how this differs from prompting an AI assistant directly: without a spec, the assistant guesses and you rewrite the prompt until it matches; with Ouroboros, the interview exposes hidden assumptions first, so the build starts from an agreed Seed. If it seems complicated, three commands cover most use: `ooo interview`, `ooo seed`, `ooo run`.
The tutorial is done when the user has experienced the interview, understands what a Seed is, and has chosen a next step.
RFC #1392 State Breadcrumb Footer
End the final response with exactly one line `◆ <current state> → next: <recommended action>`. Derive the state from live session state via `ouroboros_session_status` when available, otherwise from this skill's actual outcome. Never use a linear `Step N of M` footer; when the next step is a real choice, list 2-3 options.
Read more
name: tutorial description: "Interactive tutorial teaching Ouroboros hands-on" disable-model-invocation: true
/ouroboros:tutorial
Interactive tutorial that teaches Ouroboros through hands-on experience.
Usage
ooo tutorial /ouroboros:tutorial
Principles
1. Show something useful in the first 30 seconds. 2. Learn by doing: the user answers questions about their own idea. 3. Reveal features gradually. 4. Always end a phase with one specific next action. 5. Match the audience: technical users get the run, evaluate, and evolve details; non-technical users get the interview and plain language.
Flow (about 5 minutes)
1. **Hook.** Promise that in five minutes their vague idea becomes a precise specification, then ask what they want to build. If they have no idea, use a task-management CLI as the example. 2. **Interview.** Ask 3-4 Socratic questions about their idea (the problem it solves, the main users, the one feature that makes it useful now). Point out that each answer surfaced an assumption they had not stated. 3. **Mini-Seed.** Summarize their answers in Seed vocabulary:
Goal: <their goal, refined> Constraints: <2-3 constraints they named> Acceptance criteria: <2-3 checkable outcomes>
Do not invent an ambiguity score. Explain that `ooo interview` measures ambiguity and continues until it is low enough to freeze a real Seed. 4. **The workflow.** `Interview → Seed → Execute → Evaluate`, with evaluation feeding back into the next Seed generation:
ooo interview "your idea" # expose assumptions ooo seed # freeze the Seed ooo run # execute it ooo evaluate # verify against the acceptance criteria ooo status # check drift
`ooo unstuck` helps when blocked. `run`, `evaluate`, `evolve`, and `status` need the Ouroboros MCP server (`ooo setup`). 5. **Next step.** Offer: start a real project (`ooo interview "your actual project idea"`), the full reference (`ooo help`), or setup (`ooo setup`).
If the user asks how this differs from prompting an AI assistant directly: without a spec, the assistant guesses and you rewrite the prompt until it matches; with Ouroboros, the interview exposes hidden assumptions first, so the build starts from an agreed Seed. If it seems complicated, three commands cover most use: `ooo interview`, `ooo seed`, `ooo run`.
The tutorial is done when the user has experienced the interview, understands what a Seed is, and has chosen a next step.
RFC #1392 State Breadcrumb Footer
End the final response with exactly one line `◆ <current state> → next: <recommended action>`. Derive the state from live session state via `ouroboros_session_status` when available, otherwise from this skill's actual outcome. Never use a linear `Step N of M` footer; when the next step is a real choice, list 2-3 options.
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
Other skills on ouroboros.
More skills from other plugins.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…
adr-create
Create a new Architecture Decision Record with sequential numbering and AgentDB registration
Questions about tutorial.
- Which coding agents can use tutorial?
- tutorial installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.

