Interactive tutorial teaching Ouroboros hands-on
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Interactive tutorial that teaches Ouroboros through hands-on experience.
ooo tutorial
/ouroboros:tutorial
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.
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.
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.
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).
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.
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.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use when the work spans several files or replaces a framework, language, auth, storage, or API layer (rewrites and migrations included), and the user wants it to end up working and tested. Asks only what is missing, writes a spec with acceptance criteria, then runs and verifies it in the background. Not for questions, small edits, or an existing Seed (use run).
中文简介正在准备中。当前显示原文说明。
Scan and manage brownfield repository/worktree defaults for interviews
中文简介正在准备中。当前显示原文说明。
Cancel stuck or orphaned executions
中文简介正在准备中。当前显示原文说明。
Use when the user wants proof that finished work meets its acceptance criteria, not just that tests pass: 'verify it is actually done', 'check it against the spec', 'evaluate the run'. Runs mechanical checks, a semantic review per criterion, and multi-model consensus when uncertain. With execution.auto_evolve on (the default), a rejected result with a Seed continues into a Ralph fix loop; pass auto_evolve: false to verify only.
中文简介正在准备中。当前显示原文说明。
Start or monitor an evolutionary development loop
中文简介正在准备中。当前显示原文说明。
Use when the user wants to build or change something but the request is vague or open-ended: 'help me figure out what to build', 'I'm not sure what it should do', 'add X' with no details, or no clear definition of done. Runs a short Socratic interview that turns the idea into goals, constraints, and acceptance criteria before any code is written. Not for simple questions, small clear edits, or an existing Seed.
中文简介正在准备中。当前显示原文说明。