autopilot
Use when the user dictates an app, site, bot, or feature to build end-to-end and expects a finished result without reviewing specs, tickets, or code — vibecoding sessions, non-technical users, "собери под ключ", "build it for me", "не задавай лишних вопросов" requests. Also use when the user invokes /autopilot, or asks for a build in a named mode, depth or finish — «полный автомат», «режим интервью», «погриль меня», «ручной режим», «строго по брифу», «проработай глубоко», «вылижи до эталона».
nick-vels · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add nick-vels/skills --skill autopilot技能说明
name: autopilot description: Use when the user dictates an app, site, bot, or feature to build end-to-end and expects a finished result without reviewing specs, tickets, or code — vibecoding sessions, non-technical users, "собери под ключ", "build it for me", "не задавай лишних вопросов" requests. Also use when the user invokes /autopilot, or asks for a build in a named mode, depth or finish — «полный автомат», «режим интервью», «погриль меня», «ручной режим», «строго по брифу», «проработай глубоко», «вылижи до эталона». argument-hint: "[full|semi|interview|manual] [strict|deep] [polish] что нужно построить или путь к brief.md"
Autopilot
Overview
Autopilot flies a dictated idea from words to a working project in one dialogue, without making the user approve each stage. It is self-contained: every rule it needs lives in phases/. No other skill has to be installed.
Two ideas carry the whole design.
The order is the product. Code is written in the second-to-last phase. Everything before it exists to decide what to build, and everything after it exists to prove the right thing got built.
The brief is the contract, not the design. Two obligations follow from it, and they pull in opposite directions on purpose.
Nothing may quietly vanish. The user's original words become a numbered manifest before anything else happens, and every phase is gated on it. What breaks naive vibecoding is not bad code — it is a requirement that stopped existing somewhere around the third rewrite.
The brief is not the design. It is a silhouette: it describes the happy path and nothing underneath — no empty states, no failures, no interruptions, no limits. Working those out is legitimate work, not scope creep, and it is where much of the value of this process comes from. How far to take it is the user's dial, set by the depth parameter. What is never allowed at any setting is depth that detaches from the brief.
Reading this skill
This file is the orchestrator: modes, phase order, gates. The rules for each phase live in phases/ and are read at the moment that phase starts, not before — that is what keeps the working context small.
One file at a time, and never ahead. Breaking this does not feel like breaking it: the next files are small, the flight is planned, opening them while you are already reading seems tidy. What it does is put Phase 5's rules into the context Phase 1 is thinking in, and leave them there for the rest of the run. The unit of loading is the file, not the section — a read pulls in the whole thing, which is why anything one phase needs and another does not is its own file.
Twice only where the table says twice — 7-instruments.md in Phase 4, 9-memory.md in Phases 5 and 8, legitimate there because the run has usually been compacted in between. Everywhere else, re-reading because «details have faded» buys a copy of what is still in the context.
After a compaction, re-read the state, not the phases. state.js (it holds skillDir, the reviewers and the tickets), manifest.md, interfaces.md, and the file of the phase you are actually in — those four and nothing else. The pull is to reopen 5-subagents.md to recover the thread; that spends eight thousand tokens re-reading rules you are already executing, and the thread was never in them.
| Phase | Read | Produces |
|---|---|---|
| 0 Preflight | phases/0-modes.md, phases/0-preflight.md, then 0-instruments.md and 0-memory.md | mode announced, repo configured, .autopilot/ created |
| 1 Manifest | phases/1-manifest.md | brief.md, manifest.md |
| 2 Briefing | phases/2-briefing.md | answers recorded into the manifest |
| 3 Spec | phases/3-spec.md | spec.md |
| 4 Plan | phases/4-plan.md | tickets/NN-*.md (or none — see tiers), interfaces.md seeded |
| 5 Subagents | phases/5-subagents.md | code, commits, interfaces.md grown |
| 6 Review | phases/6-review.md | per-ticket review |
| 7 Instruments | phases/7-instruments.md — in Phase 4, when the tickets are cut | state.js, dashboard.html + index.html (opened for the user) |
| 8 Final | phases/8-final.md | blind acceptance, final report |
| 9 Memory | phases/9-memory.md — in Phase 5 and Phase 8 | CLAUDE.md / AGENTS.md, docs/adr/ — the project as the next session will find it |
| — | phases/5-repair.md — when a ticket comes back anything other than DONE | the repair path, retries, spec amendments |
| — | phases/rationalizations.md — on a failed gate, on catching yourself excusing something, once before the report | nothing; it is a checklist |
| — | phases/polish.md — only with the polish parameter | доводка rounds |
The words the user sees
The phases have English names in this file and the user never sees them. In the chat, on the dashboard and in the final report there is exactly one Russian word per stage, and it is this one. Two vocabularies for one process is how a person reads the README and then cannot find any of it on the screen.
| Phase | stages[].id | Пользователю |
|---|---|---|
| 0 Preflight | preflight | Подготовка |
| 1 Manifest | manifest | Требования |
| 2 Briefing | briefing | Брифинг |
| 3 Spec | spec | Спецификация |
| 4 Plan | plan | План |
| 5 Subagents | build | Разработка |
| 6 Review | review | Код-ревью |
| 8 Final | final | Приёмка |
Two rules hold this together:
- «Сборка» — это весь прогон, а не один этап. «Сборка идёт», «сборка прервалась», «продолжи сборку» — про процесс целиком. Поэтому пятый этап называется «Разработка»: иначе одно слово означает и часть, и целое. И «сборка» в смысле
npm run build— тоже не он. - Единица работы — «таск». Не «задача», не «тикет», не «issue». «Задача» — это то, что поставил пользователь (бриф); одно слово на две разные вещи ломает и отчёт, и дашборд.
Phases 7 and 9 are not sequential, and each is split in two along the line where it is read. The instrum
阅读完整来源 ↗