菜单
Run one bounded Atris autonomy step. Use when the user says autopilot, run one tick, do the next thing, keep going, or make progress without losing proof.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Frontend aesthetics policy. Use when building UI, components, landing pages, dashboards, or any frontend work. Prevents generic ai-generated look.
Backward partner to /flow. Picks the next horizon from inbox + wiki + lessons, writes the reverse path as tagged tasks to TODO.md so /autopilot can pursue it tick by tick. Triggers on: endgame, what's the last move, where are we heading, reverse engineer, work backward.
Run one verified, scored improvement tick and write its receipt. Use when the user asks to improve, make this better, ship one thing, run a tick, or get smarter. `atris improve` alone shows metabolism vitals; use `atris improve tick` to ship work.
Dispatch coding work to an installed terminal agent — Codex, Cursor, Devin, Grok, or Atris Fast — as an interchangeable worker engine. Claude orchestrates: writes the bounded prompt, the engine builds, Claude verifies and lands. Triggers on: use codex, use cursor, use devin, use grok, use atris, engine, dispatch to, worker agent, second opinion build.
Working method distilled from Claude Fable 5 for daily-driver models (Opus, Sonnet). Use at session start, before any multi-step task, or when output feels shallow, hedged, or prematurely "done". Triggers on fable method, think like fable, deep pass.
Use the Render.com CLI v2.x (`render`) to inspect Render services, check CLI auth, list services and deploys, trigger deploys when explicitly requested, and view logs. Use when an agent needs Render CLI commands, non-interactive flags, deploy status polling, or service auto-deploy checks.
| name | autopilot |
| description | Run one bounded Atris autonomy step. Use when the user says autopilot, run one tick, do the next thing, keep going, or make progress without losing proof. |
| version | 1.0.0 |
| tags | ["autonomy","missions","workflow","proof"] |
Use this skill to turn vague momentum into one bounded mission step with proof. Do not loop forever inside the chat.
test -d atris || npx -y atris init
atris/atris.md and atris/MAP.md.atris mission run "<objective>" --owner <member>
atris mission status --status active --json
atris mission goal --json
Run one bounded step only:
atris mission tick <id> --verify --summary "<what changed>"
atris mission complete <id> --proof "<receipt or verifier>"
If the verifier fails, leave the mission running or blocked with the failure stated plainly.
atris mission run "<objective>" --owner <member> starts durable autonomous work.atris mission status --status active --json shows active work.atris mission goal --json exposes the current mission goal for runtimes that support visible goal mirroring.atris mission tick <id> --verify --summary "<summary>" records one proof-bearing step.atris autopilot --dry-run previews the older task-queue autopilot when available.atris autopilot --auto --iterations=1 runs one legacy queue tick when the repo uses that flow.