autopilot skillA
autopilot is agent-read markdown (skill) from yan-labs/yan-skills: 接收一句模糊指令,自动调查、分类、拆解为 XML 阶段计划、选 skill、定完成判定, 然后以无人值守模式通过 loop/goal + agent-mode 完整执行到底—— 包括自动部署、自动 E2E 测试、自动代码 review,不跳过任何阶段。 当用户扔过来一句宽泛任务时主动使用——"把 bug 修了"、"补测试"、 "优化性能"、"把这个功能做完"、"代码扫一遍"、"调查一下为什么 XX"。 也在用户说"autopilot"、"auto"、"帮我规划"、"自己搞定"、"直接跑"、 "你来拆"、"别问我怎么做"时触发。即使用户没有说这些关键词, 只要输入明显是未拆解的宽泛意图,也应该主动激活。 调用 autopilot = 授权全自动无人值守执行,不需要中途确认。.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Autopilot 接收一句话,自动拆解成结构化执行计划,然后以无人值守模式完整执行到底。 用户调用 autopilot 意味着:**授权 AI 完全自主地完成整套流程**—— 调查、实现、部署、E2E 验证、代码 review、二次部署、二次验证、收尾。 不需要中途确认,不允许跳过必要阶段或把未完成包装为完成。用户说“发版”“发布”“上线”未限定范围时,默认自动发布当前项目所有适用发布面;先检查和验证,结果逐项回读,不扩到无关项目。用户明确限制始终优先。 --- ## 安装与更新 来源:[Skills.sh](https://skills.sh/yan-labs/yan-skills) ```bash # 首次全局安装,或更新失败时重新安装 npx skills add yan-labs/yan-skills --skill autopilot -g -y # 将已安装的全局 Skill 更新到最新版 npx skills update autopilot -g -y ``` 若使用项目级安装,去掉安装命令中的 `-g`;项目级更新使用 `npx skills update autopilot -p -y`。 --- ## 编排者角色(CRITICAL · 贯穿全程) **你的主要任务是分析、编排和验证,具体任务尽可能交给 subagent 去执行。** 自己只做需求澄清、方案拆解、任务分发和结果验收; 实现类工作(读大量代码、写代码、跑测试、批量修改)一律用 Agent 工具派给 subagent 执行。 主循环是指挥,不是工兵——把上下文留给决策,把苦力留给 subagent。 这条规则与下方 `<behavior id="main-context-execution">` 和 `<rule id="context-hygiene">` 是同一件事的三种表述,互相加强,不冲突。 --- ## 执行与恢复规则(CRITICAL) 调用 autopilot 授权持续推进任务,不等于授权创建持久 Goal,也不要求先安排唤醒才允许工作。 - 默认采用 **state-only**:先把目标、阶段、验证条件和有界下一步写入 `progress.md`,然后在当前轮直接执行可推进工作。多个阶段可在同一轮完成,按阶段更新状态。 - 只有用户或系统明确要求持久 Goal 时,才采用 **explicit-goal**:创建或恢复该任务唯一的 Goal;不得因调用本技能、无人值守或等待部署而隐式创建。 - 只有确实需要跨轮等待或恢复时,使用当前平台实际可用的调度能力。CI/部署等待按项目规则安排当前任务唯一的定时恢复,登记目标任务及下一次运行时间后结束当前轮;不以前台反复查询代替恢复。 …
Read the whole file at its exact version.
How to install
mdr add yan-labs/yan-skills/autopilot@git:20260912.2c2f140mdr add yan-labs/yan-skills/autopilot@sha256:e8034680e30293bePin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_tb4qies4bwd46kly)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260912.2c2f140 latest | 2026-09-12 | 2c2f140 | 56,010 B | A | view · diff |
| git:20260912.36aadf0 | 2026-09-12 | 36aadf0 | 54,864 B | A | view · diff |
| git:20260906.3e67348 | 2026-09-06 | 3e67348 | 51,773 B | A | view · diff |
| git:20260905.47148ec | 2026-09-05 | 47148ec | 52,253 B | A | view · diff |
| git:20260903.9aa319a | 2026-09-03 | 9aa319a | 53,603 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (56010 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
yan-labs/yan-skills · 203 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_tb4qies4bwd46kly GET https://markdownregistry.com/api/v1/resolve?ref=yan-labs/yan-skills/autopilot GET https://markdownregistry.com/api/v1/blob/e8034680e30293be5c203cb2f2d528f48183ac03c1c9c1b1985f83d3465c052b
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
More from yan-labs/yan-skills
Every file in yan-labs/yan-skills