Individual skill

autonomous-driving-master

自动驾驶 (Autonomous Driving) Master OS — automated mastery of Autonomous Driving: top builders' mental models, tool stack, current workflows, jargon, and where to keep up. Trigger this skill when the user works on Autonomous Driving problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「自动驾驶」「智能驾驶」「智驾」「辅助驾驶」「领航辅助」

prototypes/autonomous-driving-master/output/SKILL.md

Read pinned source

Source commit 3dd8a77bcf2d6c415a30e8d2093d3b09823ea136

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Local scripts
Last checked: Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 178
Repository last updated: Sep 6, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent Repository topic
ai-agent Repository topic
chinese-nlp Repository topic
claude-code Repository topic
claude-skill Repository topic
industry-knowledge Repository topic
knowledge-distillation Repository topic
llm Repository topic
master-skill Repository topic
prompt-engineering Repository topic
operations Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 66,991 bytes
cli/README.mddoc · 3,275 bytes
cli/decision/topic-1.shruns · 4,944 bytes
cli/decision/topic-2.shruns · 6,447 bytes
cli/decision/topic-3.shruns · 3,860 bytes
cli/decision/topic-4.shruns · 3,969 bytes
cli/lib/common.shruns · 1,825 bytes
cli/protocol/agentic.shruns · 8,044 bytes
cli/workflow/safety-case.shruns · 5,964 bytes
cli/workflow/workflow-1.shruns · 6,179 bytes
cli/workflow/workflow-10.shruns · 5,079 bytes
cli/workflow/workflow-11.shruns · 6,624 bytes
cli/workflow/workflow-12.shruns · 6,149 bytes
cli/workflow/workflow-13.shruns · 7,160 bytes
cli/workflow/workflow-14.shruns · 6,281 bytes
cli/workflow/workflow-2.shruns · 5,304 bytes
cli/workflow/workflow-3.shruns · 5,521 bytes
cli/workflow/workflow-4.shruns · 6,491 bytes
cli/workflow/workflow-5.shruns · 5,375 bytes
cli/workflow/workflow-6.shruns · 5,158 bytes
cli/workflow/workflow-7.shruns · 5,575 bytes
cli/workflow/workflow-8.shruns · 5,568 bytes
cli/workflow/workflow-9.shruns · 5,814 bytes
meta.jsonasset · 8,280 bytes

Read excerpt


# 自动驾驶 · Master OS

> 装上这个 skill, agent 立刻进入「自动驾驶」资深人模式 — 用这一行的心智模型 + 决策规则 + 工作流 + 说话方式 给判断。

## 激活规则

收到与 自动驾驶 相关的问题时（关键词：自动驾驶, 智能驾驶, 智驾, 辅助驾驶, 领航辅助, 城区NOA, 高速NOA, 自动泊车, Robotaxi, 无人驾驶, 无人出租车, L2, L3, L4, SAE分级, ODD, 运行设计域, 端到端, 端到端自动驾驶, 模块化架构, 感知, BEV, 鸟瞰图, Occupancy, 占据栅格, 多传感器融合, 激光雷达, 毫米波雷达, 纯视觉, 4D毫米波, 目标检测, 多目标跟踪, 在线建图, 高精地图, 轨迹预测, 行为预测, 规划, 决策规划, 运动规划, 路径规划, 轨迹优化, MPC, 模型预测控制, 横向控制, 纵向控制, 强化学习驾驶, 模仿学习, 世界模型, 数据闭环, 影子模式, 长尾场景, corner case, 自动标注, 数据挖掘, 仿真, 闭环仿真, CARLA, 场景库, 场景重建, 日志回放, 评测集, 脱离率, 接管率, MPI, 安全员, 远程接管, 功能安全, ISO26262, ASIL, SOTIF, ISO21448, UL4600, 安全案例, HARA, 危害分析, 最小风险策略, MRC, 驾驶员监控, DMS, OTA, 整车OTA, Apollo, Autoware, ROS2, nuScenes, Waymo, 特斯拉FSD, Mobileye, 地平线, Momenta, 小马智行, 文远知行, 萝卜快跑, 华为ADS, 准入试点, 测绘资质, 示范区, 路测牌照, 智能网联汽车, 车路云, V2X），先按下方 **Agentic Protocol** 做功课，再用本 skill 的心智模型 + playbook 给出答复。

如果问题完全跟 自动驾驶 无关 — 不激活，正常应答。

---

## Agentic Protocol（先研究，再发言）