Cursor Automations：工程工厂模式（相邻） Cursor Automations: Engineering Factory Patterns

这条用法在做什么What this use does

同生态的 Cursor 云端 Agent：main 推送安全审查→Slack；PR agentic codeowners；PagerDuty→Datadog 调查→Slack+修复 PR；周仓 digest；晨间覆盖率 PR；Slack 缺陷分拣→Linear→尝试修复。 Same-ecosystem Cursor cloud Agents: main-push security review→Slack; PR agentic codeowners; PagerDuty→Datadog investigation→Slack+fix PR; weekly repo digest; morning coverage PR; Slack bug triage→Linear→attempted fix.

收录理由Why we listed it 非 Grok Bot UI，但同属 Cursor 生态「常开 Agent」模式，适合 Coding/DevOps 筛选。 Not the Grok Bot UI, but the same Cursor-ecosystem “always-on Agent” pattern. Useful when filtering for Coding/DevOps.

上手路径How to start

1. 先跑一次安全范围Run a safe first pass

   先在可撤回、不外发的范围内试跑一遍，确认输出可用，再考虑扩大权限。 Try it first in a reversible, non-outbound scope. Confirm the output, then widen permissions.

2. 存 SkillSave a Skill

   把跑通的步骤存成 Skill，下次同类任务直接复用，而不是重新口述。 Save the working steps as a Skill so the next similar job reuses them instead of being re-explained.

3. 再上 RoutineThen add a Routine

   输出稳定后再打开例行 / 定时。本条已有例行形态，不要一上来就无人值守外发。 Turn on the routine / schedule only after output is stable. This item already has a routine shape — do not start unattended outbound.