atlas
把声明性需求映射为实物级系统清单与上下文，便于治理与审计。
需使用 az CLI 与仓库/目录访问，可能涉及敏感信息泄露。
扫描云、仓库和本地并构建可查询的系统 atlas。
把你真实的云、代码库和本地目录都扫一遍，挖出系统结构、流程和数据，再用 Atlas knowledge graph 丰富成可查询的系统地图。适合做资产清单、盘点 Azure 账号、映射 git 仓库或寻找那些隐藏的约束和坑。特点是以实机扫描为主、图谱为辅，能把零散信息自动汇成一张可搜索的 atlas，帮助快速发现真实环境的细节。
▸ 展开 SKILL.md 英文原文
Atlas turns your STATED NEED into a real systems atlas by SCANNING your actual sources (Azure via `az`, git repos, local dirs) and process/data mining them, THEN enriching against the Atlas knowledge graph. Use this skill when asked to inventory/map your real systems, scan your cloud + repos + directories, mine the real processes or data they contain, or collect their real constraints/gotchas. (atlas, scan my systems, inventory our azure account, map my repos, real systems atlas, process mining, data mining, collect nuances, system discovery)
帮我安装这个 skill：https://raw.githubusercontent.com/a5c-ai/babysitter/main/plugins/atlas-unified/skills/atlas/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/a5c-ai/babysitter/main/plugins/atlas-unified/skills/atlas/SKILL.md"# atlas This skill turns a stated need into a **real systems atlas** by SCANNING your actual sources — Azure subscriptions (via read-only `az`), git repos, and local directories — and process/data mining them, THEN enriching the result against the Atlas knowledge graph. It is the brain of the `atlas` plugin. The scan is PRIMARY; the graph is SECONDARY. For non-trivial runs it delegates orchestration to `babysitter:babysit` using an atlas-specific `.a5c` process; for simple lookups it queries the graph directly. ## 1. Scan-first, graph-second The output you want is an evidence-backed inventory of **your** systems — e.g. `azure-inventory.json` (every real resource id + RG from `az`), `works