メニュー
Use for project infra and architecture context: environments, adapters, runtime configuration, deployments, service dependencies, datastores, API contracts, ownership, incidents, and dependency blast radius.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/potpie-ai/potpie --skill potpie-infra-architectureコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SOC 職業分類に基づく
SKILL.md を表示中
| name | potpie-infra-architecture |
| description | Use for project infra and architecture context: environments, adapters, runtime configuration, deployments, service dependencies, datastores, API contracts, ownership, incidents, and dependency blast radius. |
Use this skill when the task touches environments, adapters, deployment behavior, runtime config, service dependencies, production incidents, or architecture changes.
Start from the service, environment, adapter, or dependency named by the task. Resolve identity before assuming keys:
potpie graph search-entities "<service env adapter dependency>" --limit 10
Read the service neighborhood with the graph workbench:
potpie graph read \
--subgraph infra_topology \
--view service_neighborhood \
--scope service:<service-name> \
--environment <dev|staging|prod|preview> \
--depth 2 \
--direction both \
--limit 20
Omit --environment only when the task is environment-agnostic. For broad
architecture work, run potpie --json graph describe infra_topology --view service_neighborhood --examples before choosing the read shape.
Use infra context for blast radius, where-to-look decisions, deployment changes, adapter selection, and incident debugging. Preserve environment qualifiers; a staging dependency is not proof of a production dependency.
Look for explicit topology facts: DEFINED_IN, DEPLOYED_TO, DEPENDS_ON,
USES, EXPOSES, HOSTED_ON, and OWNED_BY.
Record only source-backed topology or carefully labeled agent inferences. Use
authoritative_fact when evidence is an explicit source of truth such as
deployment config, service manifest, infra doc, ADR, or user statement. Use
agent_claim for lower-authority interpretation.
Use the workbench write flow:
potpie --json graph catalog --task "record infra architecture"
potpie graph search-entities "<service>" --type Service --limit 10
potpie --json graph describe infra_topology --view service_neighborhood --examples
potpie --json graph propose --file mutation.json
potpie --json graph commit <plan_id> --verify
potpie --json graph history --plan <plan_id>
Every durable infra fact needs an environment when the fact differs by environment, evidence when available, and a retrieval-grade description.
Architecture capture is harness-led: inspect authoritative sources and write semantic facts. Do not use scanner-driven graph updates or infer topology from directory names, imports, or package files alone.