メニュー
Use only for an explicit @loom deploy request or deployment operation; do not select this skill for a plain @loom software-delivery request.
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/valkor-ai/loom --skill loom-deploy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。
Use when the user invokes /loom to route software delivery, knowledge, or deploy work through the Loom MCP server.
Mandatory routing skill. When the user explicitly invokes @loom, call the matching Loom MCP route before any repository work; plain delivery requests must start with loom.plan.
Lint and format GDScript files using gdtoolkit (gdlint + gdformat). Use after writing or modifying .gd files, when asked to check code style, fix lint errors, format code, or set up linting configuration. Also use when gdlint/gdformat errors appear in output and need diagnosis. Does NOT require Godot — runs as a standalone Python tool.
SOC 職業分類に基づく
SKILL.md を表示中
| name | loom-deploy |
| description | Use only for an explicit @loom deploy request or deployment operation; do not select this skill for a plain @loom software-delivery request. |
Deployment is a Loom MCP workflow. Route deploy requests to the registered loom.deploy* tools.
This skill is not the route for a plain @loom <request>. Plain delivery requests must go through the loom skill and loom.plan; use this skill only when the user explicitly requests deployment.
@loom deploy -> loom.deployRun.@loom deploy prepare -> loom.deployPrepare.@loom deploy up -> loom.deployUp.@loom deploy status -> loom.deployStatus.@loom deploy inspect -> loom.deployInspect.@loom deploy validate -> loom.deployValidate.@loom deploy logs -> loom.deployLogs.@loom deploy bootstrap -> loom.deployBootstrap.@loom deploy down -> loom.deployDown.@loom deploy repair -> loom.deployRepair.Follow the returned action result. For user_gate with preResponseContract, execute the contract before any visible response: call loom.inspectRequest, then call loom.readFieldGroup for only required requestReadPlan.groups, and present the returned deployment decision. During active_operation, only call the observation tools named by the result, obey observationPolicy, obey forbiddenActions, and do not report completion while finalResponsePolicy forbids it. During deployment asset repair, edit only the returned generated deployment assets or the returned modelRepairRef, then call the returned retryTool; do not retry asset repair through loom.deployRun. Never edit generated source-model/topology/facts snapshots directly. During deploy execution repair, edit only the returned application/runtime files and submit through the returned repair submit tool.
Do not invent deployment files, stack choices, preview URLs, ports, or repair scopes outside the current MCP result.
The current MCP deploy result remains the authority. Load no reference by default; load deploy references only when the MCP result supplies an exact reference load plan.
Protocol:
next.deployReferenceProfile.referenceLoadPlan or details.deployReferenceProfile.referenceLoadPlan.referenceLoadPlan entry contains refId, path, and reason. Resolve path relative to this skill's references/ directory.refId, stack names, failure text, or the references/ directory.deployReferenceProfile, leave deploy references unread.