Menu

Individual skill

loom-deploy

0upvotes

Use when the user invokes /loom deploy or /loom-deploy to prepare, run, inspect, validate, stop, bootstrap, or repair deployment through Loom MCP.

plugins/claude-code/skills/loom-deploy/SKILL.md

Read pinned source

Source commit 7cf9b229d22656ac28cb6fa47d26bb6230155b0a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Instructions only
Last checked
Nov 9, 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)
1,464
Repository last updated
Nov 3, 2026
License
Apache-2.0

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

Files and excerpt

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

Browse files
Read excerpt

# loom-deploy

Deployment is controlled by Loom MCP deploy tools. Use the matching `loom.deploy*` tool and follow its structured 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`, call only the observation tools named by the result, obey `observationPolicy`, obey `forbiddenActions`, and do not report completion while `finalResponsePolicy` forbids it. During asset repair, edit only the returned generated deployment assets or the returned `modelRepairRef`, then call the returned `retryTool`; never edit generated source-model/topology/facts snapshots directly. Do not retry asset repair through `loom.deployRun`. During deploy execution repair, edit only the returned application/runtime files and submit through the returned repair submit tool.

Do not infer stack topology, generated file paths, preview URLs, ports, or repair scope outside the current MCP result.

## Reference Loading

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:
- After a deploy MCP result, look for `next.deployReferenceProfile.referenceLoadPlan` or `details.deployReferenceProfile.referenceLoadPlan`.
Back to top