Rolecard Workshop Ops

Shared communication

Apply TW plain-language and guidance rules to user-facing work. Explain terms in context; preserve the user's chosen 新人/入门/熟练/老手 level without inferred changes. 新人 and 入门 receive detailed explanations; every level receives needed and bug explanations unless the user explicitly waives that scope. Soul and prose modes never disable this baseline. Load the shared reference for task entry, level management, or explanation decisions.

Before any operational write, use $consult-tavernweave-library with the rolecard-workshop-ops route to load A0 and the deployment/workshop guides. Keep public guidance separate from production coordinates, credentials, live state, and deployment authorization.

Use this skill for workshop infrastructure and the contract between a rolecard client, a public catalog, a package Gateway, identity provider, review tools, and storage. Keep local rolecard UI work out of this skill unless the failure crosses that boundary.

Operating Modes

Choose one mode and state it before acting.

Read-only diagnosis is the default. Inspect repository state, configuration names, health responses, public indexes, logs already available to the user, and contract tests. Do not deploy or alter remote state.
Change candidate is for preparing a bounded patch or deployment plan. Name the exact files, services, behavior change, verification, and rollback path. A candidate is not permission to deploy.
Authorized deployment requires an explicit user request to deploy or mutate the named environment. Reconfirm the resolved target, current release, backup/rollback surface, and verification commands immediately before execution.