Make dangerous skills manual-only with `disable-model-invocation` and `context: fork`

SmartScope·medium signal

Skills auto-fire when their YAML `description` keyword-matches the conversation, which is exactly wrong for deploy/migration/destructive workflows that Claude might trigger 'helpfully' from context. Add `disable-model-invocation: true` to the SKILL.md frontmatter to require explicit user invocation, and set `context: fork` so the skill runs in an isolated context window instead of polluting the main session. This converts risky automation into a deliberate, sandboxed action.