Conductor Setup

Use this skill when configuring a repository for Conductor workspaces. When invoked directly, audit the setup against the conventions below and either apply the changes or report that none are needed.

Workflow

1. Inspect .conductor/settings.toml, .conductor/settings.local.toml, legacy conductor.json, .worktreeinclude, .conductor/*.sh, legacy root-level conductor-*.sh, package scripts, and repo docs.
2. Read references/conductor-docs.md before changing script fields or environment variable usage.
3. Pick the settings file: committed .conductor/settings.toml for team defaults, gitignored .conductor/settings.local.toml for machine-local overrides, ~/.conductor/settings.toml for user-wide preferences only. Migrate any conductor.json into .conductor/settings.toml and delete it unless the user wants it kept.
4. Keep script roles separate: scripts.setup prepares a new workspace, scripts.run.<id>.command starts long-running processes from the Run button, scripts.archive cleans up before archiving, scripts.run_mode decides whether run scripts may overlap.
5. Use Conductor variables over hard-coded paths and ports: $CONDUCTOR_WORKSPACE_PATH, $CONDUCTOR_ROOT_PATH (shared resources and caches), $CONDUCTOR_WORKSPACE_NAME, $CONDUCTOR_PORT, $CONDUCTOR_IS_LOCAL (local vs cloud).
6. Validate TOML syntax and run the narrowest relevant local check for any script you touch.

Conventions