Diagnose VoLum Windows/macOS native build, package, artifact, and CI failures. Use when tests, makedist scripts, GitHub Actions, installers, VST3 bundles, or portable zips fail.
Prepare VoLum PRs and GitHub releases. Use when creating release PRs, resolving release merge conflicts, editing GitHub release notes, checking artifacts, or discussing main/dev branch release flow.
Sync VoLum with upstream NAM sources. Use when bumping NeuralAmpModelerCore, cherry-picking from NeuralAmpModelerPlugin, comparing upstream-equivalent files, or discussing upstream sync strategy.
Safely change VoLum parameters, preset migration, user settings, or serialization. Use when adding/reordering params, renaming parameter names, changing chunk versions, or editing settings persistence.
Implement VoLum UI/layout changes efficiently. Use when modifying VoLum controls, PRE/AMP/POST triptych behavior, tuner/metronome overlays, sidebar/hero art, knob rows, or visual styling.
Opt-in implementation retro that turns observed friction into concrete tracked artifacts (new/edited rules, skills, scripts, docs) or local backlog items. Use only when the user invokes it ("captain hindsight" or "/captain-hindsight"). Not for trivial tasks.
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.