arrange

Guided arrangement — build song structure with sections, transitions, and energy flow

Guide the user through arranging their session using the V2 orchestration pipeline.

Orchestration Flow

  1. Session kernelget_session_kernel(request_text=<user's request>, mode="improve")
  2. Routeroute_request(<user's request>) for engine routes + semantic moves

Analysis Phase

  1. Scene matrixget_scene_matrix for the full clip grid
  2. Section purposesinfer_section_purposes to understand what each scene is doing
  3. Emotional arcscore_emotional_arc — does the song have build → climax → resolve?
  4. Repetition checkdetect_repetition_fatigue — are patterns overused?
  5. Motif analysisget_motif_graph for recurring patterns and fatigue risk
  6. Role conflictsdetect_role_conflicts to find competing tracks

Planning Phase

  1. Ask about target — what form? (verse-chorus, build-drop, through-composed). What energy arc?
  2. Plan arrangementplan_arrangement(target_bars, style) for section blueprint
  3. Propose movespropose_next_best_move(request_text) for arrangement semantic moves (e.g., create_buildup_tension, smooth_scene_handoff)
  4. Previewpreview_semantic_move(move_id) to see the gesture plan

Execution Phase

  1. Build sections — duplicate scenes, set names/colors, use transform_motif for melodic development
  2. Apply gesturesapply_gesture_template for transitions:
    • pre_arrival_vacuum — energy suck before drops
    • harmonic_tint_rise — filter opening for intros
    • re_entry_spotlight — highlight returning elements
    • tension_ratchet — stepped energy build
    • outro_decay_dissolve — gradual dissolution
  3. Add organic movementapply_automation_shape(curve_type="perlin") on filters/sends
  4. Verify arcscore_emotional_arc again to confirm improvement
  5. Perception checkcapture_audio + analyze_loudness to verify LRA > 2 LU

Summary

  1. Report — "What I did / what improved / what I protected / what remains"
  2. Session memoryadd_session_memory for arrangement decisions

For exploratory arrangement, use the branch-native experiment path (see livepilot-core SKILL.md, Flow B). Each section-ordering variant becomes one composer-source seed; attach pre-compiled plans via compiled_plans. When the user's request is vague or exploratory ("what would you do?", "surprise me with a structure"), bias get_session_kernel(freshness=0.7-0.9) to surface less-conservative branches.