OpenMontage/pipeline_defs/animation.yaml

name: animation
version: "2.0"
description: >
  Animation-first pipeline for motion graphics, diagram-led explainers, kinetic typography,
  math visuals, and stylized illustrative sequences. Features a research-first pre-production
  phase: the agent researches the topic and animation techniques, proposes concepts with
  animation mode selection and cost estimates, and gets explicit user approval before any
  assets are generated.
category: animation
stability: production
default_checkpoint_policy: guided

# Reference video input support
reference_input:
  supported: true
  analysis_depth: standard
  analysis_tools:
    - video_analyzer
    - transcript_fetcher
    - video_downloader
    - scene_detect
    - frame_sampler

extensions:
  custom_scripts: true
  custom_playbooks: true
  custom_skills: true
  custom_tools: false

required_skills:
  - pipelines/animation/executive-producer
  - pipelines/animation/research-director
  - pipelines/animation/proposal-director
  - pipelines/animation/script-director
  - pipelines/animation/scene-director
  - pipelines/animation/asset-director
  - pipelines/animation/edit-director
  - pipelines/animation/compose-director
  - pipelines/animation/publish-director
  - meta/reviewer
  - meta/checkpoint-protocol

orchestration:
  mode: executive-producer
  skill: pipelines/animation/executive-producer
  budget_default_usd: 2.00
  max_revisions_per_stage: 3
  max_send_backs: 3
  max_wall_time_minutes: 15

compatible_playbooks:
  recommended:
    - flat-motion-graphics
    - anime-ghibli
  also_works:
    - clean-professional
    - minimalist-diagram
  custom_allowed: true

stages:
  # ── Pre-Production ──────────────────────────────────────────────

  - name: research
    skill: pipelines/animation/research-director
    produces:
      - research_brief
    tools_available: []
    checkpoint_required: false
    human_approval_default: false
    review_focus:
      - Content landscape mapped with at least 3 existing pieces
      - Data points are specific and sourced, not vague
      - Animation technique references researched (at least 2)
      - At least 3 genuinely different angles discovered with animation_fit
      - All angles grounded in specific research findings
    success_criteria:
      - Schema-valid research_brief with at least 3 data_points
      - At least 3 angles_discovered, each with grounded_in references
      - At least 5 sources cited with URLs

  - name: proposal
    skill: pipelines/animation/proposal-director
    required_artifacts_in:
      - research_brief
    produces:
      - proposal_packet
      - decision_log
    tools_available: []
    checkpoint_required: true
    human_approval_default: true
    review_focus:
      - Concept options are genuinely different (animation mode, structure, hook)
      - Animation mode selection is grounded in technique research and tool availability
      - Each concept includes a reuse strategy (motifs, templates, transition family)
      - Production plan reflects actual tool availability from preflight
      - Cost estimate is itemized and honest
      - Free/local tool options are highlighted where applicable
      - "Audio architecture decided: single narrator / character dialogue / narrator+characters"
      - "Provider choice presented as comparison table with costs — agent recommends but user decides"
    success_criteria:
      - Schema-valid proposal_packet with at least 3 concept_options
      - selected_concept includes animation_mode and reuse_strategy
      - selected_concept includes audio_architecture (single_narrator | character_dialogue | narrator_plus_characters)
      - cost_estimate has itemized line_items with per-tool costs
      - cost_estimate includes provider_comparison table with at least 2 provider options
      - approval.status is "approved" or "approved_with_changes" before proceeding
    sub_stages:
      - name: sample
        description: "10-15 second animation preview for reference-driven productions"
        condition: "video_analysis_brief_exists"
        human_approval_default: true
        tools_available: [tts_selector, image_selector, video_selector, video_compose, audio_mixer, math_animate, diagram_gen]
        review_focus:
          - "Sample represents the approved animation mode faithfully"
          - "Visual identity matches approved playbook and style"
          - "Pacing matches reference inspiration"

  # ── Production ──────────────────────────────────────────────────

  - name: script
    skill: pipelines/animation/script-director
    required_artifacts_in:
      - proposal_packet
    optional_artifacts_in:
      - research_brief
    produces:
      - script
    optional_tools:
      - transcriber
    tools_available:
      - transcriber
    checkpoint_required: true
    human_approval_default: true
    review_focus:
      - Script beats are concise and animation-friendly
      - On-screen text remains readable and restrained
      - Timing structure leaves room for visual holds
      - Word count within +/-10% of duration target from selected concept
      - Script incorporates research data points where relevant
    success_criteria:
      - Schema-valid script artifact
      - Script sections map to distinct animation beats
      - Total duration matches selected concept target within 10%

  - name: scene_plan
    skill: pipelines/animation/scene-director
    required_artifacts_in:
      - script
    optional_artifacts_in:
      - proposal_packet
    produces:
      - scene_plan
    tools_available: []
    checkpoint_required: true
    human_approval_default: true
    review_focus:
      - Scene system is coherent and follows reuse strategy from proposal
      - Animation mode specified per scene, consistent with proposal
      - Transition logic is limited and meaningful
      - Every scene has a feasible tool path
    success_criteria:
      - Schema-valid scene_plan artifact
      - Every scene includes animation mode and visual treatment

  - name: assets
    skill: pipelines/animation/asset-director
    required_artifacts_in:
      - scene_plan
      - script
    optional_artifacts_in:
      - proposal_packet
    produces:
      - asset_manifest
    required_tools:
      - tts_selector
    optional_tools:
      - image_selector
      - video_selector
      - math_animate
      - diagram_gen
      - code_snippet
      - music_gen
    tools_available:
      - tts_selector
      - image_selector
      - video_selector
      - math_animate
      - diagram_gen
      - code_snippet
      - music_gen
    checkpoint_required: true
    human_approval_default: false
    review_focus:
      - Asset production path is explicit per scene
      - Reusable motifs and templates are prepared and referenced
      - Missing tool paths are surfaced honestly
      - Total cost within approved budget from proposal_packet
      - "Layer 3 skills read for EVERY generation tool before writing prompts (check agent_skills field)"
      - "Clip duration maximized (prefer 10s over 5s) to reduce API calls and cost"
      - "Use selector tools (video_selector, tts_selector, image_selector) — never call provider tools directly"
    success_criteria:
      - Schema-valid asset_manifest artifact
      - All referenced asset files exist on disk
      - layer3_skills_read list is present and includes all tools used for generation

  - name: edit
    skill: pipelines/animation/edit-director
    required_artifacts_in:
      - scene_plan
      - asset_manifest
    optional_artifacts_in:
      - script
    produces:
      - edit_decisions
    tools_available: []
    checkpoint_required: true
    human_approval_default: false
    review_focus:
      - Hold times and staggered reveals are preserved
      - Motion serves hierarchy rather than decoration
      - Timeline logic is consistent across scenes
      - Audio ducking configured for narration segments
    success_criteria:
      - Schema-valid edit_decisions artifact
      - Edit decisions cover all planned animation beats

  - name: compose
    skill: pipelines/animation/compose-director
    required_artifacts_in:
      - edit_decisions
      - asset_manifest
    optional_artifacts_in:
      - scene_plan
    produces:
      - render_report
      - final_review
    required_tools:
      - video_compose
      - audio_mixer
    optional_tools:
      - video_stitch
    tools_available:
      - video_compose
      - audio_mixer
      - video_stitch
    checkpoint_required: true
    human_approval_default: false
    review_focus:
      - Text and diagrams remain sharp at final resolution
      - Motion timing survives the final render
      - Audio sync matches the animatic intent
      - Duration within +/-5% of target
      - "Post-render self-review MANDATORY: extract keyframes, visually inspect each scene, flag weak frames before presenting to user"
    success_criteria:
      - Schema-valid render_report artifact
      - Output file exists and passes ffprobe validation
      - self_review_completed is true with per-scene quality notes

  - name: publish
    skill: pipelines/animation/publish-director
    required_artifacts_in:
      - render_report
      - final_review
    optional_artifacts_in:
      - proposal_packet
      - script
    produces:
      - publish_log
    tools_available: []
    checkpoint_required: true
    human_approval_default: true
    review_focus:
      - Platform packaging matches the animation style
      - Metadata reflects the actual topic, animation mode, and visual system
      - Thumbnail concept matches the final visual language
    success_criteria:
      - Schema-valid publish_log artifact
      - Export package contains video and metadata outputs