calesthio
2cd36fa8e0
Implements the 2026-04-02 transformation spec (Phases 1-8) and fixes all critical bugs found during 5-pipeline E2E testing. Governance & Decision Intelligence: - Pipeline-specific stage order in checkpoint (replaces global STAGES list) - Provider scoring engine (lib/scoring.py) with 7-dimension weighted ranking - Decision log artifact enforced at proposal/idea stage across all 10 pipelines - Delivery promise classifier prevents silent motion-to-still downgrades - Structured shot language in scene_plan schema (camera, lens, lighting, DOF) - Variation checker and slideshow risk scorer block samey output before render - Creative intake, capability extension, and creative-intake meta skills - Final self-review artifact with 5 mandatory checks before presenting output - Source media review contract for user-supplied footage Render & Theme System: - Remotion AnimatedBackground now derives colors from playbook (no more hardcoded dark blue fintech gradient on every video) - video_compose builds custom ThemeConfig from playbook YAML colors/fonts — custom playbooks flow through to Remotion automatically - Explainer component wires theme to all child components (charts, cards, etc.) - resolveAsset() handles absolute paths on Windows/Unix via file:// URIs - RENDERER_FAMILY_MAP synced with actual Remotion compositions Critical Bug Fixes: - Windows npx subprocess: run_command() resolves .cmd wrappers via shutil.which() - Silent renderer downgrade: Remotion failure now returns explicit error with options instead of silently falling back to FFmpeg - .env inline comment parsing strips trailing # comments from API keys - concat_path UnboundLocalError in video_compose finally block - audio_mixer and showcase_card capture=True kwarg bug - Selector estimate_cost() calls fixed (_select_tool -> _select_best_tool) - asset_manifest schema expanded with provider, license, subtype fields - screen-demo subtitle_gen moved from required to optional tools - Duration drift detection in post-render final review (>25% warns)
205 lines
5.9 KiB
YAML
205 lines
5.9 KiB
YAML
name: avatar-spokesperson
|
|
version: "2.0"
|
|
description: >
|
|
Presenter-led avatar pipeline for spokesperson videos, internal updates, onboarding,
|
|
sales intros, and short scripted explainers. Best for projects where a digital presenter
|
|
is the anchor and support graphics stay simple. EP orchestration adds quality gates for
|
|
lip-sync quality, presenter framing, and CTA landing.
|
|
category: custom
|
|
stability: production
|
|
default_checkpoint_policy: guided
|
|
|
|
orchestration:
|
|
mode: executive-producer
|
|
skill: pipelines/avatar-spokesperson/executive-producer
|
|
budget_default_usd: 2.00
|
|
max_revisions_per_stage: 3
|
|
max_send_backs: 3
|
|
max_wall_time_minutes: 12
|
|
|
|
extensions:
|
|
custom_scripts: true
|
|
custom_playbooks: true
|
|
custom_skills: true
|
|
custom_tools: false
|
|
|
|
required_skills:
|
|
- pipelines/avatar-spokesperson/executive-producer
|
|
- pipelines/avatar-spokesperson/idea-director
|
|
- pipelines/avatar-spokesperson/script-director
|
|
- pipelines/avatar-spokesperson/scene-director
|
|
- pipelines/avatar-spokesperson/asset-director
|
|
- pipelines/avatar-spokesperson/edit-director
|
|
- pipelines/avatar-spokesperson/compose-director
|
|
- pipelines/avatar-spokesperson/publish-director
|
|
- meta/reviewer
|
|
- meta/checkpoint-protocol
|
|
|
|
compatible_playbooks:
|
|
- clean-professional
|
|
- flat-motion-graphics
|
|
|
|
stages:
|
|
- name: idea
|
|
skill: pipelines/avatar-spokesperson/idea-director
|
|
produces:
|
|
- brief
|
|
- decision_log
|
|
tools_available: []
|
|
checkpoint_required: true
|
|
human_approval_default: true
|
|
review_focus:
|
|
- Avatar path and source reality are explicit
|
|
- CTA and audience fit the spokesperson format
|
|
- Missing capabilities are surfaced before scripting
|
|
success_criteria:
|
|
- Schema-valid brief artifact
|
|
- Brief records avatar path, narration source, and output shape
|
|
|
|
- name: script
|
|
skill: pipelines/avatar-spokesperson/script-director
|
|
required_artifacts_in:
|
|
- brief
|
|
produces:
|
|
- script
|
|
optional_tools:
|
|
- transcriber
|
|
tools_available:
|
|
- transcriber
|
|
checkpoint_required: true
|
|
human_approval_default: true
|
|
review_focus:
|
|
- Spoken copy is concise and natural
|
|
- Scene breaks are realistic for avatar delivery
|
|
- On-screen text remains restrained
|
|
success_criteria:
|
|
- Schema-valid script artifact
|
|
- Script sections map to scene-safe presenter beats
|
|
|
|
- name: scene_plan
|
|
skill: pipelines/avatar-spokesperson/scene-director
|
|
required_artifacts_in:
|
|
- script
|
|
optional_artifacts_in:
|
|
- brief
|
|
produces:
|
|
- scene_plan
|
|
tools_available: []
|
|
checkpoint_required: true
|
|
human_approval_default: true
|
|
review_focus:
|
|
- Speaker layout and background system are coherent
|
|
- Support overlays remain secondary to the presenter
|
|
- Aspect-ratio variants are planned realistically
|
|
success_criteria:
|
|
- Schema-valid scene_plan artifact
|
|
- Every scene has a defined speaker and support treatment
|
|
|
|
- name: assets
|
|
skill: pipelines/avatar-spokesperson/asset-director
|
|
required_artifacts_in:
|
|
- scene_plan
|
|
- script
|
|
optional_artifacts_in:
|
|
- brief
|
|
produces:
|
|
- asset_manifest
|
|
optional_tools:
|
|
- talking_head
|
|
- lip_sync
|
|
- tts_selector
|
|
- subtitle_gen
|
|
- image_selector
|
|
- audio_enhance
|
|
- video_selector
|
|
tools_available:
|
|
- talking_head
|
|
- lip_sync
|
|
- tts_selector
|
|
- subtitle_gen
|
|
- image_selector
|
|
- audio_enhance
|
|
- video_selector
|
|
checkpoint_required: true
|
|
human_approval_default: false
|
|
review_focus:
|
|
- Avatar generation path is explicit and honest (including no-avatar pivot if applicable)
|
|
- Narration, subtitle, and background assets are aligned
|
|
- Blocked paths are recorded instead of hidden
|
|
success_criteria:
|
|
- Schema-valid asset_manifest artifact
|
|
- All referenced asset files exist on disk
|
|
|
|
- name: edit
|
|
skill: pipelines/avatar-spokesperson/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:
|
|
- Presenter remains visually primary
|
|
- Graphics and captions reinforce rather than crowd
|
|
- CTA timing lands clearly
|
|
success_criteria:
|
|
- Schema-valid edit_decisions artifact
|
|
- Edit decisions cover the planned deliverables
|
|
|
|
- name: compose
|
|
skill: pipelines/avatar-spokesperson/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
|
|
- audio_enhance
|
|
tools_available:
|
|
- video_compose
|
|
- audio_mixer
|
|
- video_stitch
|
|
- audio_enhance
|
|
checkpoint_required: true
|
|
human_approval_default: false
|
|
review_focus:
|
|
- Lip sync or mouth timing is acceptable for the chosen path
|
|
- Subtitle placement and framing remain clean
|
|
- Audio is clear and presenter-focused
|
|
success_criteria:
|
|
- Schema-valid render_report artifact
|
|
- Output file exists and passes ffprobe validation
|
|
|
|
- name: publish
|
|
skill: pipelines/avatar-spokesperson/publish-director
|
|
required_artifacts_in:
|
|
- render_report
|
|
- final_review
|
|
optional_artifacts_in:
|
|
- brief
|
|
- script
|
|
produces:
|
|
- publish_log
|
|
tools_available: []
|
|
checkpoint_required: true
|
|
human_approval_default: true
|
|
review_focus:
|
|
- Hero export and derivatives are clearly labeled
|
|
- Metadata matches the spokesperson offer and audience
|
|
- Thumbnail or poster frame features the presenter cleanly
|
|
success_criteria:
|
|
- Schema-valid publish_log artifact
|
|
- Export package contains video and metadata outputs
|
|
|