mirror of
https://github.com/hanzoai/video.git
synced 2026-11-03 04:21:39 +00:00
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)
2.0 KiB
2.0 KiB
Script Director - Avatar Spokesperson Pipeline
When To Use
Turn the approved brief into scene-safe spoken copy for an avatar presenter. The quality bar is not literary flourish. It is spoken clarity, believable pacing, and one clean point per scene.
Reference Inputs
docs/avatar-spokesperson-best-practices.mdskills/creative/storytelling.md
Process
1. Write For Speech, Not For Slides
Prefer:
- short sentences,
- direct verbs,
- one idea per beat,
- explicit transitions,
- conversational emphasis.
If the copy sounds like a brochure when read aloud, rewrite it.
2. Break Into Scene-Safe Chunks
Avatar scenes are easier to manage when each section is compact. A useful starting point is:
- hook,
- value statement,
- proof or feature beat,
- CTA.
3. Keep On-Screen Text Light
The presenter is already carrying attention. Use on-screen text only for:
- product names,
- short proof points,
- CTA copy,
- legal or compliance text that must appear.
4. Use Metadata For Delivery Notes
Recommended metadata keys:
scene_copy_mapcta_languagepronunciation_notessupplied_script_sourcelegal_text_requirements
5. Quality Gate
- the copy sounds spoken,
- scene lengths are realistic,
- CTA placement is clear,
- text overlays are restrained.
Mid-Production Fact Verification
If you encounter uncertainty during script writing:
- Use
web_searchto verify factual claims before committing them to the script - Use
web_searchto find reference images for visual accuracy - Log verification in the decision log:
category="visual_accuracy_check"
Every factual claim in the script should be traceable to the research_brief.
If you make a claim that isn't in the research, do additional research and
add the source. Do not invent statistics, dates, or attributions.
Common Pitfalls
- Overstuffing one scene because the script reads well on paper.
- Duplicating the same sentence in speech and large text overlays.
- Writing humor or improvisational beats the avatar path cannot sell.