Files
calesthio 355fd2b7d6 Implementation spec: governance, decision intelligence, theme system, and E2E bug fixes
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)
2026-04-03 09:35:09 -07:00

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.md
  • skills/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_map
  • cta_language
  • pronunciation_notes
  • supplied_script_source
  • legal_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_search to verify factual claims before committing them to the script
  • Use web_search to 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.