Overview
Requires Python 3.11+, uv, ffmpeg, ffprobe, and tesseract on PATH. An image-capable agent must approve every cue; scripts only discover candidates and refine frame boundaries. Run scripts via `uv run`.
Operations
Each script returns structured JSON — see the script contract.
| Op ID | Script | Common flags |
|---|---|---|
forced_narrative_exact.audit_completeness | audit_completeness.py | --input, --output |
forced_narrative_exact.build_report | build_report.py | --output |
forced_narrative_exact.refine_boundaries | refine_boundaries.py | --input, --output |
forced_narrative_exact.scan_caption_band | scan_caption_band.py | --input, --output |
forced_narrative_exact.self_test | self_test.py | --input, --output |
forced_narrative_exact.validate_report | validate_report.py | --input |
Do not use for
- speech-to-text captions from audio (use `speech-captions`)
- sidecar SRT/VTT compliance or format conversion (use `captions-compliance` / `subtitles`)
- broad graphics/title/lower-third inventories without exclusive frame-accurate dialogue delivery (use `vision-analysis`)
- program act/commercial structure (use `program-master`)
- Related skills: `inspect`, `program-master`, `timecode`, and `vision-analysis`.