* docs(skills): fix unresolved cross-references in skill docs
Skill reference docs that live one directory below a skill root
(`references/`, `sub-agents/`) pointed at sibling skills with `../`,
which resolves inside the referencing skill instead of `skills/`.
Rewrite those to `../../<skill>/...` so every explicitly relative
path resolves from the file that contains it.
- faceless-explainer, pr-to-video, product-launch-video: story-design,
visual-design, motion-language, cut-catalog, sub-agents/frame-worker
now point at ../../hyperframes, ../../hyperframes-animation and
../../hyperframes-creative.
- music-to-video/references/planning.md: same fix for
hyperframes-creative design-spec and frame-presets.
- media-use/audio/references/{bgm,tts}.md: `../SKILL.md` ->
`../../SKILL.md` (the media-use skill root).
- hyperframes/references/frame-worker-core.md: the examples pointer now
reads ../../hyperframes-animation/examples/; the cut-catalog pointer
is written as skill-root shorthand (`references/cut-catalog.md`),
matching the other paths in that file, since the target is the
consuming workflow's own copy and has no single file-relative path.
- visual-design.md tables re-padded by oxfmt after the cell widened.
Co-Authored-By: Miguel Ángel <miguel.sierra@heygen.com>
* docs(skills): fix the two skill doc cross-references added since the first pass
* chore(skills): regenerate the skills manifest after the rebase
---------
Co-authored-by: Miguel Ángel <miguel.sierra@heygen.com>
Cinematic mode (pure embed) — one engine, six DNAs
Cinematic mode compiles ../../dna/ through engine.html (
make-composition.cjs). The old per-template HTML shells are retired —cinematic-creammaps todna: "cream"automatically; the other archived templates (memory-wall / champion / portrait-header, in _archive/) remain as design references only.
Use this mode for pure-embed asks (no rail): brand film, hype, social reel, showcase. The DNA locks the visual language (type, palette scheme, blend, motion grammar, hero three-act); safe-zones v2 parameterizes it to the scene (sampled accent, light- direction contact shadow, depth-match blur); the agent decides layout only (planes, blocks, per-line typography within the DNA).
Workflow
bash scripts/prepare.sh <project>→ matte ∥ transcript ∥ envelope → safe-zones v2- Pick a DNA (../../dna/README.md): bright hero band →
ink, else by register (cream / editorial / keynote / documentary / loud). Recommend, let the user pick. - Author
<project>/cinematic.json—"dna": "<name>"+ thought-blocks (schema:scripts/make-cinematic.cjsheader) node scripts/make-cinematic.cjs <project>→ plan.json → engine-compiled index.htmlnode scripts/preview-frames.cjs <project>→ § Visual QA (failure checks + the 5 positive checks in ../../references/reference-bar.md)bash scripts/render-and-composite.sh <project>→ gates → final.mp4
What the engine generates (never author these)
- word timings from the transcript; accumulate-within-block / page-flip-between-blocks
- the hero hand-off + three-act orchestration (dim → RMS-coupled per-letter entrance
→ breathe + glow), per the DNA's
heroblock - scene tokens:
--accent(sampled), contact shadow, depth blur - reading order, re-slot from measured heights, hero size/collision post-pass
What you DON'T do
- Override
.capcolor / blend / shadow / filter / motion curves — that's the DNA. Scene fights the look → pick a different DNA (bright →ink), never recolor. - Hand-position the hero into a clean margin (it belongs ON the subject, ~30–55%
occluded — safe-zones
heroBands.best). - Add full-frame grades/textures over the footage (hard rule: the video ships untouched).
Adding a DNA
dna/<name>.json — copy one, change the voice (see ../../dna/README.md
§ Adding). The engine consumes it with no code change. A DNA must be a distinct voice
with a reason to exist, not a recolor.