Confirm the route before Step 0. This skill makes a video for a product being marketed / launched / promoted. If it's really a general (non-launch) site → video (site tour / showcase, not selling a product) →

/website-to-video

; a topic / concept with no product →

/faceless-explainer

; a GitHub PR →

/pr-to-video

; an existing video to caption / package →

/embedded-captions

·

/graphic-overlays

. Out of scope (decline, don't fake): live / at-render-time data (every value is baked in at author time), or footage / screenshots / an avatar that doesn't exist yet (HyperFrames can't record or capture). Routed here on a vague "make a video", or unsure product-vs-topic / launch-vs-general-site? Read

/hyperframes-read-first

first.

PROJECT_DIR = videos/<project-name>/

PROJECT_DIR

<SKILL_DIR>/../hyperframes-core/references/subagent-dispatch.md

hyperframes.json

hyperframes capture

capture/extracted/tokens.json

phases/capture/guide.md

design-system/design.html

chunks/

agents/design-system.md

narrator_scripts.json

agents/story-design.md

audio.mjs

audio_meta.json

phases/audio/guide.md

section_plan.md

agents/visual-design.md

prep.mjs

group_spec.json

scripts/prep.mjs

captions.mjs group

html

caption_groups.json

compositions/captions.html

scripts/captions.mjs

compositions/scene_*.html

agents/hyperframes-scene.md

renders/video.mp4

agents/hyperframes-finalize.md

brew install python@3.11 node ffmpeg                   # On Linux, use the apt/dnf equivalent
npx hyperframes doctor                                  # One-time check that Chrome / dependencies are ready

• python@3.11

  — Homebrew Python, not system

  /usr/bin/python3

  (PEP 668 blocks

  pip install

  otherwise); used by the MusicGen fallback

• node >= 18

  +

  ffmpeg

  (

  audio.mjs

  uses

  ffprobe

  )
• Chrome downloads automatically on first

  npx hyperframes capture

  .

  hoist-videos.mjs

  (Step 7, runs only when a scene declares footage) reuses that cached Chrome; if it reports deps missing, run

  node <SKILL_DIR>/scripts/hoist-videos.mjs --ensure-deps

  once (~5s)

GEMINI_API_KEY

GOOGLE_API_KEY

HEYGEN_API_KEY

hyperframes auth login

--voice

ELEVENLABS_API_KEY

pip install elevenlabs

21m00Tcm4TlvDq8ikWAM

am_michael

--voice

GEMINI_API_KEY

PROJECT_DIR = videos/<project-name>/

<project-name>

<brand>-promo

capture/

$PROJECT_DIR/hyperframes.json

PROJECT_DIR="${LAUNCH_VIDEO_DIR:-videos/<project-name>}"
mkdir -p "$(dirname "$PROJECT_DIR")"
npx hyperframes init "$PROJECT_DIR" --non-interactive --skip-skills --example=blank

hyperframes init

drops a generic

AGENTS.md

/

CLAUDE.md

into

$PROJECT_DIR

; leave them in place but do not treat their generic guidance as run-time constraints — this skill is the source of truth.

• Do not run

  hyperframes init

  (or generate

  AGENTS.md

  /

  CLAUDE.md

  ) in the workspace root; do not create a

  hyperframes/

  subproject inside

  PROJECT_DIR

  .
• Every subagent dispatch context contains a

  PROJECT_DIR: <path>

  line; the subagent treats it as the project root.
• cwd discipline (master too): every Bash command runs as a

  (cd "$PROJECT_DIR" && ...)

  subshell — never bare

  cd "$PROJECT_DIR" && ...

  (persistent cwd drift makes later relative paths wrong).

$PROJECT_DIR/.env

context.log

$HEYGEN_API_KEY

$HYPERFRAMES_API_KEY

~/.heygen/credentials

Detected: <summary>. Cloud keys are optional — without them, unconfigured providers fall back locally (TTS -> Kokoro unless HeyGen is configured; BGM -> MusicGen). Reply with:

• paste keys -> I will write them to

  $PROJECT_DIR/.env

• "go" -> proceed with what is configured now
• "skip" -> proceed with local fallbacks for anything unconfigured

$PROJECT_DIR/.env

KEY=value

1. Resolve

   SKILL_DIR

   and any explicit

   TARGET_URL

   from the prompt; ensure Step 0 ran.
2. Read

   $PROJECT_DIR/context.log

   if it exists and use the Resume table below to skip completed phases.
3. Classify the input (Step 1.0) to set

   CAPTURE

   and

   VO_MODE

   , then run the matching path. Both paths share the same downstream commands.

TARGET_URL

CAPTURE=yes

$PROJECT_DIR/user_script.txt

VO_MODE

CAPTURE

CAPTURE=no

Should I use your script verbatim as the voice-over, or restructure it into more screen-ready scene narration?

• Verbatim — keep the original wording; I only split scenes and pair visuals. Duration follows the script.
• Restructure — treat it as a brief and rewrite tighter narration, 1-2 sentences per scene.

VO_MODE = verbatim | restructure

restructure

http(s)://

CAPTURE=yes

WebSearch

CAPTURE=no

CAPTURE=no

Capture + user script coexist: the crawl supplies only brand tokens + assets + visual register; the narration spine stays

user_script.txt

(honored via

VO_MODE

), never the site's own copy.

CAPTURE=yes

(cd "$PROJECT_DIR" && npx hyperframes capture "<TARGET_URL>" -o ./capture)

CAPTURE=no

visible-text.txt

colors:[]

colors

(cd "$PROJECT_DIR" && mkdir -p capture/extracted capture/assets)
(cd "$PROJECT_DIR" && cat > capture/extracted/tokens.json <<'JSON'
{ "title": "<brand/title>", "description": "<one-line>", "colors": [], "fonts": [], "headings": [], "sections": [], "ctas": [], "svgs": [], "cssVariables": {} }
JSON
)
(cd "$PROJECT_DIR" && echo '{}' > capture/extracted/design-styles.json)
(cd "$PROJECT_DIR" && printf '%s\n' "<full user script / brief>" > capture/extracted/visible-text.txt)

If the user already has a final

narrator_scripts.json

, place it in

$PROJECT_DIR/

; the Resume table skips story-design.

--style <chosen-preset>

(cd "$PROJECT_DIR" && node <SKILL_DIR>/scripts/derive-context-pack.mjs --capture ./capture)
(cd "$PROJECT_DIR" && node <SKILL_DIR>/phases/design-system/scripts/build-design.mjs ./design-system --no-emit)   # Path B: append --style <chosen-preset>

capture/BLOCKED.md

[ -s "$PROJECT_DIR/capture/extracted/tokens.json" ] && \
[ -s "$PROJECT_DIR/capture/extracted/design-styles.json" ] && \
[ -s "$PROJECT_DIR/capture/context_pack.md" ] && \
[ -s "$PROJECT_DIR/design-system/inference.json" ] && \
[ -d "$PROJECT_DIR/capture/assets" ] && echo ok || echo missing

• design-system: prompt = full

  agents/design-system.md

  +

  ## Dispatch context

  with

  SKILL_DIR

  /

  PROJECT_DIR

  /

  Target URL

  + the full text of

  design-system/inference.json

  inlined via

  cat

  (~2-4 KB, saves the subagent one Read).
• story-design: prompt = full

  agents/story-design.md

  +

  ## Dispatch context

  :

  SKILL_DIR: <absolute path>
  PROJECT_DIR: <video project root>
  Schema validator: <SKILL_DIR>/scripts/validate-narrator.mjs
  Design DNA: ./design-system/inference.json   # read site_dna once to set the narrative register
  Provided script: ./user_script.txt   # ONLY when the user supplied a script; omit the line otherwise
  Voice-over mode: <verbatim | restructure>   # pair with Provided script; omit otherwise
  Script style: Keep each scene's script concise - 1-2 sentences, no more than 20 words   # suspended in verbatim mode (length follows the script)
  Orientation: <landscape | portrait | square>   # from the user's aspect (16:9→landscape, 9:16→portrait, 1:1→square; default landscape). Echoed verbatim into narrator_scripts.orientation → sets the canvas for the whole pipeline

narrator_scripts.json

(cd "$PROJECT_DIR" && node <SKILL_DIR>/scripts/audio.mjs \
  --narrator-scripts ./narrator_scripts.json \
  --hyperframes . \
  --out ./audio_meta.json \
  --lyria-recipe <SKILL_DIR>/phases/audio/lyria-recipe.py)

$GOOGLE_API_KEY

transformers torch soundfile numpy

--voice

--provider

--no-bgm

audio.mjs

• exit 0 -> voice + transcribe complete (BGM may still be running;

  audio_meta.json

  records

  bgm_log

  /

  bgm_pid

  ), continue.
• exit 1 -> zero scenes produced voice; report and stop.

Section order is deliberate: contracts first, static references middle, work items last

section_plan.md

(cd "$PROJECT_DIR" && node <SKILL_DIR>/scripts/prep.mjs \
  --section-plan ./section_plan.md \
  --narrator-scripts ./narrator_scripts.json \
  $( [ -f audio_meta.json ] && echo "--audio-meta ./audio_meta.json" ) \
  --rules-dir <SKILL_DIR>/../hyperframes-animation/rules \
  --capture ./capture \
  --design-system ./design-system \
  --hyperframes . \
  --sfx-lib <SKILL_DIR>/assets/sfx \
  --out ./group_spec.json)

• exit 0 -> append the stdout summary to

  $PROJECT_DIR/context.log

  .
• exit 1 -> stderr names the failing scene + anchor; re-dispatch visual-design (Step 4) with the error passed through.

Each worker's prompt = full `agents/hyperframes-scene.md` + `## Dispatch context` with: `SKILL_DIR` / `PROJECT_DIR` / `Worker ID` / `Composition width` + `Composition height` (= `group_spec.width`/`height`) / `Captions: <enabled|disabled>` / `Dispatch packet: <PROJECT_DIR>/.dispatch/scene-dispatch/w<N>.txt`, plus the shared header body (`## Film direction` + `## Tokens / easings / voice`) and the worker's `Scenes:` list **copied verbatim from `group_spec.json.groups[i].scenes[<sid>]`** (`scene_id` / `effects` / `rule_paths` / `assetCandidates` / `estimatedDuration_s` / `voicePath` / `blueprint` / `design_chunks` / `creative_brief`). **When `Captions: enabled`, also pass `Caption band top y` = `height − round(height × 0.1667)` and `Foreground max y` = `Caption band top y − 20`** (landscape → 900 / 880; portrait → 1600 / 1580). `design_chunks: null` (anomaly already reported by prep) -> the worker falls back to reading `design-system/design.html`.

After all workers return, run the static composition gate (scans `compositions/scene_*.html` per `group_spec.scene_ids`; `captions.html` is covered by its own self-lint + Step 7 whole-project lint):

```bash
(cd "$PROJECT_DIR" && node <SKILL_DIR>/scripts/check-compositions.mjs \
  --hyperframes . \
  --group-spec ./group_spec.json)

• 0 -> continue to Step 7.
• 1 -> stderr names the violating scene + rule; re-dispatch that worker (do not Edit in the master).

(cd "$PROJECT_DIR" && node <SKILL_DIR>/scripts/wait-bgm.mjs \
  --audio-meta ./audio_meta.json \
  --hyperframes . \
  --timeout-ms 120000 \
  --interval-ms 2000)
(cd "$PROJECT_DIR" && node <SKILL_DIR>/scripts/assemble-index.mjs --group-spec ./group_spec.json --hyperframes .)
(cd "$PROJECT_DIR" && node <SKILL_DIR>/scripts/transitions.mjs inject --group-spec ./group_spec.json --hyperframes .)
(cd "$PROJECT_DIR" && node <SKILL_DIR>/scripts/transitions.mjs verify --group-spec ./group_spec.json --index ./index.html)
(cd "$PROJECT_DIR" && node <SKILL_DIR>/scripts/hoist-videos.mjs --group-spec ./group_spec.json --hyperframes .)
(cd "$PROJECT_DIR" && node <SKILL_DIR>/scripts/verify-output.mjs sfx --group-spec ./group_spec.json --index ./index.html)

index.html

• assemble exit 1 -> names a scene (root

  data-duration

  ≠ group_spec, or file missing) = worker contract break -> re-dispatch that worker (Step 6), then rerun this step.
• transitions inject/verify exit 1 -> injector bug (prep already validated

  transitions[]

  ) -> report for investigation; do not roll back workers.
• hoist-videos exit 1 -> an invalid

  data-video-src

  declaration (stderr names scene + reason);

  Edit

  the scene file (or re-dispatch for a real relayout), rerun this step. exit 2 -> run

  node <SKILL_DIR>/scripts/hoist-videos.mjs --ensure-deps

  from the workspace root, rerun.
• sfx-verify exit 1 -> assembler bug -> report for investigation.

agents/hyperframes-finalize.md

## Dispatch context

SKILL_DIR: <absolute path>
PROJECT_DIR: <video project root>
Render quality: high     # or draft / standard
Captions: <enabled | disabled>   # = group_spec.captions_enabled
BGM: <one-line wait-bgm verdict, e.g. "ready (lyria)" / "skipped (no key)" / "timeout">
Film direction: |        # = group_spec.film_direction (film-level invariants the briefs assume)
  <verbatim>
Scenes:                  # one line per scene, copied verbatim from group_spec.json
  - { scene_id, start_s, estimatedDuration_s, effects: [...], creative_brief: |
      <Phase 3 prose for this scene> }

• Reports the verified mp4 + fixes in place -> complete.
• STOP (a scene needs real recomposition — exception, not default) -> re-dispatch that worker (Step 6) with normal dispatch context + a

  ## Repair context

  block carrying finalize's verbatim findings and the

  Captions:

  flag -> rerun (1) -> re-dispatch finalize. Same finding survives two rounds -> stop and surface to the user.