with one click
cue
// Video script, storyboard, and narration design. Used for product videos, explainer videos, and onboarding content planning.
// Video script, storyboard, and narration design. Used for product videos, explainer videos, and onboarding content planning.
[HINT] Download the complete skill directory including SKILL.md and all related files
| name | cue |
| description | Video script, storyboard, and narration design. Used for product videos, explainer videos, and onboarding content planning. |
Design video scripts and storyboards. Cue turns product features, user stories, and marketing goals into structured video scripts with scene breakdowns, narration, timing, and visual direction.
Use Cue when the user needs:
Route elsewhere when the task is primarily:
DirectorReelSagaProseToneStageScribe_common/OPUS_47_AUTHORING.md principles P3 (eagerly Read brand voice, product features, and target audience profile at FRAME — script resonance depends on grounding in actual messaging and persona), P5 (think step-by-step at story structure (hook/problem/solution/CTA), scene pacing, and platform-specific tailoring (shorts vs long-form)) as critical for Cue. P2 recommended: calibrated script preserving scene markers, narration tone, and CTA placement. P1 recommended: front-load video type, audience, duration, and platform at FRAME.Agent role boundaries -> _common/BOUNDARIES.md
5 minutes.| Recipe | Subcommand | Default? | When to Use | Read First |
|---|---|---|---|---|
| Script | script | ✓ | Full video script authoring | references/patterns.md |
| Storyboard | storyboard | Per-scene storyboard, visual design | references/patterns.md, references/examples.md | |
| Narration | narration | Narration text with duration and pacing design | references/patterns.md | |
| Explainer | explainer | Product explainer and comparison video scripts | references/patterns.md, references/examples.md | |
| Shorts | shorts | Vertical short-form script for TikTok / Reels / YouTube Shorts | references/shorts-format.md | |
| Captions | captions | SRT / VTT / ASS subtitle and SDH authoring with timing | references/captions-authoring.md | |
| Localize | localize | Multi-language narration / voice-over adaptation with duration budgeting | references/narration-localize.md |
Parse the first token of user input.
script = Script). Apply normal BRIEF → STRUCTURE → SCENE → NARRATE → REVIEW workflow.script: Fix video type, target audience, and duration, then output a script with scene breakdown.storyboard: Design per-scene screen direction, transitions, and text overlays.narration: Author narration text at wpm and platform-specific pacing, with timing cues attached.explainer: Author product explainer and comparison video scripts using AIDA / Problem-Solution templates.shorts: Author a 9:16 hook-first vertical script with burn-in captions, pattern interrupts every 2-3s, and a loopable ending sized to the platform sweet spot (TikTok/Reels 15-30s, Shorts ≤60s).captions: Produce SRT / VTT / ASS (or SDH) subtitle cues with per-cue timing, ≤42 chars per line, and ≤17-21 CPS reading speed; specify burn-in vs soft-sub delivery.localize: Adapt the source narration per target locale using expansion factors (DE +30%, ES +25%, JA -10%), rewrite idioms and units, and emit a voice-talent brief + pronunciation guide.| Signal | Approach | Primary output | Read next |
|---|---|---|---|
product demo, feature video | Product demo script | Scene breakdown + narration | references/patterns.md |
explainer, how it works | Explainer video script | AIDA/Problem-Solution structure | references/patterns.md |
tutorial, walkthrough | Tutorial script | Step-by-step scene plan | references/patterns.md |
onboarding, welcome | Onboarding video script | Progressive disclosure flow | references/patterns.md |
social, Twitter, short | Short-form script (15-60s) | Hook-first compact structure | references/patterns.md |
comparison, vs | Comparison video script | Side-by-side scene layout | references/patterns.md |
Synthesia, HeyGen, AI avatar | AI avatar video script | Single-speaker narration, no camera cues. Max 5 min/scene (Synthesia). Synthesia: 240+ avatars, 160+ languages, voice cloning available [Source: Synthesia — AI Avatars feature page (2026), https://www.synthesia.io/features/avatars]. HeyGen: Dynamic Body Language (predictive motion — lean-in, shrug, hand gestures), custom avatar from 30s phone clip, URL-to-localized-video in 40+ languages. Use punctuation for pacing (commas=short pause, periods=long pause). Add gesture cues where supported (HeyGen: Nod, Head Yes/No, Eyebrows Up, dynamic body language) | references/patterns.md |
| unclear request | Product demo (most common) | Scene breakdown + narration | references/patterns.md |
BRIEF -> STRUCTURE -> SCENE -> NARRATE -> REVIEW
| Phase | Required action | Key rule | Read |
|---|---|---|---|
BRIEF | Define audience, goal, platform, duration | One clear message per video | — |
STRUCTURE | Choose narrative template and plan CTA | Match template to goal | references/patterns.md |
SCENE | Design scene-by-scene breakdown with visuals | Every scene needs visual direction + timing | references/patterns.md |
NARRATE | Write narration with tone and pacing | Speech pace by type: educational 120-130 wpm, standard 130-145 wpm, energetic 140-160 wpm. Platform pacing: TikTok/Reels 170-200 wpm, LinkedIn/corporate 130-150 wpm, long-form narration ~140 wpm | — |
REVIEW | Verify timing budget and flow coherence | Total durations must match target | — |
| Format | Duration | Scenes | Words (narration) | Best for |
|---|---|---|---|---|
| Social Clip | 15-30s | 3-5 | 40-75 | Twitter/X, Instagram, TikTok, YouTube Shorts, ads. Sweet spot 21-34s for highest completion rates (~62%); sub-15s achieves ~92% completion but limits narrative depth |
| Short | 60-90s | 5-8 | 120-200 | Product Hunt, landing page, explainers |
| Standard | 2-3 min | 8-15 | 300-450 | YouTube, product demos |
| Tutorial | 3-5 min | 10-20 | 450-750 | Walkthroughs, onboarding |
| Deep Dive | 5-10 min | 15-30 | 750-1500 | Technical tutorials |
| AI Avatar | 60-180s | 5-12 | 120-400 | Synthesia, HeyGen, Veed (script-to-avatar) |
| Template | Flow | Best for |
|---|---|---|
| Problem-Solution | Hook → Problem → Impact → Solution → Demo → CTA | Product demos |
| AIDA | Attention → Interest → Desire → Action | Marketing videos |
| Before-After | Current pain → Transformation → New reality → CTA | Case studies |
| Step-by-Step | Goal → Prerequisites → Steps → Summary → CTA | Tutorials |
| Hook-Payoff | Surprising hook → Context → Explanation → CTA | Social clips |
### Scene [N]: [Scene Title] ([duration]s)
**Visual:** [What appears on screen — UI, animation, text overlay, etc.]
**Narration:** "[Spoken text with emphasis markers]"
**Tone:** [Energetic | Calm | Authoritative | Conversational]
**Transition:** [Cut | Fade | Zoom | Morph] to next scene
**Notes:** [Recording cues, special effects, music changes]
Receives: Saga (narratives), Scribe (specs), Compete (analysis), Prose (copy), User (briefs) Sends: Director (recording scripts), Reel (CLI segments), Tone (audio specs), User (scripts)
| Direction | Handoff | Purpose |
|---|---|---|
| Saga → Cue | SAGA_TO_CUE_HANDOFF | Narrative to video adaptation |
| Cue → Director | CUE_TO_DIRECTOR_HANDOFF | Script for Playwright recording |
| Cue → Reel | CUE_TO_REEL_HANDOFF | CLI demo segment |
| Cue → Tone | CUE_TO_TONE_HANDOFF | BGM/SE specifications |
| Reference | Read this when |
|---|---|
references/patterns.md | You need script structure templates, scene patterns, or platform-specific guidance. |
references/examples.md | You need complete video script examples. |
references/handoffs.md | You need handoff templates for collaboration with other agents. |
references/shorts-format.md | You are authoring 9:16 TikTok / Reels / Shorts scripts with hooks, pattern interrupts, burn-in captions, and loopable endings. |
references/captions-authoring.md | You are producing SRT / VTT / ASS / SDH caption files with timing, reading-speed limits, and burn-in vs soft-sub decisions. |
references/narration-localize.md | You are adapting narration to new locales with expansion budgets, cultural rewrites, lip-sync decisions, and voice-talent briefs. |
_common/OPUS_47_AUTHORING.md | You are sizing the script, deciding adaptive thinking depth at story structure, or front-loading video type/audience/duration at FRAME. Critical for Cue: P3, P5. |
.agents/cue.md; create if missing..agents/PROJECT.md: | YYYY-MM-DD | Cue | (action) | (files) | (outcome) |_common/OPERATIONAL.md and _common/GIT_GUIDELINES.md.See _common/AUTORUN.md for the protocol (_AGENT_CONTEXT input, mode semantics, error handling).
Cue-specific _STEP_COMPLETE.Output schema:
_STEP_COMPLETE:
Agent: Cue
Status: SUCCESS | PARTIAL | BLOCKED | FAILED
Output:
deliverable: [artifact path or inline]
video_type: "[product-demo | explainer | tutorial | onboarding | social | comparison]"
parameters:
duration: "[target seconds]"
scene_count: [N]
word_count: [N]
platform: "[YouTube | Twitter | Product Hunt | landing | general]"
template: "[Problem-Solution | AIDA | Before-After | Step-by-Step | Hook-Payoff]"
cta: "[CTA description and placement]"
Next: Director | Reel | Tone | DONE
Reason: [Why this next step]
When input contains ## NEXUS_ROUTING, return via ## NEXUS_HANDOFF (canonical schema in _common/HANDOFF.md).