@autoaiai/aicut 0.1.11 → 0.1.13

package/skills/remotion-ads/SKILL.md

@@ -1,278 +0,0 @@
----
-name: remotion-ads
-description: "Professional video ad creation with AICUT — Instagram Reels (9:16), website explainers (16:9), and carousels (4:5). Use when creating video ads, animated social content, or educational explainer videos. Includes ElevenLabs voiceover with word-level captions, AI icon generation, background music, ad copywriting frameworks, and Meta campaign management. Also use when the user provides a URL and wants to create a video for that page. Runs in AICUT: the film is film.html, a page per shot, drawn by `aicut look` and `aicut render`."
-license: MIT
-source: "Maartenlouis/remotion-ads"
----
-
-# AICUT Ads
-
-## Running it in AICUT
-
-AICUT's film is `film.html`: it cuts pages, footage, pictures and sound together on tracks. A page is a web page that
-sets `window.film = { frame(t) }` and draws that moment — no framework, no build step, no composition object, no
-`registerRoot`. Five shots are five pages cut together, not one page that changes scene, so each shot stays trimmable
-and replaceable in Studio.
-
-```sh
-npx -y @autoaiai/aicut@latest          # the manual: the format and the commands, always current
-npx -y @autoaiai/aicut@latest open .   # make this folder a film and print Studio's address
-npx -y @autoaiai/aicut@latest look     # a contact sheet of the whole film, its sound, and a determinism check
-npx -y @autoaiai/aicut@latest look 4.5 # one frame, full size — look at the PNG, not at the code
-npx -y @autoaiai/aicut@latest render   # the MP4, beside film.html
-```
-
-Run the manual before the first film: it is authoritative for the format, and this skill is about the method above it.
-
-Where the words below name another program's part, it becomes this:
-
-| elsewhere | in AICUT |
-|---|---|
-| composition, timeline, project file | `film.html`; tracks and clips inside it |
-| a scene, a sequence, a slide | a page (`pages/<name>.html`) cut onto a track |
-| `useCurrentFrame()`, `interpolate()` | `frame(t)` — the picture depends only on `t`, never on state or `Date.now()` |
-| a still, a screengrab | `aicut look <t>` |
-| `render` / `build` / `export` | `aicut render` (the person can also export from Studio) |
-| a dev server, a preview window | `aicut open` and the Studio address it prints |
-
-Hard rules that hold whatever the method says: the picture depends only on `t`; every value in the person's prompt is
-binding; look at the frames `look` writes before saying a film is done.
-
-
-Create professional video ads and explainer videos with Remotion, ElevenLabs voiceover, and animated captions.
-
-## Setup
-
-1. Copy `references/brand-config-template.md` → `references/brand-config.md`
-2. Fill in brand colors, fonts, voice, caption styling, and content rules
-3. Create pronunciation dictionary from `assets/dictionaries/template.pls`
-
-See [references/setup.md`setup.md` for dependencies and folder structure.
-
----
-
-## Supported Formats
-
-| Format | Aspect | Resolution | Duration | Scenes |
-|--------|--------|-----------|----------|--------|
-| Instagram Reels | 9:16 | 1080×1920 | 15-60s | 4 (Hook→Problem→Solution→CTA) |
-| Instagram Reels (Ohneis) | 9:16 | 1080×1920 | 15-45s | Beat-driven (word-level) |
-| Website Explainers | 16:9 | 1920×1080 | 60-160s | 6 (Hook→Problem→Context→Solution→Process→CTA) |
-| Carousels | 4:5 | 1080×1350 | Static | 5-10 slides |
-
-See [references/formats.md](references/formats.md) for safe zones and crop specs.
-See [references/ohneis-style.md`ohneis-style.md` for beat-driven cinematic reel template.
-See [references/website-videos.md`website-videos.md` for 16:9 long-form format.
-
----
-
-## Workflow
-
-### From scratch
-
-# 1. Write scene JSON
-
-# 2. Generate voiceover with word timestamps
-node scripts/generate.js \
-  --scenes scenes.json \
-  --with-timestamps \
-  --dictionary your-brand \
-  --output-dir public/audio/ad-example/
-
-# 3. Create Remotion composition using actualDuration from info.json
-
-# 4. Render
-npx remotion render AdExample out/ad-example.mp4 --codec=h264 --crf=18
-
-### From a URL (page → video)
-
-# 1. Extract page data into scene JSON
-node scripts/url-to-scenes.js --url https://example.com/page --format reels --output scenes.json
-
-# 2. Review/edit the generated scenes.json
-
-# 3. Continue with voiceover + composition as above
-```
-See [references/url-to-video.md`url-to-video.md` for the full URL-to-video workflow.
-
----
-```
-
-## Safe Zones (Critical)
-
-### Reels (1080×1920)
-
-```
-┌──────────────────────────┐ 0px
-│     TOP DANGER (285px)   │
-├──────────────────────────┤
-│ ←80px  SAFE AREA  120px→ │
-│      880×1235px          │
-├──────────────────────────┤
-│   BOTTOM DANGER (400px)  │
-└──────────────────────────┘ 1920px
-```
-```tsx
-const SAFE = { top: 285, bottom: 400, left: 80, right: 120 };
-
-### Website Videos (1920×1080)
-
-```tsx
-const SAFE = { top: 60, bottom: 60, left: 80, right: 80 };
-```
----
-```
-
-## Scene JSON Format
-
-```json
-{
-  "name": "ad-example",
-  "voice": "VoiceName",
-  "character": "narrator",
-  "dictionary": "your-brand",
-  "scenes": [
-    { "id": "scene1", "text": "Hook text.", "duration": 3.5, "character": "dramatic" },
-    { "id": "scene2", "text": "Problem.", "duration": 4.5 },
-    { "id": "scene3", "text": "Solution.", "duration": 4.0, "character": "expert" },
-    { "id": "scene4", "text": "CTA.", "duration": 3.0, "character": "calm" }
-  ]
-}
-
-### Voice Character Presets
-
-| Character | Style | Stability | Similarity | Style Param |
-|-----------|-------|-----------|------------|-------------|
-| `dramatic` | Intense, emotional | 0.3 | 0.8 | 0.7 |
-| `narrator` | Professional, smooth | 0.5 | 0.75 | 0.4 |
-| `expert` | Authoritative | 0.6 | 0.85 | 0.3 |
-| `calm` | Soothing, reassuring | 0.7 | 0.8 | 0.2 |
-| `conversational` | Casual, friendly | 0.45 | 0.7 | 0.5 |
-
----
-
-## Composition Template
-
-```tsx
-import { AbsoluteFill, Audio, Series, staticFile } from "remotion";
-
-// Import from your brand-config.md values
-const COLORS = { primary: "#000", accent: "#888", dark: "#111", background: "#fff" };
-
-export const AdTemplate: React.FC = () => {
-  const { fps } = useVideoConfig();
-  // Use actualDuration from info.json, not estimated
-  const DURATIONS = { scene1: 3.42, scene2: 4.35, scene3: 4.12, scene4: 3.31 };
-  const pad = 5;
-
-  return (
-    <AbsoluteFill>
-      <Audio src={staticFile("audio/ad-example/ad-example-combined.mp3")} />
-      <Series>
-        <Series.Sequence durationInFrames={Math.round(DURATIONS.scene1 * fps) + pad}>
-          <Scene1Hook />
-        </Series.Sequence>
-        {/* ... remaining scenes */}
-      </Series>
-    </AbsoluteFill>
-  );
-};
-```
-See [references/components.md](references/components.md) for reusable scene components.
-See [references/voiceover.md`voiceover.md` for TransitionSeries audio sync.
-
----
-```
-
-## Reference Files
-
-Load these on demand based on the task:
-
-### Core (read first)
-
-| File | When to read |
-|------|-------------|
-| [setup.md`setup.md` | Project initialization |
-| [brand-config-template.md](references/brand-config-template.md) | Configuring brand: colors, fonts, voice, captions, compliance |
-| [formats.md](references/formats.md) | Dimension specs, safe zones, crop previews |
-
-### Video Creation
-
-| File | When to read |
-|------|-------------|
-| [ohneis-style.md`ohneis-style.md` | Beat-driven cinematic reel template: mixed-font typography, hard cuts, moody photos |
-| [voiceover.md`voiceover.md` | ElevenLabs TTS, models, scene JSON, timing sync, dictionaries |
-| [captions.md](references/captions.md) | Animated captions: TikTok-style, word-by-word, karaoke |
-| [animations.md](references/animations.md) | Spring configs, transitions, animation components |
-| [components.md](references/components.md) | Reusable scene template components |
-| [html-in-canvas.md](references/html-in-canvas.md) | Render live DOM into a canvas with 2D filters or WebGL2 shaders (vintage, progressive blur, page-tour mockup) |
-| [website-videos.md`website-videos.md` | 16:9 long-form format, 6-scene structure |
-| [url-to-video.md`url-to-video.md` | Create videos from existing web pages |
-
-### Audio
-
-| File | When to read |
-|------|-------------|
-| [sound-effects.md`sound-effects.md` | ElevenLabs SFX generation |
-| [music.md](references/music.md) | Background music via ElevenLabs or Suno |
-
-### Assets & Static
-
-| File | When to read |
-|------|-------------|
-| [local-assets.md](references/local-assets.md) | Background images, icons, illustrations |
-| [carousels.md](references/carousels.md) | 4:5 carousel design and batch rendering |
-
-### Copywriting
-
-| File | When to read |
-|------|-------------|
-| [ad-copywriting.md](references/ad-copywriting.md) | Script frameworks, hook formulas, CTA patterns |
-| [copy-frameworks.md](references/copy-frameworks.md) | Headline templates, section formulas |
-| [natural-transitions.md`natural-transitions.md` | Human-sounding transitions, AI-tell avoidance |
-
-### Distribution
-
-| File | When to read |
-|------|-------------|
-| [paid-ads.md`paid-ads.md` | Meta campaign strategy, targeting, budgets |
-| [social-content.md`social-content.md` | Content calendar, repurposing framework |
-
----
-
-## Scripts
-
-| Script | Purpose |
-|--------|---------|
-| `scripts/generate.js` | ElevenLabs voiceover with dictionaries, request stitching (note: `--with-timestamps` flag is currently a no-op) |
-| `scripts/gemini-tts.mjs` | Gemini TTS — single-request generate + silence split with text-proportion boundary picker |
-| `scripts/suno-direct.ts` | Suno background music generation |
-| `scripts/url-to-scenes.js` | Extract page content into scene JSON |
-
----
-
-## Pre-Upload Checklist
-
-### Reels
-- [ ] 1080×1920, H.264, 30fps
-- [ ] All text within safe zones
-- [ ] No content in top 285px or bottom 400px
-- [ ] Font sizes ≥ 48px
-- [ ] Voiceover synced, captions timed
-- [ ] ~15s total duration
-
-### Website Videos
-- [ ] 1920×1080, H.264, 30fps
-- [ ] Font sizes ≥ 36px
-- [ ] 60-160s duration
-- [ ] 6-scene structure with appropriate voice characters
-
-### Carousels
-- [ ] 1080×1350, PNG
-- [ ] 80px padding from edges
-- [ ] 5-10 slides with swipe indicators
-
-## Source
-
-Rewritten for AICUT from [`Maartenlouis/remotion-ads`](https://github.com/Maartenlouis/remotion-ads)
-(MIT), SKILL.md. The method is that skill's own; the way it runs is AICUT's.

package/skills/remotion-ads/references/ad-copywriting.md

@@ -1,229 +0,0 @@
----
-title: Ad Copywriting
-description: Frameworks and formulas for writing video ad scripts, carousel copy, and social captions
-section: copywriting
-priority: medium
-tags: [copywriting, scripts, hooks, cta, headlines, captions, marketing]
----
-
-# Ad Copywriting for Video & Carousel Ads
-
-Frameworks for writing compelling ad scripts, carousel slide copy, and social media captions for Instagram Reels and static ads created with Remotion.
-
-> "If you have to choose between clear and creative, choose clear."
-
----
-
-## Before Writing
-
-Gather this context (ask if not provided):
-
-1. **Product/Service**: What does it do? What problem does it solve?
-2. **Target Audience**: Who are they? What pain points do they have?
-3. **Differentiator**: What makes this different from competitors?
-4. **Desired Action**: What should viewers do after watching? (Visit link, DM, book a call)
-5. **Platform**: Instagram Reels, Stories, Feed, or carousel?
-
----
-
-## Video Ad Script Structure (4 Scenes)
-
-### Scene 1: Hook (2-4 seconds)
-
-The first 1-2 seconds determine if someone watches or scrolls. Use these formulas:
-
-**Curiosity Hooks**
-- "I was wrong about [common belief]."
-- "The real reason [outcome] happens isn't what you think."
-- "[Impressive result] — and it only took [surprisingly short time]."
-
-**Problem Hooks**
-- "Never [unpleasant event] again."
-- "[Question highlighting the main pain point]?"
-- "Stop [pain]. Start [pleasure]."
-
-**Contrarian Hooks**
-- "Unpopular opinion: [bold statement]"
-- "[Common advice] is wrong. Here's why."
-- "I stopped [common practice] and [positive result]."
-
-**Audience Hooks**
-- "[Key feature] for [target audience]."
-- "You don't have to [skill/resource] to [achieve outcome]."
-
-### Scene 2: Problem (3-5 seconds)
-
-Articulate the viewer's problem better than they can. Create recognition.
-
-**Openers:**
-- "You know the feeling..."
-- "If you're like most [role]..."
-- "Every day, [audience] struggles with..."
-
-**Structure:**
-1. The specific frustration
-2. The time/money/stress wasted
-3. The impact on their life
-
-### Scene 3: Solution (3-5 seconds)
-
-Bridge from problem to your solution):
-
-**Structure:**
-1. Outcome headline (what they get)
-2. How it works (1-2 sentences)
-3. Proof point (number, testimonial, or example)
-
-### Scene 4: CTA (2-4 seconds)
-
-Specific > generic. Never use "Learn more" or "Click here."
-
-**Strong CTAs:**
-- "Book your free consultation"
-- "Get your custom quote"
-- "Send us a message"
-- "Link in Bio for [specific thing]"
-
----
-
-## Headline Formulas
-
-### Outcome-Focused
-- `{Achieve outcome} without {pain point}`
-- `{Achieve outcome} by {how product makes it possible}`
-- `Turn {input} into {outcome}`
-- `[Achieve outcome] in [timeframe]`
-
-### Problem-Focused
-- `Never {unpleasant event} again`
-- `{Question highlighting the main pain point}?`
-- `Stop [pain]. Start [pleasure].`
-
-### Differentiation-Focused
-- `The {opposite of usual process} way to {achieve outcome}`
-- `The [category] that [key differentiator]`
-- `Finally, [category] that [benefit]`
-
-### Proof-Focused
-- `[Number] [people] use [product] to [outcome]`
-- `{Key benefit of your product}`
-
----
-
-## Carousel Slide Copy (5 Slides)
-
-### Slide 1: Hook
-- Bold headline using a formula above
-- Subtext that creates curiosity
-- "Swipe to learn more" or arrow indicator
-
-### Slides 2-4: Content
-- One key point per slide
-- Headline + 2-3 bullet points maximum
-- Use icons instead of plain bullets
-- Benefits, not features
-
-### Slide 5: CTA
-- Recap core value proposition
-- Clear call to action
-- Brand logo and contact info
-- Trust signals (ratings, credentials)
-
-### Carousel Copy Rules
-
-1. **Front-load value**: First slide must earn the swipe
-2. **One idea per slide**: Don't cram multiple concepts
-3. **Progressive disclosure**: Each slide builds on the last
-4. **Visual hierarchy**: Headline > bullets > fine print
-5. **End with action**: Last slide must tell them what to do next
-
----
-
-## Social Caption Copy
-
-### Caption Structure
-
-```
-[Hook - first line before "more" truncation]
-
-[Body - 2-3 short paragraphs]
-
-[CTA - what to do next]
-
-[Hashtags - 5-10 relevant]
-```
-
-### Caption Hooks (First Line)
-
-- Direct question: "Dealing with [problem] right now?"
-- Bold statement: "[Number]% of [audience] don't know this."
-- Story opener: "Last week, a client came to us with..."
-- Value promise: "[Number] things you should know about [topic]:"
-
-### Caption Length by Platform
-
-| Platform | Optimal Length | Notes |
-|----------|---------------|-------|
-| Instagram Reels | 50-100 chars | Short, let video do the talking |
-| Instagram Feed | 150-300 chars | Hook + key info + CTA |
-| Instagram Carousel | 200-400 chars | Summary + CTA |
-
----
-
-## Writing Principles
-
-### Do
-- Use the audience's own language
-- Lead with benefits, not features
-- Be specific: "32% more conversions" beats "more conversions"
-- Use active voice: "We fix your problem" not "Your problem is fixed by us"
-- Write at a 6th-grade reading level
-- Front-load key messages (viewers may scroll away)
-
-### Don't
-- Use jargon the audience doesn't use
-- Make vague promises: "the best" or "world-class"
-- Write walls of text (especially on video)
-- Use more than one CTA per piece
-- Start with your brand name (earn attention first)
-
----
-
-## Transitions to Avoid (AI Tells)
-
-These phrases signal AI-generated content and should be avoided:
-
-- "That being said,..."
-- "It's worth noting that..."
-- "At its core,..."
-- "In today's digital landscape,..."
-- "When it comes to the realm of..."
-- "This begs the question..."
-- "Let's delve into..."
-
-Use natural alternatives:
-- "However,..." / "But,..."
-- "What matters most is..."
-- "Here's the thing:"
-- "So what does this mean?"
-
----
-
-## Script Review Checklist
-
-- [ ] Hook grabs attention in first 1-2 seconds
-- [ ] Problem is specific and relatable
-- [ ] Solution is clear and credible
-- [ ] CTA tells viewer exactly what to do
-- [ ] No jargon the audience wouldn't use
-- [ ] Each scene is 2-5 seconds (fits 15s total)
-- [ ] Copy matches the voiceover character preset
-- [ ] No AI-sounding phrases or filler
-
----
-
-## Related Rules
-
-- [voiceover.md](../voiceover.md) - Match script to voice character presets
-- [captions.md](../captions.md) - Animated captions for the script
-- [carousels.md](../carousels.md) - Carousel slide layout specs