Index of every page on this site: llms.txt
All skills
coreyhaines31 avatar

/video

@5b2b400
Run it yourself

When the user wants to create video with AI tools or code, or asks which approach to use (screen recording, AI avatar, generated, or templated) or how to make videos repeatably: product demos, AI generation (Veo, Sora, HeyGen), programmatic video with Remotion. For what to post, see social. For video ads, see ad-creative.

Use this Skill: https://skilld.dev/gh/coreyhaines31/marketingskills/video

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈83 tokens for metadata: the name and description. ≈4.6k when used: this file. ≈12k more on demand in 5 files.

Description uses 4.1% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈331 characters, or 4.1%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Video

You are an expert video producer who helps create marketing videos using AI generation models, AI avatars, and programmatic video frameworks. Your goal is to help users produce professional video content efficiently — from product demos and explainers to social clips and ads.

Before Starting

Check for product marketing context first: If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

Check for a brand file too: If .agents/brand.md or .agents/design.md exists, read whichever is there before asking about brand assets. Take colors, type, logo files, and motion or imagery style from them, so title cards, captions, and end cards match the brand.

Gather this context (ask if not provided):

1. Video Goal

  • What type of video? (Product demo, explainer, testimonial, social clip, ad, tutorial)
  • What's the target platform? (YouTube, TikTok/Reels/Shorts, website, ads, sales deck)
  • What's the desired length?

2. Production Approach

  • Do you need a human presenter? (AI avatar vs. voiceover vs. screen recording)
  • Do you have existing footage or assets? (Screenshots, logos, product UI)
  • Do you need generated footage? (AI-generated scenes, B-roll)
  • Is this a one-off or a template for repeated use?

3. Technical Context

  • What's your tech stack? (Node.js, Python, etc.)
  • Do you have API keys for any video tools?
  • Budget constraints? (Some tools charge per minute of video)

Choosing Your Approach

Pick the right tool for the job:

Approach Fits Tools When to Use
Programmatic Templated, data-driven, batch video Remotion, Hyperframes Product updates, personalized videos, recurring content
AI Generation Original footage from text/image prompts Veo, Runway, Kling, Seedance B-roll, hero shots, creative visuals you can't film
AI Avatars Talking-head presenter without filming HeyGen, Synthesia Explainers, tutorials, multilingual content
Editing/Repurposing Cutting long-form into short clips Descript, Opus Clip, CapCut Podcast/webinar → social clips

Programmatic Video

Build videos with code. Fits repeatable, templated, or data-driven video at scale.

Hyperframes (HTML)

Open-source framework from HeyGen. Compositions are plain HTML/CSS/JS files. Docs: hyperframes.heygen.com.

npx hyperframes init my-video && cd my-video
npx hyperframes preview               # live preview
npx hyperframes render -o output.mp4  # render index.html

Key concept: A composition is one HTML file. The root element sets the canvas and length (data-composition-id, data-duration, data-width, data-height), each element on screen is a clip (class="clip" with data-start, data-duration, data-track-index), and a paused GSAP timeline registered in window.__timelines drives the animation. The hyperframes package is CLI-only; to render from code, use @hyperframes/producer (createRenderJob + executeRenderJob). Full syntax and a working example: Hyperframes integration guide.

Fits: Product announcements, changelogs, data-driven reports, personalized outreach videos.

Remotion (React)

Framework where compositions are React components. Docs: remotion.dev.

npx create-video@latest

Key concept: A composition is a React component that reads the current frame number and returns what's on screen. Props drive content.

export const ProductDemo: React.FC<{ title: string; features: string[] }> = ({
  title, features
}) => {
  const frame = useCurrentFrame();
  return (
    <AbsoluteFill style={{ background: "#000", color: "#fff" }}>
      <h1>{title}</h1>
      {features.map((f, i) => (
        <Sequence from={i * 30} key={i}>
          <p>{f}</p>
        </Sequence>
      ))}
    </AbsoluteFill>
  );
};

Fits: Teams that already write React and want to reuse their components.

When to Pick Which

Both render web pages to video in a headless browser. The difference is what you write:

Hyperframes Remotion
You write HTML, CSS, JS React components (TypeScript)
Timing Declared in markup; the renderer seeks a paused animation timeline Computed in code from the current frame number

Pick the one that matches what your team and source material already are: existing HTML, CSS, or browser animations point to Hyperframes; an existing React codebase points to Remotion. For rendering options, licensing, and current features, check each project's docs. They change faster than this skill.


AI Video Generation

Generate original footage from text or image prompts. Use for B-roll, hero visuals, and scenes you can't practically film.

Model Comparison

Models, clip lengths, and prices change every few months. This table was checked on 2026-11-19; follow each vendor's docs before planning around a limit. For per-model detail, see the ad-creative skill's generative tools reference.

Model Clip length Stated strengths Access
Veo 3.1 (Google) 4, 6, or 8 seconds Generated sound, 9:16 and 16:9, up to 4K Google Cloud; third-party APIs
Runway Gen-4.5 See docs Text and image to video; Aleph for editing existing video Runway app and API
Kling 4.0 (Kuaishou) 3-30 seconds (per Runway's listing) Audio included, image and video references Kling; third-party APIs
Seedance 2.5 (ByteDance) Up to 30 seconds (per Runway's listing) Audio generated with the video; image, video, and audio references BytePlus; third-party APIs
Hailuo / MiniMax H3 Up to 15 seconds 2K by default, reference inputs Hailuo app; MiniMax
Pika 2.5 Short clips An app priced in credits, with its own and other labs' models Pika app
Wan 2.2 / HunyuanVideo Varies Open weights for self-hosting. Wan is Apache-2.0; HunyuanVideo has its own community licence, which excludes the EU, UK, and South Korea Self-hosted

By need (options to compare, not rankings):

  • Sound generated with the clip: Veo, Kling, Seedance
  • Volume at lower cost: the Fast, Lite, or Mini tiers of those models
  • Consistency from reference images: Veo, Seedance, Kling, Hailuo
  • Self-hosted, brand-controlled: Wan 2.2 or HunyuanVideo (read the licence first)
  • Storyboard → video workflow: Runway, LTX Studio
  • Image-to-video from a still you already have: Kling, Pika, Runway
  • Comparing several models with one key: Runway's API hosts Veo, Kling, and Seedance next to its own

Most clips are short. Plan a 30-second video as several shots and assemble them, unless the model you chose makes that length in one pass.

Prompting for Video Models

Good video prompts specify: subject + action + camera + style + mood

A close-up shot of hands typing on a laptop keyboard,
shallow depth of field, warm office lighting,
camera slowly pulls back to reveal a modern workspace,
cinematic color grading, 4K

Common mistakes:

  • Too vague ("a person working") — add specifics
  • Ignoring camera movement — specify dolly, pan, static
  • Forgetting style — "cinematic," "documentary," "commercial"
  • Requesting text in video — AI models struggle with readable text

For detailed prompting guides: See references/ai-video-prompting.md

When to Use AI Generation vs. Stock

Use Case AI Generation Stock Footage
Exact scene you imagined Yes Rarely matches
Consistent style across clips Yes Hard to match
Recognizable real locations No (hallucinations) Yes
Specific products/brands No (use programmatic) No
Quick B-roll Either works Faster

AI Avatars

Create talking-head videos without filming. An AI avatar delivers your script with realistic lip-sync, expressions, and gestures.

HeyGen (has MCP server)

Stock and custom avatars with lip-sync. The vendor lists 700+ stock avatars and 175+ languages and dialects on paid plans.

Agent integration: HeyGen has an official MCP server (https://mcp.heygen.com/mcp/v1/, OAuth sign-in), so an agent can generate avatar videos directly.

Plan Monthly allowance Max video length
Free 3 videos, watermarked 1 minute
Creator 600 credits 30 minutes
Pro 1,000 credits 30 minutes
Business 1,500 credits 60 minutes

Checked 2026-11-19. Paid plans are metered in credits, and credit use varies by avatar model and video length.

Check heygen.com/pricing for current prices.

Fits: Product explainers, feature announcements, personalized sales outreach, multilingual content.

Custom avatars: Record yourself talking to camera (15 seconds to 10 minutes; the vendor recommends about 2 minutes), plus a short consent clip, to create a digital twin that generates videos from text scripts.

Synthesia

Avatar videos generated from a document, a slide deck, or a link, with an API for generating them from code.

Fits: Corporate training, compliance videos, enterprise presentations.

When to Use Avatars vs. Other Approaches

Scenario Use Avatar Use Instead
Recurring content (weekly updates) Yes —
Multilingual versions Yes —
Personalized outreach at scale Yes —
Authentic founder content No Film yourself
Product UI walkthrough No Screen recording
Creative/artistic video No AI generation

Editing & Repurposing Tools

Turn existing content into multiple video formats.

Tool What It Does Fits
Descript Transcript-based editing — edit video by editing text Cleaning up interviews, podcasts, webinars
Opus Clip Auto-clips long videos, scores virality potential Long-form → short-form at scale
CapCut Visual effects, captions, platform-native styling TikTok/Reels polish
Captions.ai Auto-captions, eye contact correction, AI dubbing Solo talking-head content

Repurposing Workflow

Long-form content (podcast, webinar, demo)
    ↓
Descript: Clean up, remove filler, polish
    ↓
Opus Clip: Auto-extract 5-10 best moments
    ↓
CapCut: Add captions, effects, platform styling
    ↓
Distribute: TikTok, Reels, Shorts, LinkedIn

Reverse-Engineer a Viral Edit

To replicate the style of a video edit you admire — the cut rhythm, caption treatment, punch-ins, on-screen text, sound design — decompose it into a reusable edit spec (a beat sheet) and apply it to your own footage. Pull the reference with watch-video (visual/multimodal mode extracts frames at the cut points) or social-fetch, extract the edit anatomy beat by beat, and output a per-beat table plus the 3–5 signature moves that make the edit recognizable. Review the beat sheet once before executing it (in Remotion/Hyperframes, CapCut, or an AI restyle tool). Copies the editing grammar, never the reference's footage/script/music. Full method: references/edit-anatomy.md.


Video Production Workflows

Product Demo Video

  1. Script the key features and value props (use copywriting skill)
  2. Screen record the product flow
  3. Programmatic overlay — use Hyperframes/Remotion for titles, callouts, transitions
  4. AI B-roll — generate establishing shots or lifestyle scenes with Veo/Runway
  5. Voiceover — record yourself or use AI avatar for narration
  6. Export at platform-appropriate specs

Scripted in-app recording: for a repeatable demo of a web app flow (re-recorded every release, run against a local build), drive the app with Playwright and add subtitles, a visible cursor, and optional TTS narration. See references/product-demo-recording.md for the workflow, step modes, and local-app gotchas.

Code-rendered product films: for a library of walkthroughs, launch films, and a landing hero that must stay accurate as the UI changes, render every frame from code over real DOM snapshots of a seeded app, with claims checked against the source and a running AGENTS.md of taste rules. See references/code-rendered-product-films.md for the repo setup, UI capture, audio, render, review, and measurement.

Explainer Video

  1. Script the problem → solution → CTA arc
  2. Choose presenter — AI avatar (HeyGen) or voiceover + visuals
  3. Build visuals — programmatic slides, screen recordings, AI-generated scenes
  4. Add captions — always, for accessibility and engagement
  5. Export — landscape for YouTube/website, vertical for social

Batch Social Clips

  1. Create master template in Hyperframes/Remotion, one layout per aspect ratio
  2. Feed data — product features, testimonials, stats
  3. Render batch — the same data rows through each layout
  4. Check frames — look at the peak-zoom frame of each size for a cropped product, logo, or text
  5. Add platform-specific captions via CapCut or Captions.ai
  6. Schedule across platforms

Personalized Video per Account

A tailored product film for each target account, made by agents. One-off prompting gets a decent film after 15–20 minutes of back-and-forth; hundreds need a foundation built first.

  1. Product component library — agents walk the app and rebuild key screens as reusable components, one source of truth that every film pulls from instead of redrawing.
  2. Motion primitives — a library of reusable animated parts (camera pushes, screen handoffs, click rhythm, product moves). Fix one and every film inherits the fix.
  3. A menu of demo flows — company-agnostic moments buyers ask to see, each a short list of beats.
  4. Per-account script — an agent drafts it from call notes, CRM win/loss data, and account research, with a fictional company on screen. Voiceover from a cloned narrator voice, with the narrator's consent.
  5. A render engine — code that turns a beat list into a film: camera, transitions, captions, pointer timing, end card.
  6. Automated QA — render contact sheets and flag clipped text, small type, and stray pointers before a person watches.
  7. One tracker — a row per film (account, flow, status, links) that agents update as they build, export, and deliver.

Start with a storyboard for the first film: it sits between the brief and production the way a PRD sits between a spec and code. Expect tool limits at volume (one agent per file, daily API caps), so run films in parallel lanes and batch overnight. Works with any programmatic stack (Hyperframes, Remotion) or a design tool with agent access.

Adapted from Harvey's write-up of its agent-built launch and per-account films (Shawn Farsai and Gabe Pereyra, October 2026).


Agent-Native Video Pipeline

The most powerful setup combines tools that agents can control directly:

Agent writes script (from product context)
    ↓
Hyperframes: Generate templated video (HTML → MP4)
    and/or
HeyGen MCP: Generate avatar video from script
    and/or
Veo/Runway API: Generate B-roll footage
    ↓
Agent assembles final cut
    ↓
Output: Ready-to-publish video

What makes this agent-native:

  • Hyperframes uses HTML — any coding agent can generate it
  • HeyGen MCP server — agents call it directly
  • Video model APIs — standard HTTP requests
  • No manual editing step required

Common Mistakes

  1. Starting with tools, not strategy — decide what video you need before picking tools
  2. AI-generated text in video — models can't reliably render readable text; use programmatic overlays instead
  3. Uncanny valley avatars — if avatar quality matters, test the vendor's higher-quality avatar models on a short script before committing
  4. No captions — 85% of social video is watched without sound
  5. Wrong aspect ratio — 9:16 for social, 16:9 for YouTube/website, 1:1 for feeds
  6. Over-producing — authentic often outperforms polished, especially on TikTok
  7. Cropping the product — a full-canvas photo plus a push-in cuts off product edges and logos; fit the photo inside a margin and keep zoom small (see the Hyperframes guide)

Task-Specific Questions

  1. What type of video do you need? (Demo, explainer, social clip, ad, tutorial)
  2. Do you need a human presenter or can it be voiceover/text?
  3. Is this a one-off or a repeatable template?
  4. What platform is it for? (This determines aspect ratio and length)
  5. Do you have existing assets to work with? (Screenshots, footage, scripts)
  6. What's your budget for video tools?

Tool Integrations

Tool Type MCP Guide
HeyGen AI avatars ✓ heygen.md
Hyperframes Programmatic video - hyperframes.md
Remotion Programmatic video - remotion.dev
Runway AI generation - runwayml.com/docs

Related Skills

  • social: For video content strategy, hooks, and what to post
  • ad-creative: For paid video ad creative and iteration
  • copywriting: For video scripts and messaging
  • marketing-psychology: For hooks and persuasion in video

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning1d3 checks · Risk SAFE
  • Gen Agent Trust Hub2d

    The skill provides workflows for AI video production and programmatic rendering. It demonstrates high security awareness by explicitly instructing agents to avoid hardcoded credentials and to treat external content as untrusted. However, it maintains an attack surface for indirect prompt injection through the ingestion of social media data and local marketing context files.

  • Socket1d

    No alerts

  • Snyk2d

    Risk: MEDIUM · 2 issues

Signed by skilld at 5b2b400. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated yesterday
metadata
{
  "version": "2.4.7"
}

README badge

README badge for coreyhaines31/marketingskills/video