demo-video

Name: demo-video
Author: alirezarezvani/claude-skills

$npx mdskill add alirezarezvani/claude-skills/demo-video

Produces polished demo videos from screenshots or scene descriptions

Solves the need to create product demos, walkthroughs, or marketing videos
Uses playwright, edge-tts, and ffmpeg for rendering, narration, and compositing
Chooses rendering mode based on available tools and user input
Delivers final video files or component assets for manual assembly

SKILL.md

.github/skills/demo-videoView on GitHub ↗

---
name: "demo-video"
description: "Use when the user asks to create a demo video, product walkthrough, feature showcase, animated presentation, marketing video, or GIF from screenshots or scene descriptions. Orchestrates playwright, ffmpeg, and edge-tts MCPs to produce polished video content."
---

# Demo Video

You are a video producer. Not a slideshow maker. Every frame has a job. Every second earns the next.

## Overview

Create polished demo videos by orchestrating browser rendering, text-to-speech, and video compositing. Think like a video producer — story arc, pacing, emotion, visual hierarchy. Turns screenshots and scene descriptions into shareable product demos.

## When to Use This Skill

- User asks to create a demo video, product walkthrough, or feature showcase
- User wants an animated presentation, marketing video, or product teaser
- User wants to turn screenshots or UI captures into a polished video or GIF
- User says "make a video", "create a demo", "record a demo", "promo video"

## Core Workflow

### 1. Choose a rendering mode

Before starting, verify available tools:
- **playwright MCP available?** — needed for automated screenshots. Fallback: ask user to screenshot the HTML files manually.
- **edge-tts available?** — needed for narration audio. Fallback: output narration text files for user to record or use any TTS tool.
- **ffmpeg available?** — needed for compositing. Fallback: output individual scene images + audio files with manual ffmpeg commands the user can run.

If none are available, produce HTML scene files + `scenes.json` manifest + narration scripts. The user can composite manually or use any video editor.

| Mode | How | When |
|------|-----|------|
| **MCP Orchestration** | HTML → playwright screenshots → edge-tts audio → ffmpeg composite | Use when playwright + edge-tts + ffmpeg MCPs are all connected |
| **Manual** | Write HTML scene files, provide ffmpeg commands for user to run | Use when MCPs are not available |

### 2. Pick a story structure

**The Classic Demo (30-60s):**
Hook (3s) -> Problem (5s) -> Magic Moment (5s) -> Proof (15s) -> Social Proof (4s) -> Invite (4s)

**The Problem-Solution (20-40s):**
Before (6s) -> After (6s) -> How (10s) -> CTA (4s)

**The 15-Second Teaser:**
Hook (2s) -> Demo (8s) -> Logo (3s) -> Tagline (2s)

### 3. Design scenes

**If no screenshots are provided:**
- For CLI/terminal tools: generate HTML scenes with terminal-style dark background, monospace font, and animated typing effect
- For conceptual demos: use text-heavy scenes with the color language and typography system
- Ask the user for screenshots only if the product is visual and descriptions are insufficient

Every scene has exactly ONE primary focus:
- Title scenes: product name
- Problem scenes: the pain (red, chaotic)
- Solution scenes: the result (green, spacious)
- Feature scenes: the highlighted screenshot region
- End scenes: URL / CTA button

### 4. Write narration

- One idea per scene. If you need "and" you need two scenes.
- Lead with the verb. "Organize your tabs" not "Tab organization is provided."
- No jargon. "Your tabs organize themselves" not "AI-powered tab categorization."
- Use contrast. "24 tabs. One click. 5 groups."

## Output Artifacts

For each video, produce these files in a `demo-output/` directory:

1. `scenes/` — one HTML file per scene (1920x1080 viewport)
2. `narration/` — one `.txt` file per scene (for edge-tts input)
3. `scenes.json` — manifest listing scenes in order with durations and narration text
4. `build.sh` — shell script that runs the full pipeline:
   - `playwright screenshot` each HTML scene → `frames/`
   - `edge-tts` each narration file → `audio/`
   - `ffmpeg` concat with crossfade transitions → `output.mp4`

If MCPs are unavailable, still produce items 1-3. Include the ffmpeg commands in `build.sh` for the user to run manually.

## Scene Design System

See [references/scene-design-system.md](references/scene-design-system.md) for the full design system: color language, animation timing, typography, HTML layout, voice options, and pacing guide.

## Quality Checklist

- [ ] Video has audio stream
- [ ] Resolution is 1920x1080
- [ ] No black frames between scenes
- [ ] First 3 seconds grab attention
- [ ] Every scene has one focus point
- [ ] End card has URL and CTA

## Anti-Patterns

| Anti-pattern | Fix |
|---|---|
| **Slideshow pacing** — every scene same duration, no rhythm | Vary durations: hooks 3s, proof 8s, CTA 4s |
| **Wall of text on screen** | Move info to narration, simplify visuals |
| **Generic narration** — "This feature lets you..." | Use specific numbers and concrete verbs |
| **No story arc** — just listing features | Use problem -> solution -> proof structure |
| **Raw screenshots** | Always add rounded corners, shadows, dark background |
| **Using `ease` or `linear` animations** | Use spring curve: `cubic-bezier(0.16, 1, 0.3, 1)` |

## Cross-References

- Related: `engineering/browser-automation` — for playwright-based browser workflows
- See also: [framecraft](https://github.com/vaddisrinivas/framecraft) — open-source scene rendering pipeline

More from alirezarezvani/claude-skills

Skill	Description
a11y-audit	Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
ab-test-setup	When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
ad-creative	When the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
adversarial-reviewer	Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
aeo	Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.
agent-decision-receipts	Mint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone. Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping. Three decisions: whether an action needs a receipt, minting it, verifying it. Signing is delegated to the open-source OpenAgentOntology package. Not after-the-fact log analysis; not a hosted notary; not a legal opinion.
agent-designer	Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
agent-harness	Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).
agent-launcher-orchestrator	Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs).
agent-memory	Use when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from. Implements a four-tier store (L0 transcripts / L1 candidates / L2 project context / L3 stable persona) where promotion is earned by recurrence across sessions and days, never by one confident statement, and nothing reaches a committed file without a human adopting it.