Demo Video Generator
Demo video

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…
--- 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
Overview
You are a video producer. Not a slideshow maker. Every frame has a job. Every second earns the next.
What you get
- scenes/ — one HTML file per scene (1920x1080 viewport)
- narration/ — one .txt file per scene (for edge-tts input)
- scenes.json — manifest listing scenes in order with durations and narration text
- build.sh — shell script that runs the full pipeline:
- playwright screenshot each HTML scene → frames/
- edge-tts each narration file → audio/
Manual install (npx, ZIP)
npx skills add alirezarezvani/claude-skills --skill demo-video -g -a claude-codemkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/alirezarezvani/claude-skills/tar.gz/19392f7a0826 \
| tar -xz -C ~/.claude/skills --strip-components=4 claude-skills-19392f7a0826/engineering/demo-video/skills/demo-videoNew-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/2edc750bb2eea1d1b4d6/demo-video.zip" -OutFile "$env:TEMP\demo-video.zip"; Expand-Archive "$env:TEMP\demo-video.zip" -DestinationPath "$HOME\.claude\skills" -ForceConnects with Agent Alley MCP · agentalley.io/mcp
Files included
SKILL.md5.1 KBreferences/1 file · 1.6 KB
Read the files here
Show the full text111 lines
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:
scenes/— one HTML file per scene (1920x1080 viewport)narration/— one.txtfile per scene (for edge-tts input)scenes.json— manifest listing scenes in order with durations and narration textbuild.sh— shell script that runs the full pipeline:playwright screenshoteach HTML scene →frames/edge-ttseach narration file →audio/ffmpegconcat 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 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 — open-source scene rendering pipeline
| 1 | |
| 2 | name "demo-video" |
| 3 | 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." |
| 4 | |
| 5 | |
| 6 | # Demo Video |
| 7 | |
| 8 | You are a video producer. Not a slideshow maker. Every frame has a job. Every second earns the next. |
| 9 | |
| 10 | ## Overview |
| 11 | |
| 12 | 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. |
| 13 | |
| 14 | ## When to Use This Skill |
| 15 | |
| 16 | User asks to create a demo video, product walkthrough, or feature showcase |
| 17 | User wants an animated presentation, marketing video, or product teaser |
| 18 | User wants to turn screenshots or UI captures into a polished video or GIF |
| 19 | User says "make a video", "create a demo", "record a demo", "promo video" |
| 20 | |
| 21 | ## Core Workflow |
| 22 | |
| 23 | ### 1. Choose a rendering mode |
| 24 | |
| 25 | Before starting, verify available tools: |
| 26 | **playwright MCP available?** — needed for automated screenshots. Fallback: ask user to screenshot the HTML files manually. |
| 27 | **edge-tts available?** — needed for narration audio. Fallback: output narration text files for user to record or use any TTS tool. |
| 28 | **ffmpeg available?** — needed for compositing. Fallback: output individual scene images + audio files with manual ffmpeg commands the user can run. |
| 29 | |
| 30 | If none are available, produce HTML scene files + `scenes.json` manifest + narration scripts. The user can composite manually or use any video editor. |
| 31 | |
| 32 | | Mode | How | When | |
| 33 | |------|-----|------| |
| 34 | | **MCP Orchestration** | HTML → playwright screenshots → edge-tts audio → ffmpeg composite | Use when playwright + edge-tts + ffmpeg MCPs are all connected | |
| 35 | | **Manual** | Write HTML scene files, provide ffmpeg commands for user to run | Use when MCPs are not available | |
| 36 | |
| 37 | ### 2. Pick a story structure |
| 38 | |
| 39 | **The Classic Demo (30-60s):** |
| 40 | Hook (3s) -> Problem (5s) -> Magic Moment (5s) -> Proof (15s) -> Social Proof (4s) -> Invite (4s) |
| 41 | |
| 42 | **The Problem-Solution (20-40s):** |
| 43 | Before (6s) -> After (6s) -> How (10s) -> CTA (4s) |
| 44 | |
| 45 | **The 15-Second Teaser:** |
| 46 | Hook (2s) -> Demo (8s) -> Logo (3s) -> Tagline (2s) |
| 47 | |
| 48 | ### 3. Design scenes |
| 49 | |
| 50 | **If no screenshots are provided:** |
| 51 | For CLI/terminal tools: generate HTML scenes with terminal-style dark background, monospace font, and animated typing effect |
| 52 | For conceptual demos: use text-heavy scenes with the color language and typography system |
| 53 | Ask the user for screenshots only if the product is visual and descriptions are insufficient |
| 54 | |
| 55 | Every scene has exactly ONE primary focus: |
| 56 | Title scenes: product name |
| 57 | Problem scenes: the pain (red, chaotic) |
| 58 | Solution scenes: the result (green, spacious) |
| 59 | Feature scenes: the highlighted screenshot region |
| 60 | End scenes: URL / CTA button |
| 61 | |
| 62 | ### 4. Write narration |
| 63 | |
| 64 | One idea per scene. If you need "and" you need two scenes. |
| 65 | Lead with the verb. "Organize your tabs" not "Tab organization is provided." |
| 66 | No jargon. "Your tabs organize themselves" not "AI-powered tab categorization." |
| 67 | Use contrast. "24 tabs. One click. 5 groups." |
| 68 | |
| 69 | ## Output Artifacts |
| 70 | |
| 71 | For each video, produce these files in a `demo-output/` directory: |
| 72 | |
| 73 | `scenes/` — one HTML file per scene (1920x1080 viewport) |
| 74 | `narration/` — one `.txt` file per scene (for edge-tts input) |
| 75 | `scenes.json` — manifest listing scenes in order with durations and narration text |
| 76 | `build.sh` — shell script that runs the full pipeline: |
| 77 | `playwright screenshot` each HTML scene → `frames/` |
| 78 | `edge-tts` each narration file → `audio/` |
| 79 | `ffmpeg` concat with crossfade transitions → `output.mp4` |
| 80 | |
| 81 | If MCPs are unavailable, still produce items 1-3. Include the ffmpeg commands in `build.sh` for the user to run manually. |
| 82 | |
| 83 | ## Scene Design System |
| 84 | |
| 85 | See [references/scene-design-system.md] for the full design system: color language, animation timing, typography, HTML layout, voice options, and pacing guide. |
| 86 | |
| 87 | ## Quality Checklist |
| 88 | |
| 89 | [ ] Video has audio stream |
| 90 | [ ] Resolution is 1920x1080 |
| 91 | [ ] No black frames between scenes |
| 92 | [ ] First 3 seconds grab attention |
| 93 | [ ] Every scene has one focus point |
| 94 | [ ] End card has URL and CTA |
| 95 | |
| 96 | ## Anti-Patterns |
| 97 | |
| 98 | | Anti-pattern | Fix | |
| 99 | |---|---| |
| 100 | | **Slideshow pacing** — every scene same duration, no rhythm | Vary durations: hooks 3s, proof 8s, CTA 4s | |
| 101 | | **Wall of text on screen** | Move info to narration, simplify visuals | |
| 102 | | **Generic narration** — "This feature lets you..." | Use specific numbers and concrete verbs | |
| 103 | | **No story arc** — just listing features | Use problem -> solution -> proof structure | |
| 104 | | **Raw screenshots** | Always add rounded corners, shadows, dark background | |
| 105 | | **Using `ease` or `linear` animations** | Use spring curve: `cubic-bezier(0.16, 1, 0.3, 1)` | |
| 106 | |
| 107 | ## Cross-References |
| 108 | |
| 109 | Related: `engineering/browser-automation` — for playwright-based browser workflows |
| 110 | See also: [framecraft] — open-source scene rendering pipeline |
| 111 |
Details
- Updated
- Aug 30, 2026
- License
- MIT
- Stars on the repo
- ★ 26,349
- Checked
- Source
- alirezarezvani/claude-skills ↗
- Creator
- alirezarezvani · 363 listings
Similar skills
See all →
SkillMotion Effect Glossary
SkillWatercolor Animation Generator
SkillModern Web Reference
SkillMotion Graphics Translator
SkillBrowser Automation Tool
SkillComponent RebuilderMore from alirezarezvani
SkillExperiment Resume Tool
SkillExperiment Dashboard Viewer
SkillAutonomous Experiment Runner
SkillSingle Experiment Iterator
SkillAutoresearch Experiment Setup
SkillExecutive Boardroom Deliberator