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.
How to use it
Claude Code
- Run the line below. It pulls the whole folder into
~/.claude/skills/demo-video, including the files SKILL.md points to. - Describe your job in plain words. Claude Code follows the skill from there.
npx degit alirezarezvani/claude-skills/engineering/demo-video/skills/demo-video#main ~/.claude/skills/demo-videoFor one project only, change the path to .claude/skills/demo-video. This skill also uses scenes.json, build.sh — copying SKILL.md alone won't be enough. See the folder on GitHub.
Claude (web or desktop app)
- On this page open ⋯ → Download .md.
- Save it as SKILL.md in a folder, zip the folder, then Customize → Skills → + → Create skill → Upload a skill.
- Pick the file and Save. Claude shows the name and description and runs a security scan.
- Check the skill is switched on.
- Start a new chat and describe your job in plain words. The AI follows the skill from there.
ChatGPT or another app
- ChatGPT: make a Project and paste it into Instructions.
- Neither? Paste it at the top of a new chat — it works for that chat.
Not working?
- Check which app you pasted it into — the steps above name the right one.
- Some skills need the paid tier of Claude or ChatGPT.
Paste into Claude, ChatGPT or Cursor.
Source of Demo video
Show the full text111 lines
| name | description |
|---|---|
| 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 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:
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 |
Discussion
Browse more free Claude skills.