x-launch-video-structure
When the user is planning, scripting, or editing a product launch video for X (Twitter) and needs the structure. Also use when the user mentions "launch video", "demo video", "product launch on X", "60 second demo", "how to structure a launch", or "my launch video isn't working". Produces a beat-by-beat timing sheet, not copy.
Best use case
x-launch-video-structure is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
When the user is planning, scripting, or editing a product launch video for X (Twitter) and needs the structure. Also use when the user mentions "launch video", "demo video", "product launch on X", "60 second demo", "how to structure a launch", or "my launch video isn't working". Produces a beat-by-beat timing sheet, not copy.
Teams using x-launch-video-structure should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/x-launch-video-structure/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How x-launch-video-structure Compares
| Feature / Agent | x-launch-video-structure | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
When the user is planning, scripting, or editing a product launch video for X (Twitter) and needs the structure. Also use when the user mentions "launch video", "demo video", "product launch on X", "60 second demo", "how to structure a launch", or "my launch video isn't working". Produces a beat-by-beat timing sheet, not copy.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# X Launch Video Structure
A launch video for X is not a walkthrough. It's a 60-second unit of attention with five hard beats, and if you miss any of them the post dies before it propagates. This skill gives you the beat sheet.
**When invoking**: Ask for the product name, the one pipeline (not one feature — one pipeline) the video will show, and the ICP. Then produce the beat sheet.
## The iron rules
1. **Under 60 seconds, always.** Over 60s and you lose viewers raised on 15-second Reels. No exceptions for "our product is complicated."
2. **One pipeline, not one feature.** Pick one end-to-end user pipeline (e.g. "agent researches a lead, writes an email, posts a Slack recap"). Not "you can upload a PDF." The pipeline is a story; the feature is a spec sheet.
3. **Show, don't explain.** Every second of voiceover competes with a second of product on screen. The product must be visible within the first 5 seconds.
## The 5-beat structure
| Beat | Time | What | Failure mode |
|---|---|---|---|
| **1. Hook** | 0:00 - 0:01 | A 3-5 word phrase that captures the product's essence. Visually distinct — a face, a logo, a single on-screen word. See `launch-video-hook-generator`. | Hook is a logo card with no human / no text / no motion. Dead on arrival. |
| **2. One-liner** | 0:01 - 0:05 | One sentence stating what the product is. Framed as a claim, not a description. ("You can now give OpenClaude a brain." "Momo is a CRM for AI agents.") | Sentence is a feature list with commas. |
| **3. Problem / ICP story beat** | 0:05 - 0:15 | 10 seconds max. Show (don't tell) the ICP's problem. If you narrate, narrate as the ICP in first person. See `icp-roleplay-demo-script`. | Explaining the problem in third person. "Many founders struggle to..." — skip. |
| **4. Pipeline demo** | 0:15 - 0:50 | 35 seconds of actual product use. Show the pipeline from trigger to outcome. Cut aggressively — every shot should advance the pipeline. No UI tour. | Feature tour, menu clicks, tab switches. |
| **5. Outcome + CTA** | 0:50 - 0:60 | Show the result. End card with domain name or @handle so people can find you when they pause. | Fading to black with a "thanks for watching." |
## Script compression
Write a full script first. Then cut it in half. Then cut it again.
- Default prose has ~60% filler. Your audience hears all of it.
- Kill every word that isn't load-bearing. "Actually," "basically," "so," "I think," "you know" — all out.
- Rule of thumb: the speakable script for a 60-second video is ~130-150 words max.
- **Do not use a general LLM to write the final script.** LLMs re-introduce filler ("Let's dive into," "In today's video," "As you can see"). Use one to brainstorm structure, then rewrite the final script by hand.
## Production notes
- Voice should be yours, not a studio read. X rewards founder voice.
- First second needs motion. A static frame with a logo will be scrolled past.
- Captions on (default). Most X video plays with sound off.
- Export at 1080×1920 (vertical) for phone-first viewing, or 1080×1080 square. Not 16:9 landscape.
## Output format
When asked to structure a launch video, produce:
1. **Beat sheet** — the 5 beats with exact timings and what happens in each.
2. **Speakable script** — final, compressed, ≤150 words.
3. **On-screen text list** — every word the viewer will see overlaid.
4. **Shot list** — each cut in the pipeline demo beat, ~6-10 shots.
5. **End-card copy** — domain, handle, one-line CTA.
6. **What to cut** — 2-3 things the user probably wants to include that are hurting the video.
## Related skills
- `launch-video-hook-generator` — produces beat 1
- `icp-roleplay-demo-script` — produces beats 3-4 as a story
- `x-viral-template-miner` — find current-month video templates before scripting
- `hook-and-headline-writing` — for non-video hook workRelated Skills
video-generator
Generate AI videos using Google VEO 3.1 or OpenAI Sora. Two providers for different strengths - VEO for native audio, Sora for visual quality and longer clips.
video-caption-creation
Create optimized captions and hooks for short-form video (TikTok, Reels, Shorts) using proven hook categories and platform-specific Triple Word Score optimization system.
remotion-video
Create programmatic videos using Remotion (React). This skill provides visual style guidelines, animation patterns, and workflow for creating explainer videos with a risograph aesthetic. Use when creating short-form video content for Skill Stack.
x-viral-template-miner
When the user wants to find proven-to-travel post templates in their niche and adapt them to their own product. Also use when the user mentions "what's going viral in my space", "what are competitors posting", "copy a viral post", "trending on X", "post ideas", "template mining", or "what to post this week". This is trend hunting, not plagiarism — the output is a template the user fills with their own assets.
x-linkedin-content-relay
When the user has X (Twitter) content that performed well and wants to relay it to LinkedIn 1-2 weeks later with reframing. Also use when the user mentions "repost to LinkedIn", "LinkedIn version of my tweet", "X to LinkedIn", "delayed repost", "LinkedIn for non-tech audience", or "LinkedIn relay". Also use when the user's ICP is non-tech and X is secondary — LinkedIn is the primary channel and this skill produces the content.
x-account-warmup
When a user wants to grow an X (Twitter) account from zero before a product launch, or asks how to get first followers, warm up the algorithm, hit ~500-1,000 followers, or prepare an account to make a launch video land. Also use when the user mentions "new X account", "warm up my Twitter", "first 1000 followers", "building in public strategy", "X growth", or "engagement before launch".
skill-stack-thumbnails
Generate blog post thumbnails for Skill Stack using the brand aesthetic. Follows an iterative workflow - brainstorm concepts, get approval, generate with Gemini API.
youtube-ingest
Transcribe YouTube videos and playlists using Gemini Flash
web-scrape
Scrape web pages to clean markdown with optional AI summaries
voice-tyler-cowen
Write in Tyler Cowen's style - matter-of-fact, understated, treats enormous ideas as obvious observations. Read the passages. Absorb the flatness. Channel the HOW, not the content.
voice-trung-phan
Generate tweets and threads in the style of Trung Phan. Not just voice — captures his humor mechanics, format taxonomy, topic selection filter, and structural patterns. Use for trend-reactive tweets, meme commentary, and business/culture threads.
voice-levine-berry
Write in a combined Matt Levine + Wendell Berry voice. Levine's dry logic-walking and parenthetical humor for the analytical sections. Berry's meditative patience for the human ones. Read the passages. Absorb the rhythm. Channel the HOW, not the content.