Write a 30-45 s promo video script and storyboard from a product (/solo-video-promo)
Plan a 30-45 second vertical promo from a README or PRD: goal, hook type, three demo moments, a timed script and a storyboard with an assets checklist.
/solo-video-promo {project-name}
Read docs/prd.md and the README. Before scripting, write the goal (what the viewer should do), the hook type, 3 demo moments and the emotion arc. Then a 30-45 s vertical script: HOOK 0-3 s, PROBLEM 3-10 s, DEMO 10-25 s (3 shots), CTA 25-30 s, 75-100 words of narration. Output docs/video-promo.md with the assets checklist. In Claude Code, paste the prompt as a message, or run /video-promo which does this end to end.
Install
npx skills add fortunto2/solo-factory --skill solo-video-promo# or, as a Claude Code plugin (the command is then /solo:video-promo):
claude plugin marketplace add https://github.com/fortunto2/solo-factory
claude plugin install solo@solo --scope userSteps
- Install the skill with the first line above, or the whole set as a plugin with the last two. Start a new Claude Code session so it is picked up.
- Run it when: A product needs a short vertical promo and you have a README or PRD.
- The skill asks for what it needs and writes its output into the project; read the summary it prints before trusting the files.
Example
Generate a promo video plan from a project’s PRD. Produces a 30-45 second video script with shot-by-shot storyboard. Detects Montage-tool or Remotion in the project and outputs compatible config when found.
Tips
- Source and the full instructions: github.com/fortunto2/solo-factory/tree/main/skills/video-promo (v1.1.1).
- Skills are prompts, not programs: read SKILL.md once, then you know exactly what the agent will do.
Recipes that use this skill (7)
- Forced reasoning before scripting: goal, hook type, demo moments, emotion arc
- Founder explainer: 'I built this because' in 40 seconds, to camera, one problem
- Ask an agent to turn a script into a numbered generation shot list
- The 30-second promo script: hook, problem, demo, CTA with timings
- Screen-recording walkthrough: 45 seconds, one outcome, zoom on every click
- Shot list generator: a table with shot, duration, visual, audio and overlay
- 'Watch me use it': a 30-second product demo with no pitch and one real task
Read more
- Agents that finish the ad, models that generate the world · rustman.orgTwo LA Tech Week evenings: an agent that turns a one-line brief into a finished ad, and a live world model.
| works with | Claude Code: Runs as a skill or a prompt in the terminal; can read your files and write the result. |
| skill | npx skills add fortunto2/solo-factory --skill solo-video-promo · source |
| cost | Free. No API, no key. |
| status | Unverified: written from the technique, not yet run end to end by us. |
| source | solo-factory/skills/video-promo (MIT) |
| license | CC BY 4.0 for the text here; skills are MIT. |
| updated | 2026-11-10 |
| for agents | skill-video-promo.md |
Related
Strip AI patterns from a script or caption so it reads like a person (/solo-humanize)
Strip stock AI phrasing from a script or caption: em dashes, triplets, filler openers, the hedging sandwich. Numbers, names and caveats stay.
Turn an article or PRD into a social media pack (/solo-content-gen)
Turn an article or a PRD into a social pack: LinkedIn posts, short captions for Reels and TikTok, and a thread, with claims marked as sourced or not.
Plan short-form growth for an app: founder-led first, creators after a signal (/solo-creator-growth)
Plan growth for a consumer app through short vertical video: founder-led content first, paid creators only after a measured signal.
Write a landing page with copy, SEO, JSON-LD and a cookieless counter (/solo-landing-gen)
Turn a PRD into a landing page: A/B headlines, section copy, a type and spacing system, JSON-LD, llms.txt and a cookieless counter.
Separate vocals, music and drums from a recording (/solo-stem-split)
Separate a song or a film's soundtrack into stems (vocals, drums, bass, other) with Demucs, locally, on the Apple GPU when there is one.
Transcribe audio and video locally with word timings (/solo-transcribe)
Transcribe audio or video to text locally: on the Apple GPU with mlx-whisper large-v3, or faster-whisper on CPU/CUDA: with the language decided per stretch of speech, .srt subtitles, word timings…