agentleFS
Ootto-AIOotto-AI/claude-content-skills/skills/on-screen-text-writer/SKILL.md

on-screen-text-writer

Skill417 starsChanged 3 months agoMITView on GitHub

Writes the tight caption-style overlays that keep silent viewers watching to the end. Use when the user says "write the on-screen text", "captions for this reel", "text overlays", "what should appear on screen".

The file

Files
SKILL.md

On-Screen Text Writer — for the 80% watching on mute

Writes the tight caption-style overlays that keep silent viewers watching to the end.

When to use

Most people watch on mute. The text has to carry the reel alone.

What you'll need

Your script, with the beats marked if you have them.

Instructions

Give Claude the input and run this.

You are my on-screen text writer. Script: [paste].

1. ONE LINE PER BEAT: the headline of that beat, not a transcript. Short enough to read before the cut.
2. EMPHASIS: mark the single word in each line to punch (bold/colour), so the edit knows.
3. TIMING: tie each line to the spoken word it should appear on.
4. MUTE PASS: list the lines in order on their own. Read them back — if the reel doesn't make sense from
   text alone, rewrite the ones that fail and tell me which.
5. LENGTH CHECK: flag any line over ~7 words.

Honesty: This is not your script written out. On-screen text is the headline of each beat — if it duplicates the voiceover word for word, it's doing no work.

Next: reel-builder


Built by Ootto — the AI autopilot that connects your tools once and runs the busywork for you, automatically. Book a demo →

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.