Text Over Footage logo

Text Over Footage

Community
alisadiq-ai
text-over-footage

Style for edit-video: one short, readable line of text over B-roll that matches it, for jokes, observations and setup/payoff reels. Use for POV and relatable text reels, recreations of a text-over-video format, or when there is no talking head.

Overview

Publisheralisadiq-ai
Repositoryfavstash-ai-video-editing-skills
Skill nametext-over-footage
Stars
56
Forks
8
Bundled files
1
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by alisadiq-ai on GitHub. Read the source before you install it.

Installation

Install the Text Over Footage AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/alisadiq-ai/favstash-ai-video-editing-skills/tree/main/skills/3-editing-styles/text-over-footage
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/alisadiq-ai/favstash-ai-video-editing-skills.git /tmp/favstash-ai-video-editing-skills
mkdir -p .claude/skills
cp -r /tmp/favstash-ai-video-editing-skills/skills/3-editing-styles/text-over-footage .claude/skills/text-over-footage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Text Over Footage in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Text Over Footage on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Text Over Footage is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Text over footage

A style on top of edit-video. The text carries the idea; the footage supplies the personality, the situation or the payoff. Prefer one clean full-screen shot and one readable text block, visible from the first frame.

Copy

  • One premise, meaningful line breaks and a short payoff. Borrow the mechanism of a proven format (a relatable setup, a quick reversal, contrast between text and footage), then write a line that's true for this creator.
  • When recreating a reference, read its overlay from the actual frames. A saved post's caption field often holds a different line from the one on screen.
  • No unrequested CTA, explanatory paragraph or slogan.

Footage

  • The creator's own footage by default, matched to the joke's situation, not just "person at a desk": a date joke at a café, a late-night grind at a dark desk, a long day as a night-to-day timelapse.
  • Avoid a stretch where they're visibly talking to someone unless the line is about talking. Slow, idle typing doesn't read as busy.
  • Use another creator's clip only for a shot the creator explicitly names. Then soften its burned-in text, punch in about 10% and change the grade.
  • A clip that has already been posted needs a punch-in and a new grade, or the platform's duplicate check may hold the reel (see publish-and-analyze).

Type (tested defaults)

SettingValue
FontOne bold geometric sans, for example Sora Bold (OFL), white
EdgeNo outline; a soft drop shadow (black, about 70% opacity, small blur, slight y offset)
SizeAbout 42px glyph height at 1080 wide, so a 32-character line spans about 700px
WrappingThe fewest lines that fit about 700px, balanced, no single-word last line
PositionCentered, upper third by default (block center around y .23). Move it where the face or the joke needs space
Long copySame style, smaller

Contrast comes from choosing clear space and from the shadow, not from a stroke. Keep the whole block inside edit-video's safe area.

Timing and sound

Static text visible from the opening is the default; use a second reveal only when it improves the joke or matches a visible action. Hold it long enough to read twice at phone size: about 6–10 seconds for short copy. Longer copy needs more time or fewer words, not smaller type.

A trending or original sound often carries this format. Use audio the creator may reuse; a sound being available in the app doesn't make the file reusable elsewhere. Static text changes don't each need a sound effect.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Text Over Footage AI skill do?

Style for edit-video: one short, readable line of text over B-roll that matches it, for jokes, observations and setup/payoff reels. Use for POV and relatable text reels, recreations of a text-over-video format, or when there is no talking head.

Why use Text Over Footage on TypingMind?

Because you install it once and use it with any model. Text Over Footage is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Text Over Footage in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alisadiq-ai/favstash-ai-video-editing-skills/tree/main/skills/3-editing-styles/text-over-footage. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Text Over Footage?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Text Over Footage?

As many as you like. As long as a model supports skills, you can use Text Over Footage with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Text Over Footage AI skill free?

Yes. It is published on GitHub by alisadiq-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇