words-from-behind
Skill0 starsChanged 21 days agoMITView on GitHub
Video effect - a title (e.g. "Directed by Claude Code") rises from behind a laptop lid, steps forward in front of it, then sinks back behind. Use when the user types /words-from-behind or wants text emerging from behind an object in their footage.
In this repository8 other files it gives its agents.
- icon-on-palmSkill
- orbitSkill
- paperSkill
- share-commentSkill
- thanos-snapSkill
- visuals-coreSkill
- zig-zag-graphSkill
- zoomingSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Ask for the two lines (top small line, big line).
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/words-from-behind
Two lines of title text start hidden behind the laptop lid, rise up over it with a little overshoot, step forward (they grow and pass in front of the lid with a soft shadow), hold, then sink back down behind the lid. ~3.1 s.
Needs: a locked-off clip with the lid visible against the wall. Requires visuals-core next to this folder.
Steps
- Ask for the two lines (top small line, big line). Default: "Directed by" / "Claude Code".
- Make or check the mask:
python ../visuals-core/mask.py --in clip.mp4 --t <hand-free time> --out laptop_mask.png. - Preview and render:
python words_from_behind.py --in clip.mp4 --start 74.8 --dur 3.1 --out preview --preview 0.06,0.5,1.2,2.95 \ --line1 "Directed by" --line2 "Claude Code" --mask laptop_mask.png python words_from_behind.py --in clip.mp4 --start 74.8 --dur 3.1 --out words.mp4 --line1 ... --line2 ... --mask laptop_mask.png
Flags
| flag | default | meaning |
--line1, --line2 | "Directed by", "Claude Code" | small top line ('' to skip) and big line |
--color1, --color2, --shadow | ink, orange, ink | text colours (big line has a stacked shadow) |
--size2 | 122 | big line size in px at 1080 wide |
--font | bold system font | any TTF/OTF |
--peak, --forward | 185 / 290 px above the lid top | y positions of the rise and the step forward |
--back-at | dur - 0.68 | when it starts sinking back |
Check before delivering
- At 0.06 s and at the very end only the top of the text peeks over the lid. The lid must cut it cleanly.
- The big line fits inside the frame width; shorten it or lower
--size2.
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
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.

