captions
Skill4 starsChanged 9 days agoMITView on GitHub
Captions — Reel-style captions, active word on a colour pill. Renders a video with the rudywizz-motion engine. Use when the user asks for this look by name.
- Installs packages
11 other projects use a version of this.
Adopted by
Most recently taken up by
- Vibha-Ramprakash/claude-caption-stylestheir own version, first seen Nov 15, 2026
- zuckenbert/video-from-codetheir own version, first seen Nov 8, 2026
- Littlpinguin/marketing-cockpit-templatetheir own version, first seen Nov 3, 2026
- skulitom/Cutbolttheir own version, first seen Nov 1, 2026
- TakeOff-Team/claude-shortform-video-editortheir own version, first seen Oct 25, 2026
- appariciojunior/video-editor-skillstheir own version, first seen Oct 25, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- ZeroPointRepo/youtube-skills★ 972same name
- artemchuikin/youtube-skills★ 273same name
- appariciojunior/video-editor-skills★ 246same name
- TakeOff-Team/claude-shortform-video-editor★ 11same name
- Vibha-Ramprakash/claude-caption-styles★ 11same name
- Littlpinguin/marketing-cockpit-template★ 9same name
- skulitom/Cutbolt★ 1same name
- vidmoat/skills★ 1same name
- bloxy-studios/shorts-studio★ 0same name
- Gopyr/gopyr-skills-hub★ 0same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository43 other files it gives its agents.
- bar-chartSkill
- beat-cutSkill
- card-carouselSkill
- chat-storySkill
- countdownSkill
- cta-followSkill
- cube-spinSkill
- doodle-storySkill
- editorialSkill
- extrude-3dSkill
- glitch-titleSkill
- halftone-pressSkill
- highlight-quoteSkill
- history-titleSkill
- history-videoSkill
- inflateSkill
- ink-bleedSkill
- led-marqueeSkill
- lower-thirdSkill
- lyric-videoSkill
- map-routeSkill
- murmurationSkill
- neon-signSkill
- odometerSkill
- orbit-ringSkill
- parchment-letterSkill
- particle-sphereSkill
- pixel-questSkill
- presenterSkill
- receiptSkill
- reelSkill
- retro-gridSkill
- roomSkill
- rudywizz-motionSkill
- scrambleSkill
- signal-tuneSkill
- split-flapSkill
- story-3dSkill
- text-tunnelSkill
- ticker-rowsSkill
- typewriterSkill
- vhs-memorySkill
- word-stackSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
Read $RM/SKILL.md once for setup, the workflow (check stills → render → verify) and the full catalogue.
- Very specific: line 20
Put the user's text in single quotes (write '\'' for an apostrophe inside it) so the shell never interprets it.
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Captions
Reel-style captions, active word on a colour pill.
Find the engine (the sibling rudywizz-motion skill folder) and a temp folder both bash and Node agree on:
RM="${CLAUDE_SKILL_DIR}/../rudywizz-motion"
[ -f "$RM/engine/cli.mjs" ] || RM=$(ls -dt "${CLAUDE_PLUGIN_ROOT}/skills/rudywizz-motion" ~/.claude/plugins/cache/*/rudywizz-motion/*/skills/rudywizz-motion ~/.claude/skills/rudywizz-motion .claude/skills/rudywizz-motion 2>/dev/null | head -1)
TMP=$(node -p "require('os').tmpdir()")
(cd "$RM" && node -e "require.resolve('playwright')" 2>/dev/null) || (cd "$RM" && npm install --no-audit --no-fund) # first run onlyRead $RM/SKILL.md once for setup, the workflow (check stills → render → verify) and the full catalogue.
Put the user's text in single quotes (write '\'' for an apostrophe inside it) so the shell never interprets it.
Render (the user's text — $ARGUMENTS — goes in --text; default "Bu altyazılar tamamen kodla üretildi ve şeffaf arka planla dışa aktarılabilir"):
node "$RM/engine/cli.mjs" still captions --text '<text>' --at 4 --size 540 --out "$TMP/captions-check.png" # look at it first
node "$RM/engine/cli.mjs" render captions --text '<text>' --out captions.mp4Options (--set key=value, JSON values allowed):
maxWords— Words per caption chunk (1–4)position— Vertical position, 0 = top, 1 = bottompill— Highlight colour behind the active wordtimes— Optional array of start seconds per word (from your transcript)
Combine freely with --camera, --grade, --bloom, --leak, --film, --format 1:1|4:5|16:9, --audio, --alpha --out x.mov.
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.

