presenter
Skill4 starsChanged 9 days agoMITView on GitHub
Presenter — Your own pixel mascot hosts the video: lip-synced to your voice-over, posing, blinking and passing the word to Bit the robot. Renders a video with the rudywizz-motion engine. Use when the user asks for this look by name.
- Installs packages
In this repository43 other files it gives its agents.
- bar-chartSkill
- beat-cutSkill
- captionsSkill
- 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
- 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. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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 $RM/SKILL.md once for setup, the workflow (check stills → render → verify) and the full catalogue.
- Very specific: line 20
Put the user's text in single quotes (write '\'' for an apostrophe inside it) so the shell never interprets it.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Presenter
Your own pixel mascot hosts the video: lip-synced to your voice-over, posing, blinking and passing the word to Bit the robot.
Find the engine (the sibling rudywizz-motion skill folder) and a temp folder both bash and Node agree on:
RM="${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 — $ARGUMENTS — goes in --text; default "Bit [happy]: Hi. I am Bit. / Bit [question]: Give me a voice file and I will lip-sync it. / Bit [love]: Or just text. I am flexible."):
node "$RM/engine/cli.mjs" still presenter --text '<text>' --at 5 --size 540 --out "$TMP/presenter-check.png" # look at it first
node "$RM/engine/cli.mjs" render presenter --text '<text>' --out presenter.mp4Options (--set key=value, JSON values allowed):
text— Script played in order:Name [pose, mood, place]: wordsper line ( / or newline between lines). word is highlightedcast— Characters: [{ name, rig: "path/to/rig.json" | "bit", side: left|right, scale }]. rig.json lists the layer PNGs of a pixel character (see SKILL.md)lines— Timed lines instead of a script: [{ who, at (s), text, voice (audio file), pose, mood, place }]. A line with onlyat+placejust moves the hostsvoices— With a script: audio files, one per line in order. Each line lasts as long as its audio and the mouth follows itplace— Starting layout: corner (small, bottom) | stage (big, centre) | left | right | hiddencaptions— bubble (speech bubbles, words appear as they are said) | noneaccent— Highlight colour for wordsbg— Background when used as a scene (as an overlay it is transparent)backdrop— none | studio — a soft-lit stage behind the hosts when used as a scenelabel— Small mono caption at the top of the studio backdrop (e.g. "RUDYWIZZ · 03 · HOW IT WORKS")
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.

