agentleFS
RudywizzRudywizz/rudywizz-motion/skills/reel/SKILL.md

reel

Skill4 starsChanged 9 days agoMITView on GitHub

Director mode — turn the user's clips, photos, places and lines into a finished vertical reel with camera moves, shader transitions, captions, maps and a colour grade, rendered by rudywizz-motion. Use when the user types /reel or asks to edit/montage a reel or short from their footage.

  • Installs packages

11 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read $RM/SKILL.md once for setup, the workflow (check stills → render → verify) and the full catalogue.

    line 17
  2. Very specific:

    Put the user's text in single quotes (write '\'' for an apostrophe inside it) so the shell never interprets it.

    line 18
  3. Very specific:

    Write reel.json next to the assets (start from node "$RM/engine/cli.mjs" init reel.json.

    line 22
  4. Very specific:

    look: teal-orange (travel), kodak (warm lifestyle), cyber (music), sepia + film (history)

    line 27
  5. Very specific:

    Check stills at the middle of each scene (still reel.json --at <t> --size 540 --out "$TMP/reel-<t>.png") and look at them.

    line 28
  6. Distinctive:

    Verify duration with ffprobe and deliver.

    line 29

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/reel — composition director

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 only

Read $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.

  1. Collect inputs: the user's clips/images (paths), places, text lines, music + BPM, target length (default 15 s), format (default 9:16).
  2. Plan an edit on paper first — 4–8 scenes, 1.5–3.5 s each for clips; hook in the first second; one idea per scene.
  3. Write reel.json next to the assets (start from node "$RM/engine/cli.mjs" init reel.json; schema: section 4 of $RM/SKILL.md). Good defaults:
    • clips: camera: "handheld" or "punch-in", speed: "ramp-mid" on the hero shot
    • transitions: whip between energetic shots, zoom into reveals, leak/burn for mood changes, glitch on beats
    • text: captions overlay on clips; a style scene (neon-sign, inflate, beat-cut…) as opener or closer
    • places: a map-route scene as the intro
    • look: teal-orange (travel), kodak (warm lifestyle), cyber (music), sepia + film (history)
  4. Check stills at the middle of each scene (still reel.json --at <t> --size 540 --out "$TMP/reel-<t>.png") and look at them; the CLI flags typos with "did you mean". Fix, then render reel.json --out reel.mp4 (add --audio).
  5. Verify duration with ffprobe and deliver.

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.