Get this effect
Switch to Code in your Claude Desktop App
Install the skill (once)
Show the prompt
Install the Recharm video effects skill: download https://recharm-growth-staging.s3.us-east-2.amazonaws.com/website/downloads/recharm-video-effects.zip and unzip it into ~/.claude/skillsAsk for the effect
Add a rotating word headline to input.mp4 Headline: SKIN THAT FEELS Words: SMOOTH, BRIGHT, HYDRATED, RADIANT
Several videos, several effects, one ask
Put your clips in the folder, mention them with @, and ask for everything at once. Claude runs one tested script after another on each clip, then joins them.
Add a rotating word headline to @clip1.mp4, put a sale badge on @clip2.mp4, give @clip3.mp4 a VHS look, then join all three with crossfades.
Settings you can change
Ask Claude to change any of these, or edit them at the top of the script.
| Setting | Default | What it does |
|---|---|---|
HEADLINE | SKIN THAT FEELS | The line that stays put. |
WORDS | SMOOTH, BRIGHT, HYDRATED, RADIANT | The words that take turns under it. |
START | 0.4 | Second the headline appears. |
HOLD | 1.2 | Seconds each word stays. |
TURN | 0.3 | Seconds each roll takes. |
WORD_COLOR | (255, 214, 0) | Rotating word color. |
Without the skill
Don’t want to install the skill? Paste this prompt into Claude Code and Claude writes the script itself.
Show the prompt
Add a rotating word headline to input.mp4: from 0.4 seconds, the line "SKIN THAT FEELS" in white bold text with a thin black outline (text height 7.5% of the frame width), centered 9% of the way down, and directly under it one larger yellow (255, 214, 0) word with a black outline (14% of the frame width), centered across. The word cycles SMOOTH, BRIGHT, HYDRATED, RADIANT and back to SMOOTH, changing every 1.2 seconds (at 0.4, 1.6, 2.8, 4.0 and 5.2 seconds); each change takes 0.3 seconds with an ease-out, the old word rolling up and out while the new one rolls up in from below, both clipped to a strip the height of the word so they vanish at its edges like a slot machine. The top line never moves. Use Python with Pillow to draw the text and ffmpeg to put it on the video (don't rely on ffmpeg's drawtext filter), keep the audio, and save it as output.mp4.Run it without Claude
This is the exact script we tested. Save it as rotating-word-headline.py and run:
python3 rotating-word-headline.py input.mp4 output.mp4Show the script
#!/usr/bin/env python3
"""Rotating word headline: a fixed line stays put while the yellow word under it rolls through alternatives.
Usage: python3 rotating-word-headline.py input.mp4 output.mp4
Needs ffmpeg and Pillow (pip install pillow).
"""
import json
import math
import subprocess
import sys
from pathlib import Path
from PIL import Image, ImageDraw, ImageFont
HEADLINE = "SKIN THAT FEELS" # the line that stays put
WORDS = ["SMOOTH", "BRIGHT", "HYDRATED", "RADIANT"] # the words that take turns under it
START = 0.4 # second the headline appears
HOLD = 1.2 # seconds each word stays
TURN = 0.3 # seconds a word takes to roll out and the next to roll in
SIZE = 0.075 # headline text height as a share of the frame width
WORD_SIZE = 0.14 # rotating word height as a share of the frame width
Y = 0.09 # center of the headline line (0 = top, 1 = bottom)
WORD_COLOR = (255, 214, 0) # rotating word color
FONTS = ["/System/Library/Fonts/Supplemental/Arial Bold.ttf", # macOS
"/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf", # Linux
"C:/Windows/Fonts/arialbd.ttf"] # Windows
FONT_FILE = next((f for f in FONTS if Path(f).exists()), None) or sys.exit("No bold font found: add one to FONTS")
def ease_out(p):
p = min(max(p, 0), 1)
return 1 - (1 - p) ** 3
def slot(t):
"""The word strip: the current word, or the old one rolling up and out while the new one rolls up in."""
img = Image.new("RGBA", (w, slot_h))
draw = ImageDraw.Draw(img)
k = int((t - START) // HOLD)
p = ease_out((t - START - k * HOLD) / TURN)
words = [(WORDS[k % len(WORDS)], (1 - p) * slot_h)]
if k > 0:
words.append((WORDS[(k - 1) % len(WORDS)], -p * slot_h))
for word, dy in words:
draw.text((w / 2, slot_h / 2 + dy), word, font=word_font, anchor="mm", fill=WORD_COLOR,
stroke_width=round(w * 0.008), stroke_fill="black")
return img
def overlay(t):
img = Image.new("RGBA", (w, h))
if t >= START:
ImageDraw.Draw(img).text((w / 2, h * Y), HEADLINE, font=font, anchor="mm", fill="white",
stroke_width=round(w * 0.006), stroke_fill="black")
img.alpha_composite(slot(t), (0, round(h * Y + font.size * 0.6)))
return img
def probe(path):
info = json.loads(subprocess.check_output(["ffprobe", "-v", "error", "-select_streams", "v:0", "-show_entries",
"stream=width,height,r_frame_rate:format=duration", "-of", "json", path]))
s = info["streams"][0]
num, den = s["r_frame_rate"].split("/")
return s["width"], s["height"], s["r_frame_rate"], float(num) / float(den), float(info["format"]["duration"])
def render(src, out):
"""Draw overlay(t) on every frame of src and save to out, keeping the audio."""
ff = subprocess.Popen(["ffmpeg", "-y", "-v", "error", "-i", src,
"-f", "rawvideo", "-pix_fmt", "rgba", "-s", f"{w}x{h}", "-r", rate, "-i", "-",
"-filter_complex", "[0:v][1:v]overlay=shortest=1,format=yuv420p[v]",
"-map", "[v]", "-map", "0:a?", "-c:v", "libx264", "-crf", "18", "-c:a", "copy", out],
stdin=subprocess.PIPE)
for i in range(math.ceil(duration * fps)):
ff.stdin.write(overlay(i / fps).tobytes())
ff.stdin.close()
if ff.wait():
sys.exit("ffmpeg failed")
src, out = sys.argv[1:3]
w, h, rate, fps, duration = probe(src)
font = ImageFont.truetype(FONT_FILE, round(w * SIZE))
word_font = ImageFont.truetype(FONT_FILE, round(w * WORD_SIZE))
slot_h = round(word_font.size * 1.3)
render(src, out)





