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 swipe up arrow to input.mp4 Label: SWIPE UP
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 swipe up arrow 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 |
|---|---|---|
LABEL | SWIPE UP | The text under the arrow. |
START | 0.5 | Second the arrow and text fade in. |
PERIOD | 0.8 | Seconds per bounce. |
BOUNCE | 0.045 | How far the arrow jumps, as a share of the frame height. |
ARROW_COLOR | (255, 214, 0) | Chevron 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 swipe up arrow to input.mp4: two stacked yellow (255, 214, 0) chevrons pointing up, each 18% of the frame width across and 5.5% of the width tall, drawn with lines 2.4% of the width thick and set 6% of the width apart, centered across with their resting center 80% of the way down. Under them, "SWIPE UP" in white bold text 8.5% of the frame width tall, centered across at 89.5% down. Give both a soft dark blurred shadow. They fade in over 0.25 seconds starting at 0.5 seconds, then the chevrons bounce until the end: they lift 4.5% of the frame height and drop back every 0.8 seconds (lift = |sin(pi * (t - 0.5) / 0.8)| x 4.5% of the height), while the text stays still. Nothing shows before 0.5 seconds. Use Python with Pillow to draw it 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 swipe-up-arrow.py and run:
python3 swipe-up-arrow.py input.mp4 output.mp4Show the script
#!/usr/bin/env python3
"""Swipe up arrow: a yellow double chevron bounces upward over "SWIPE UP" text near the bottom of the frame.
Usage: python3 swipe-up-arrow.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, ImageFilter, ImageFont
LABEL = "SWIPE UP" # the text under the arrow
START = 0.5 # second the arrow and text fade in
FADE = 0.25 # seconds the fade-in takes
PERIOD = 0.8 # seconds per bounce
BOUNCE = 0.045 # how far the arrow jumps, as a share of the frame height
ARROW_Y = 0.80 # arrow's resting center (0 = top, 1 = bottom)
TEXT_Y = 0.895 # text's center
ARROW_COLOR = (255, 214, 0) # chevron color
TEXT_SIZE = 0.085 # text height as a share of the frame width
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 with_shadow(img):
"""Put a soft dark shadow under img so it reads on any footage."""
shadow = Image.new("RGBA", img.size, (0, 0, 0, 0))
shadow.putalpha(img.getchannel("A").point(lambda a: a * 0.6))
shadow = shadow.filter(ImageFilter.GaussianBlur(w * 0.012))
shadow.alpha_composite(img)
return shadow
def arrow():
"""Two stacked chevrons pointing up, centered in a w x w/3 image."""
img = Image.new("RGBA", (w, w // 3))
draw = ImageDraw.Draw(img)
half, rise, gap, stroke = w * 0.09, w * 0.055, w * 0.06, round(w * 0.024)
cx, cy = w / 2, w / 6
for tip in (cy - gap * 0.9, cy + gap * 0.1):
draw.line([(cx - half, tip + rise), (cx, tip), (cx + half, tip + rise)], fill=ARROW_COLOR, width=stroke, joint="curve")
return with_shadow(img)
def label():
img = Image.new("RGBA", (w, w // 5))
font = ImageFont.truetype(FONT_FILE, round(w * TEXT_SIZE))
ImageDraw.Draw(img).text((w / 2, w / 10), LABEL, font=font, anchor="mm", fill="white")
return with_shadow(img)
def overlay(t):
img = Image.new("RGBA", (w, h))
if t < START:
return img
alpha = min((t - START) / FADE, 1)
lift = abs(math.sin(math.pi * (t - START) / PERIOD)) * BOUNCE * h # up and back down once per PERIOD
img.alpha_composite(text_img, (0, round(h * TEXT_Y - text_img.height / 2)))
img.alpha_composite(arrow_img, (0, round(h * ARROW_Y - arrow_img.height / 2 - lift)))
if alpha < 1:
img.putalpha(img.getchannel("A").point(lambda a: a * alpha))
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)
arrow_img, text_img = arrow(), label()
render(src, out)





