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 slide-in text to input.mp4 Text: NEW GLOW
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 slide-in text 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 |
|---|---|---|
TEXT | NEW GLOW | The headline. |
START | 0.5 | Second the slide starts. |
SLIDE | 0.6 | Seconds the slide takes. |
FADE | 0.3 | Seconds the fade in takes, from the start of the slide. |
SIZE | 0.13 | Text height as a share of the frame width. |
Y | 0.18 | Where the text's center sits (0 = top, 1 = bottom). |
COLOR | (255, 214, 0) | Text 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 slide-in text to input.mp4: "NEW GLOW" in Arial Black (or any heavy bold font) 13% of the frame width tall, bright yellow (255, 214, 0), with a soft dark shadow (color (20, 10, 40) at about 67% opacity, offset 3 px right and 5 px down, blurred 6 px). Its final position is centered across the frame with its center 18% of the way down. At 0.5 seconds it starts with its left edge one text-width past the left edge of the frame (fully off-screen) and slides right to the final position over 0.6 seconds with an ease-out (fast start, soft stop, cubic), fading from transparent to fully opaque over the first 0.3 seconds of the slide. Nothing is on screen before 0.5 seconds, and once it stops it stays still to the end. 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 slide-in-text.py and run:
python3 slide-in-text.py input.mp4 output.mp4Show the script
#!/usr/bin/env python3
"""Slide-in text: a headline glides in from off the left edge while fading in, then stops in place.
Usage: python3 slide-in-text.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
TEXT = "NEW GLOW" # the headline
START = 0.5 # second the slide starts
SLIDE = 0.6 # seconds the slide takes
FADE = 0.3 # seconds the fade in takes, from the start of the slide
SIZE = 0.13 # text height as a share of the frame width
Y = 0.18 # where the text's center sits (0 = top, 1 = bottom)
COLOR = (255, 214, 0) # text color, a bright yellow
FONTS = ["/System/Library/Fonts/Supplemental/Arial Black.ttf", # macOS
"/System/Library/Fonts/Supplemental/Arial Bold.ttf", # macOS
"/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf", # Linux
"C:/Windows/Fonts/ariblk.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 headline():
"""The text with a soft dark shadow, cropped tight, drawn once."""
font = ImageFont.truetype(FONT_FILE, round(w * SIZE))
pad = font.size // 3
x0, y0, x1, y1 = ImageDraw.Draw(Image.new("RGBA", (1, 1))).textbbox((0, 0), TEXT, font=font)
img = Image.new("RGBA", (x1 - x0 + 2 * pad, y1 - y0 + 2 * pad))
shadow = img.copy()
ImageDraw.Draw(shadow).text((pad - x0 + 3, pad - y0 + 5), TEXT, font=font, fill=(20, 10, 40, 170))
img.alpha_composite(shadow.filter(ImageFilter.GaussianBlur(6)))
ImageDraw.Draw(img).text((pad - x0, pad - y0), TEXT, font=font, fill=COLOR)
return img
def overlay(t):
"""The headline starts just past the left edge and eases out to the center, fading up as it moves."""
img = Image.new("RGBA", (w, h))
p = min(max((t - START) / SLIDE, 0), 1)
if p == 0:
return img
end_x = (w - text.width) // 2
x = round(-text.width + (end_x + text.width) * (1 - (1 - p) ** 3)) # ease out: fast start, soft stop
fade = min((t - START) / FADE, 1)
layer = text.copy()
layer.putalpha(layer.getchannel("A").point(lambda a: round(a * fade)))
img.alpha_composite(layer, (x, round(h * Y - text.height / 2)))
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)
text = headline()
render(src, out)





