screen-recording

import imageio.v3 as iio
from PIL import Image
import numpy as np
 
frames = []
durations = []
 
for frame_path, duration_ms in frame_list:
    img = Image.open(frame_path)
    frames.append(np.array(img))
    durations.append(duration_ms)
 
iio.imwrite("demo.gif", frames, duration=durations, loop=0)

from PIL import Image, ImageDraw, ImageFont
 
def annotate_frame(frame_path, annotations, out_path):
    img = Image.open(frame_path)
    draw = ImageDraw.Draw(img)
 
    for ann in annotations:
        # Apply annotation (rect, arrow, label, etc.)
        pass
 
    img.save(out_path)

def apply_fade(base_frame, annotation_layer, alpha):
    """Blend annotation onto frame at given alpha (0.0 to 1.0)"""
    blended = Image.blend(
        base_frame.convert("RGBA"),
        annotation_layer.convert("RGBA"),
        alpha
    )
    return blended.convert("RGB")
 
# 2-frame pop-in at 10fps: 50% then 100%
faded_frames = [
    apply_fade(base, annotations, 0.5),  # frame 1: half opacity
    apply_fade(base, annotations, 1.0),  # frame 2: full opacity
]

# Small test GIF: 10 bare frames → fade frames → 15 hold frames
# Add a frame counter overlay for debugging:
draw.text((10, height - 30), f"F{i}/{total} a={alpha:.0%} FADE",
          fill="white", font=small_font)

import mss
from PIL import Image
import time
 
def record_gif(output_path, region=None, duration=5, fps=8):
    """Record screen region to GIF. region = {left, top, width, height} or None for full screen."""
    with mss.mss() as sct:
        if region is None:
            region = sct.monitors[1]  # primary monitor
 
        frames = []
        t_end = time.time() + duration
        while time.time() < t_end:
            t0 = time.time()
            shot = sct.grab(region)
            frames.append(Image.frombytes('RGB', shot.size, shot.rgb))
            time.sleep(max(0, 1 / fps - (time.time() - t0)))
 
    frames[0].save(output_path, save_all=True, append_images=frames[1:],
                   duration=int(1000 / fps), loop=0, optimize=True)
    return len(frames)
 
record_gif('demo.gif', region={'left': 0, 'top': 0, 'width': 800, 'height': 500}, duration=3)

# Find window rect, then record it as a GIF
# Reuse find_window() from the ui-screenshots skill
import ctypes
from ctypes import c_int, Structure, byref, windll
 
class RECT(Structure):
    _fields_ = [('left', c_int), ('top', c_int), ('right', c_int), ('bottom', c_int)]
 
hwnd = find_window('My App')[0][0]
rect = RECT()
windll.user32.GetWindowRect(hwnd, byref(rect))
region = {'left': rect.left, 'top': rect.top,
          'width': rect.right - rect.left, 'height': rect.bottom - rect.top}
record_gif('app-demo.gif', region=region, duration=5, fps=8)

import numpy as np
from scipy import ndimage
 
def find_changed_clusters(frame_a, frame_b, threshold=30, min_pixels=300, dilate=5):
    """Find bounding boxes of changed regions between two frames."""
    diff = np.abs(frame_b.astype(float) - frame_a.astype(float)).max(axis=2)
    mask = diff > threshold
    dilated = ndimage.binary_dilation(mask, iterations=dilate)
    labeled, n = ndimage.label(dilated)
    clusters = []
    for i in range(1, n + 1):
        ys, xs = np.where(labeled == i)
        if len(ys) < min_pixels:
            continue
        clusters.append((xs.min(), ys.min(), xs.max(), ys.max(), len(ys)))
    return sorted(clusters, key=lambda c: -c[4])  # largest first