Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jeremylongshore/klingai-storage-integration
Download and store Kling AI generated videos in cloud storage (S3, GCS, Azure).
Passed 16 of 22 test cases with the skill, and 10 of 22 without it.
and 5 more in the full report
7 fixed9 passed either way5 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
When preserving metadata for a generated video saved as `/tmp/output/video_123.mp4`, what filename and extension should be given to the sidecar JSON metadata file?
| Checked | Without skill | With skill |
|---|---|---|
| Replaces .mp4 extension with .meta.json. | Missed | Passed |
The instructions your model reads when the skill loads.
Kling AI video URLs from task_result.videos[].url are temporary CDN links that expire. You must download and store videos in your own storage. This skill covers S3, GCS, and Azure Blob.
import requests
import os
def download_video(video_url: str, output_dir: str = "output") -> str:
"""Download generated video from Kling CDN."""
os.makedirs(output_dir, exist_ok=True)
# Extract filename or generate one
filename = video_url.split("/")[-1].split("?")[0]
if not filename.endswith(".mp4"):
filename = f"kling_{int(time.time())}.mp4"
filepath = os.path.join(output_dir, filename)
response = requests.get(video_url, stream=True, timeout=120)
response.raise_for_status()
with open(filepath, "wb") as f:
for chunk in response.iter_content(chunk_size=8192):
f.write(chunk)
size_mb = os.path.getsize(filepath) / (1024 * 1024)
print(f"Downloaded: {filepath} ({size_mb:.1f} MB)")
return filepath
import boto3
def upload_to_s3(filepath: str, bucket: str, key_prefix: str = "kling-videos/") -> str:
test cases passed, vs 10 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.