Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mlflow/upload-media
Upload one or more local images or videos to GitHub and get back a `user-attachments` URL for each, to embed in a PR body, issue, or comment.
Passed 19 of 22 test cases with the skill, and 11 of 22 without it.
and 7 more in the full report
9 fixed13 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
What exact package flag parameter must be passed to `uv run` when executing the media upload CLI tool?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies --package skills for the uv run command. | Missed | Passed |
The instructions your model reads when the skill loads.
Files: $ARGUMENTS (when empty, the paths named in the request).
uv run --package skills skills upload-media <path>... # prints "<path>\t<url>" per file
Embed an image as . Embed a video as the bare URL in its own paragraph, blank line above and below; anything else renders as a link rather than a player.
No GitHub documentation covers this endpoint, so it can stop working without notice. Source: https://x.com/steipete/status/2088486859244741020.
test cases passed, vs 11 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.