Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →superset-sh/feedback
Collect and submit feedback about Superset — bug reports, feature requests, or general feedback — privately to the Superset team or as a public GitHub issue.
Passed 6 of 13 test cases with the skill, and 5 of 13 without it.
and 6 more in the full report
6 fixed5 passed either way9 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
When collecting initial environment context for a Superset report, what exact CLI commands retrieve the version and operating system details?
| Checked | Without skill | With skill |
|---|---|---|
| Runs superset --version for version information. | Missed | Passed |
| Runs uname -sm for operating system details. | Missed | Passed |
The instructions your model reads when the skill loads.
Help the user turn their feedback about Superset into a well-formed report and submit it where they choose. Treat whatever they wrote after the command as the seed.
Run in parallel; skip anything that fails:
superset --version and uname -sm for the environment blocksuperset auth whoami for the signed-in user/org (private submissions only)Do NOT include repository contents, terminal output, or logs unless the user explicitly agrees when asked.
For bugs, also offer (never assume):
--diagnostics flag. Tell the user logs can contain file paths and project names before they agree.Classify as bug, feature request, or general feedback from their words; ask only if genuinely ambiguous. Then draft:
Show the full draft, then ask the user (use the ask_user tool if available, otherwise a plain question) with exactly these options:
Never submit anything before the user explicitly picks 1 or 2. Loop on edits.
test cases passed, vs 5 / 13 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.