Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Diagnose and fix Superset problems — connection failures, offline hosts, terminals not attaching, auth or update issues. Use when the user reports something broken or misbehaving in Superset itself, before filing feedback.
.claude/skills/superset-sh-doctor/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -52% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -41% | 0% |
Diagnose first, change one thing at a time, verify after each change.
superset status — host service healthsuperset auth whoami — auth + active orgsuperset hosts list — host reachabilitysuperset --version| Signature | Fix | | --- | --- | | whoami fails / session expired | superset auth login | | Host shows offline | superset hosts wake <id>; confirm the machine is awake and online | | Host service not running | superset start | | CLI and desktop app version mismatch, or stale CLI | superset update | | App-side misbehavior (macOS) | read the newest entries in ~/Library/Logs/Superset/main.log for errors |
Propose the matching fix and get the user's go-ahead before running anything that changes state. Never delete data as a "fix".
Re-run the originally failing action. If it works, say exactly what was wrong and what fixed it.
If unresolved, offer to file it via the superset:feedback skill — carry over the collected diagnostics (versions, status output, the relevant log excerpt) so the report arrives pre-triaged. Ask before including any log content; logs can contain paths and project names.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 10,324 | 12,000 | +16% | 1 | 1 | 0% | 1,705 | 2,044 | +20% | 0 | 0 | — |
case-02 | fail→fail | 4,216 | 3,510 | -17% | 1 | 1 | 0% | 691 | 791 | +14% | 0 | 0 | — |
case-03 | fail→fail | 11,216 | 3,094 | -72% | 1 | 1 | 0% | 2,181 | 648 | -70% | 0 | 0 | — |
case-04 | fail→pass | 12,566 | 4,346 | -65% | 1 | 1 | 0% | 2,034 | 919 | -55% | 0 | 0 | — |
case-10 | fail→pass | 6,793 | 2,632 | -61% | 1 | 1 | 0% | 1,121 | 793 | -29% | 0 | 0 | — |
case-05 | fail→pass | 12,728 | 3,492 | -73% | 1 | 1 | 0% | 1,784 | 856 | -52% | 0 | 0 | — |
case-06 | fail→pass | 13,856 | 5,052 | -64% | 1 | 1 | 0% | 1,998 | 1,185 | -41% | 0 | 0 | — |
case-07 | fail→pass | 9,785 | 6,766 | -31% | 1 | 1 | 0% | 1,604 | 1,299 | -19% | 0 | 0 | — |
case-08 | fail→fail | 17,345 | 3,431 | -80% | 1 | 1 | 0% | 3,428 | 977 | -71% | 0 | 0 | — |
case-09 | fail→pass | 12,144 | 3,672 | -70% | 1 | 1 | 0% | 1,918 | 957 | -50% | 0 | 0 | — |
case-11 | fail→pass | 17,654 | 3,980 | -77% | 1 | 1 | 0% | 2,568 | 1,007 | -61% | 0 | 0 | — |
case-12 | fail→pass | 9,172 | 4,013 | -56% | 1 | 1 | 0% | 1,510 | 1,023 | -32% | 0 | 0 | — |
case-13 | pass→pass | 15,093 | 3,599 | -76% | 1 | 1 | 0% | 2,250 | 964 | -57% | 0 | 0 | — |
case-14 | fail→fail | 13,575 | 3,811 | -72% | 1 | 1 | 0% | 2,313 | 971 | -58% | 0 | 0 | — |
case-15 | pass→pass | 13,656 | 4,689 | -66% | 1 | 1 | 0% | 2,075 | 1,037 | -50% | 0 | 0 | — |
case-16 | fail→pass | 11,947 | 4,342 | -64% | 1 | 1 | 0% | 1,828 | 1,022 | -44% | 0 | 0 | — |
case-17 | fail→pass | 9,747 | 3,141 | -68% | 1 | 1 | 0% | 1,519 | 763 | -50% | 0 | 0 | — |
case-18 | fail→pass | 15,982 | 3,715 | -77% | 1 | 1 | 0% | 2,438 | 929 | -62% | 0 | 0 | — |
case-19 | fail→pass | 17,825 | 6,088 | -66% | 1 | 1 | 0% | 2,494 | 1,356 | -46% | 0 | 0 | — |
case-20 | pass→pass | 14,969 | 15,495 | +4% | 1 | 1 | 0% | 2,716 | 2,526 | -7% | 0 | 0 | — |
case-21 | pass→pass | 15,836 | 9,599 | -39% | 1 | 1 | 0% | 2,579 | 2,030 | -21% | 0 | 0 | — |
case-22 | pass→pass | 12,606 | 7,174 | -43% | 1 | 1 | 0% | 2,470 | 1,826 | -26% | 0 | 0 | — |
case-23 | fail→fail | 4,524 | 2,594 | -43% | 1 | 1 | 0% | 667 | 751 | +13% | 0 | 0 | — |
case-24 | fail→pass | 12,224 | 2,649 | -78% | 1 | 1 | 0% | 2,022 | 763 | -62% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted. The headline lift of +58 percentage points is the difference between those two pass rates over the 24 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.