Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Routing target for `/poteto-mode` and any request for poteto's style. Resume an existing `poteto-agent` for the conversation rather than spawning a sibling. Reads the `poteto-mode` skill's `SKILL.md` in full before any work, including its inline Principles index. Substituting `generalPurpose` skips that read and drifts.
.claude/skills/kunanonj-cursor-plugin-pstack-agent-poteto-agent/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✓→✓ | ＝ Same ✓ | 48% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 28% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | -22% | 0% |
| case-01 | ✗→✗ | ＝ Same ✗ | 25% | 0% |
| case-02 | ✗→✗ | ＝ Same ✗ | 68% | 0% |
You are operating as poteto-mode's full agent style. Read the poteto-mode skill's SKILL.md in full before doing any work, including its inline Principles index. Navigate to a leaf principle-* skill whenever you apply that principle.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 16,283 | 23,389 | +44% | 1 | 1 | 0% | 3,532 | 4,408 | +25% | 0 | 0 | — |
case-02 | fail→fail | 14,145 | 21,687 | +53% | 1 | 1 | 0% | 3,181 | 5,331 | +68% | 0 | 0 | — |
case-03 | fail→fail | 14,110 | 10,071 | -29% | 1 | 1 | 0% | 3,330 | 258 | -92% | 0 | 0 | — |
case-04 | pass→pass | 11,915 | 13,700 | +15% | 1 | 1 | 0% | 1,438 | 2,135 | +48% | 0 | 0 | — |
case-05 | fail→fail | 1,282 | 16,795 | +1210% | 1 | 1 | 0% | 219 | 3,087 | +1310% | 0 | 0 | — |
case-06 | pass→pass | 4,620 | 6,286 | +36% | 1 | 1 | 0% | 1,095 | 1,404 | +28% | 0 | 0 | — |
case-07 | pass→pass | 8,555 | 7,217 | -16% | 1 | 1 | 0% | 1,808 | 1,413 | -22% | 0 | 0 | — |
case-08 | fail→fail | 15,852 | 16,060 | +1% | 1 | 1 | 0% | 3,515 | 3,061 | -13% | 0 | 0 | — |
case-09 | fail→fail | 14,960 | 4,048 | -73% | 1 | 1 | 0% | 3,313 | 260 | -92% | 0 | 0 | — |
case-10 | fail→fail | 18,472 | 19,253 | +4% | 1 | 1 | 0% | 4,221 | 4,999 | +18% | 0 | 0 | — |
case-11 | fail→fail | 18,369 | 2,978 | -84% | 1 | 1 | 0% | 3,955 | 305 | -92% | 0 | 0 | — |
case-12 | fail→fail | 14,208 | 16,756 | +18% | 1 | 1 | 0% | 3,181 | 4,047 | +27% | 0 | 0 | — |
case-13 | fail→fail | 15,379 | 3,736 | -76% | 1 | 1 | 0% | 3,341 | 299 | -91% | 0 | 0 | — |
case-14 | fail→fail | 20,803 | 22,758 | +9% | 1 | 1 | 0% | 4,456 | 5,115 | +15% | 0 | 0 | — |
case-15 | fail→fail | 9,553 | 26,609 | +179% | 1 | 1 | 0% | 2,334 | 6,244 | +168% | 0 | 0 | — |
case-16 | fail→fail | 18,653 | 2,896 | -84% | 1 | 1 | 0% | 4,027 | 212 | -95% | 0 | 0 | — |
case-17 | fail→fail | 13,955 | 4,870 | -65% | 1 | 1 | 0% | 2,794 | 268 | -90% | 0 | 0 | — |
case-18 | fail→fail | 21,707 | 2,223 | -90% | 1 | 1 | 0% | 6,172 | 221 | -96% | 0 | 0 | — |
case-19 | fail→fail | 16,929 | 3,707 | -78% | 1 | 1 | 0% | 3,091 | 260 | -92% | 0 | 0 | — |
case-20 | fail→fail | 16,039 | 4,563 | -72% | 1 | 1 | 0% | 3,664 | 327 | -91% | 0 | 0 | — |
case-21 | fail→fail | 14,626 | 21,905 | +50% | 1 | 1 | 0% | 3,029 | 4,816 | +59% | 0 | 0 | — |
case-22 | fail→fail | 13,777 | 6,070 | -56% | 1 | 1 | 0% | 2,895 | 294 | -90% | 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. 22 cases were attempted, and 12 counted toward the lift figure. The other 10 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of 0 percentage points is the difference between those two pass rates over the 12 comparable cases.
Other measured skills in the registry, with their headline benchmark lift.