Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →List all installed EvoNexus plugins with status, version, and update availability. Use when the user asks about installed plugins, wants an inventory, or mentions plugins generally. Triggers on "quais plugins tenho", "list plugins", "plugins instalados", "o que tem instalado".
.claude/skills/evolution-foundation-plugin-list/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -64% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 61% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -70% | 0% |
Return the current inventory of installed plugins.
pythonfrom dashboard.backend.sdk_client import evo plugins = evo.get("/api/plugins")
Response is a JSON array of {id, name, version, status, tier, installed_at, source_url}.
If user hints at "desatualizados" / "outdated" / "updates":
pythonmarketplace = evo.get("/api/plugins/marketplace")
Match installed vs marketplace by id; flag when installed.version < marketplace.version (semver).
| slug | name | version | status | update? |
|------|------|---------|--------|---------|
| pm-essentials | PM Essentials | 1.0.0 | active | — |
| int-pipedrive | Pipedrive Suite | 0.4.1 | active | 0.5.0 |Order by name ascending. Hide columns user didn't ask for.
Close with a one-line summary: total installed, N with updates, N broken (status=broken = manifest SHA mismatch, suggest plugin-health).
[] — say plainly no plugins installed, offer plugin-marketplace.source_url from output unless asked — long and noisy.status is routine_activation_pending, surface explicitly — scheduler offline during install, restart needed.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 6,403 | 8,033 | +25% | 1 | 1 | 0% | 1,083 | 1,264 | +17% | 0 | 0 | — |
case-02 | fail→fail | 6,864 | 4,482 | -35% | 1 | 1 | 0% | 1,221 | 1,155 | -5% | 0 | 0 | — |
case-03 | fail→fail | 7,236 | 22,202 | +207% | 1 | 1 | 0% | 1,243 | 4,224 | +240% | 0 | 0 | — |
case-04 | pass→pass | 6,754 | 5,233 | -23% | 1 | 1 | 0% | 1,118 | 1,361 | +22% | 0 | 0 | — |
case-05 | fail→pass | 9,584 | 1,499 | -84% | 1 | 1 | 0% | 1,653 | 587 | -64% | 0 | 0 | — |
case-06 | pass→pass | 10,704 | 7,118 | -34% | 1 | 1 | 0% | 1,839 | 1,603 | -13% | 0 | 0 | — |
case-07 | pass→fail | 3,176 | 3,865 | +22% | 1 | 1 | 0% | 547 | 1,110 | +103% | 0 | 0 | — |
case-13 | fail→pass | 10,509 | 2,123 | -80% | 1 | 1 | 0% | 1,693 | 690 | -59% | 0 | 0 | — |
case-08 | fail→pass | 3,512 | 3,999 | +14% | 1 | 1 | 0% | 686 | 1,105 | +61% | 0 | 0 | — |
case-09 | fail→fail | 4,366 | 4,468 | +2% | 1 | 1 | 0% | 652 | 574 | -12% | 0 | 0 | — |
case-10 | pass→pass | 4,578 | 2,175 | -52% | 1 | 1 | 0% | 777 | 732 | -6% | 0 | 0 | — |
case-11 | fail→pass | 4,904 | 2,114 | -57% | 1 | 1 | 0% | 822 | 774 | -6% | 0 | 0 | — |
case-12 | fail→pass | 13,744 | 2,055 | -85% | 1 | 1 | 0% | 2,217 | 675 | -70% | 0 | 0 | — |
case-14 | pass→pass | 9,794 | 2,382 | -76% | 1 | 1 | 0% | 1,678 | 778 | -54% | 0 | 0 | — |
case-15 | fail→pass | 9,804 | 1,989 | -80% | 1 | 1 | 0% | 1,545 | 716 | -54% | 0 | 0 | — |
case-16 | pass→pass | 2,896 | 3,254 | +12% | 1 | 1 | 0% | 509 | 888 | +74% | 0 | 0 | — |
case-17 | fail→pass | 6,656 | 6,176 | -7% | 1 | 1 | 0% | 1,100 | 1,479 | +34% | 0 | 0 | — |
case-18 | fail→pass | 6,771 | 24,503 | +262% | 1 | 1 | 0% | 1,135 | 4,236 | +273% | 0 | 0 | — |
case-19 | pass→pass | 3,938 | 3,047 | -23% | 1 | 1 | 0% | 366 | 928 | +154% | 0 | 0 | — |
case-20 | pass→pass | 5,389 | 2,665 | -51% | 1 | 1 | 0% | 1,022 | 889 | -13% | 0 | 0 | — |
case-21 | fail→pass | 8,591 | 1,303 | -85% | 1 | 1 | 0% | 1,450 | 554 | -62% | 0 | 0 | — |
case-22 | fail→pass | 4,884 | 1,875 | -62% | 1 | 1 | 0% | 876 | 720 | -18% | 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 21 counted toward the lift figure. The other 1 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 +41 percentage points is the difference between those two pass rates over the 21 comparable cases. 1 case got worse with the skill loaded, and it is 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.