Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user has the Tycana plugin installed but appears to be new (no items, empty context, or MCP connection issues) — guide them through getting started.
.claude/skills/ccplugins-getting-started-with-tycana/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -12% | 0% |
This skill activates when a user is new to Tycana or hasn't set up their connection yet.
You'll know a user is new when:
get_context returns empty results or a "No active items found" noteThe user has an account but hasn't captured anything yet. Help them get started:
"What are you working on right now? I'll start tracking it so I can help you plan and prioritize."
"Now that I know what's on your plate, try /tycana:morning tomorrow for a daily briefing, or /tycana:next when you're not sure what to tackle."
remember to save it.Guide them to set up their connection:
"Looks like Tycana isn't connected yet. You'll need a Tycana account to use these features."
Don't troubleshoot connection issues beyond this. Point them to the getting-started page.
Practical and low-pressure. The user just installed something new — don't overwhelm them with features or philosophy. Just help them capture their first few items and let the value speak for itself.
"I'll remember this across our conversations. Next time you ask what to work on, I'll know."
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 12,460 | 7,825 | -37% | 1 | 1 | 0% | 1,841 | 1,279 | -31% | 0 | 0 | — |
case-02 | fail→pass | 12,218 | 4,869 | -60% | 1 | 1 | 0% | 1,847 | 1,361 | -26% | 0 | 0 | — |
case-03 | pass→pass | 9,487 | 4,247 | -55% | 1 | 1 | 0% | 1,298 | 1,138 | -12% | 0 | 0 | — |
case-04 | fail→pass | 11,312 | 6,214 | -45% | 1 | 1 | 0% | 1,637 | 1,365 | -17% | 0 | 0 | — |
case-05 | fail→pass | 10,567 | 3,936 | -63% | 1 | 1 | 0% | 1,508 | 1,135 | -25% | 0 | 0 | — |
case-06 | fail→pass | 8,144 | 3,423 | -58% | 1 | 1 | 0% | 1,140 | 998 | -12% | 0 | 0 | — |
case-07 | pass→pass | 8,752 | 14,004 | +60% | 1 | 1 | 0% | 913 | 1,691 | +85% | 0 | 0 | — |
case-08 | fail→fail | 4,699 | 9,666 | +106% | 1 | 1 | 0% | 489 | 2,058 | +321% | 0 | 0 | — |
case-09 | fail→pass | 8,685 | 5,855 | -33% | 1 | 1 | 0% | 1,187 | 1,100 | -7% | 0 | 0 | — |
case-10 | fail→pass | 14,299 | 4,258 | -70% | 1 | 1 | 0% | 1,911 | 1,298 | -32% | 0 | 0 | — |
case-11 | pass→pass | 12,817 | 11,650 | -9% | 1 | 1 | 0% | 1,749 | 2,222 | +27% | 0 | 0 | — |
case-12 | fail→pass | 30,987 | 4,550 | -85% | 1 | 1 | 0% | 4,442 | 1,282 | -71% | 0 | 0 | — |
case-13 | fail→pass | 7,581 | 4,116 | -46% | 1 | 1 | 0% | 1,141 | 1,185 | +4% | 0 | 0 | — |
case-14 | fail→fail | 8,258 | 10,163 | +23% | 1 | 1 | 0% | 1,163 | 1,736 | +49% | 0 | 0 | — |
case-15 | fail→pass | 13,503 | 4,631 | -66% | 1 | 1 | 0% | 957 | 1,246 | +30% | 0 | 0 | — |
case-16 | fail→pass | 9,638 | 3,195 | -67% | 1 | 1 | 0% | 1,328 | 984 | -26% | 0 | 0 | — |
case-17 | pass→pass | 7,750 | 5,531 | -29% | 1 | 1 | 0% | 1,041 | 1,197 | +15% | 0 | 0 | — |
case-18 | fail→pass | 23,777 | 14,823 | -38% | 1 | 1 | 0% | 1,626 | 1,298 | -20% | 0 | 0 | — |
case-19 | pass→pass | 6,166 | 13,243 | +115% | 1 | 1 | 0% | 761 | 2,536 | +233% | 0 | 0 | — |
case-20 | pass→pass | 11,468 | 10,408 | -9% | 1 | 1 | 0% | 1,625 | 1,797 | +11% | 0 | 0 | — |
case-21 | pass→pass | 16,559 | 12,214 | -26% | 1 | 1 | 0% | 2,422 | 2,164 | -11% | 0 | 0 | — |
case-22 | pass→pass | 12,570 | 12,640 | +1% | 1 | 1 | 0% | 1,935 | 2,640 | +36% | 0 | 0 | — |
case-23 | pass→pass | 12,797 | 11,683 | -9% | 1 | 1 | 0% | 1,950 | 2,592 | +33% | 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. 23 cases were attempted. The headline lift of +52 percentage points is the difference between those two pass rates over the 23 comparable cases.
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.