Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Persistent task management and productivity intelligence via MCP. Captures tasks from conversation, plans your day, tracks patterns, and gives personalized recommendations that improve over time.
.claude/skills/davepoon-tycana/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 177% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 96% | 0% |
| case-20 | ✓→✓ | ＝ Same ✓ | 25% | 0% |
| case-21 | ✓→✓ | ＝ Same ✓ | 8% | 0% |
| case-22 | ✓→✓ | ＝ Same ✓ | 10% | 0% |
Tycana gives Claude persistent memory about your work across conversations. Connect once via MCP, and every session includes your tasks, projects, deadlines, blockers, and computed intelligence from your patterns.
Homepage: tycana.com Getting started: tycana.com/getting-started
https://app.tycana.com/mcp (OAuth 2.1)/plugin install tycana| Tool | Purpose | |------|---------| | capture | Create tasks from conversation context | | complete | Mark items done with outcome and notes | | plan_day | Generate prioritized daily plan | | what_next | Energy-aware next action recommendation | | review | Progress summary with pattern analysis | | get_context | Load current work context | | search | Find items by keyword or filter | | list_items | List items with status/project filters | | get_item | Get full detail on a specific item | | update_item | Modify item properties | | relate_items | Create blocking/dependency relationships | | remember | Store personal preferences and constraints | | cleanup_project | Archive completed items in a project | | delete_item | Remove an item |
"Plan my day"
"Remind me to update the deployment docs before Friday"
"What should I work on next? I have about an hour and low energy"
"How's the infrastructure project going?"
"Review my week"
"Brain dump — I've got a bunch of things rattling around"| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→fail | 8,575 | 1,658 | -81% | 1 | 1 | 0% | 586 | 808 | +38% | 0 | 0 | — |
case-01 | fail→fail | 3,243 | 6,445 | +99% | 1 | 1 | 0% | 501 | 884 | +76% | 0 | 0 | — |
case-02 | fail→fail | 4,090 | 4,242 | +4% | 1 | 1 | 0% | 672 | 858 | +28% | 0 | 0 | — |
case-03 | fail→fail | 6,143 | 12,199 | +99% | 1 | 1 | 0% | 1,190 | 1,580 | +33% | 0 | 0 | — |
case-04 | fail→fail | 3,759 | 5,041 | +34% | 1 | 1 | 0% | 600 | 1,333 | +122% | 0 | 0 | — |
case-05 | fail→fail | 4,809 | 2,432 | -49% | 1 | 1 | 0% | 780 | 920 | +18% | 0 | 0 | — |
case-07 | fail→pass | 2,311 | 3,324 | +44% | 1 | 1 | 0% | 368 | 1,019 | +177% | 0 | 0 | — |
case-08 | fail→fail | 4,883 | 2,499 | -49% | 1 | 1 | 0% | 346 | 804 | +132% | 0 | 0 | — |
case-09 | fail→fail | 3,349 | 2,501 | -25% | 1 | 1 | 0% | 504 | 884 | +75% | 0 | 0 | — |
case-10 | fail→fail | 3,064 | 2,082 | -32% | 1 | 1 | 0% | 442 | 818 | +85% | 0 | 0 | — |
case-11 | fail→pass | 2,633 | 2,192 | -17% | 1 | 1 | 0% | 415 | 815 | +96% | 0 | 0 | — |
case-12 | fail→fail | 6,485 | 2,668 | -59% | 1 | 1 | 0% | 1,052 | 730 | -31% | 0 | 0 | — |
case-13 | fail→fail | 2,403 | 2,016 | -16% | 1 | 1 | 0% | 332 | 767 | +131% | 0 | 0 | — |
case-14 | fail→fail | 2,411 | 5,649 | +134% | 1 | 1 | 0% | 388 | 858 | +121% | 0 | 0 | — |
case-15 | fail→fail | 4,170 | 3,044 | -27% | 1 | 1 | 0% | 701 | 657 | -6% | 0 | 0 | — |
case-16 | fail→fail | 4,618 | 3,704 | -20% | 1 | 1 | 0% | 653 | 807 | +24% | 0 | 0 | — |
case-17 | fail→fail | 10,761 | 4,881 | -55% | 1 | 1 | 0% | 1,071 | 934 | -13% | 0 | 0 | — |
case-18 | fail→fail | 6,078 | 4,278 | -30% | 1 | 1 | 0% | 936 | 804 | -14% | 0 | 0 | — |
case-19 | fail→fail | 3,088 | 3,652 | +18% | 1 | 1 | 0% | 502 | 963 | +92% | 0 | 0 | — |
case-20 | pass→pass | 7,718 | 7,439 | -4% | 1 | 1 | 0% | 1,375 | 1,723 | +25% | 0 | 0 | — |
case-21 | pass→pass | 13,507 | 11,323 | -16% | 1 | 1 | 0% | 2,289 | 2,483 | +8% | 0 | 0 | — |
case-22 | pass→pass | 14,126 | 12,128 | -14% | 1 | 1 | 0% | 2,550 | 2,803 | +10% | 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 14 counted toward the lift figure. The other 8 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 +9 percentage points is the difference between those two pass rates over the 14 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.