Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Launch the weft TUI dashboard in a new terminal window. Use only when user types /wf-dashboard.
.claude/skills/ccplugins-wf-dashboard/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | -45% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -85% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -63% | 0% |
| case-20 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-06 | ✓→✗ | ▼ Worse | 1% | 0% |
Launch the interactive TUI dashboard in a new terminal tab.
Run this command to open the dashboard in a new iTerm/Terminal tab:
bashPLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude/plugins/marketplaces/local/plugins/weft}" PROJECT_DIR="${CLAUDE_PROJECT_DIR:-.}" osascript -e " tell application \"System Events\" set frontApp to name of first application process whose frontmost is true end tell if frontApp is \"iTerm2\" then tell application \"iTerm\" tell current window create tab with default profile tell current session write text \"PYTHONPATH='$PLUGIN_ROOT' CLAUDE_PROJECT_DIR='$PROJECT_DIR' python3 '$PLUGIN_ROOT/core/dashboard.py'; exit\" end tell end tell end tell else tell application \"Terminal\" do script \"PYTHONPATH='$PLUGIN_ROOT' CLAUDE_PROJECT_DIR='$PROJECT_DIR' python3 '$PLUGIN_ROOT/core/dashboard.py'; exit\" activate end tell end if "
Tell the user: "Dashboard opened in a new tab. Press r to refresh, q to quit."
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 5,740 | 10,585 | +84% | 1 | 1 | 0% | 731 | 819 | +12% | 0 | 0 | — |
case-02 | fail→fail | 7,598 | 9,238 | +22% | 1 | 1 | 0% | 1,026 | 526 | -49% | 0 | 0 | — |
case-03 | fail→fail | 11,048 | 12,330 | +12% | 1 | 1 | 0% | 1,588 | 943 | -41% | 0 | 0 | — |
case-04 | pass→pass | 17,720 | 15,547 | -12% | 1 | 1 | 0% | 2,764 | 3,037 | +10% | 0 | 0 | — |
case-05 | pass→pass | 10,155 | 11,172 | +10% | 1 | 1 | 0% | 1,748 | 2,031 | +16% | 0 | 0 | — |
case-06 | pass→fail | 13,767 | 10,421 | -24% | 1 | 1 | 0% | 1,847 | 1,872 | +1% | 0 | 0 | — |
case-07 | pass→pass | 14,783 | 6,457 | -56% | 1 | 1 | 0% | 2,502 | 1,234 | -51% | 0 | 0 | — |
case-08 | pass→pass | 5,392 | 3,057 | -43% | 1 | 1 | 0% | 806 | 703 | -13% | 0 | 0 | — |
case-09 | pass→pass | 13,211 | 9,744 | -26% | 1 | 1 | 0% | 1,999 | 1,835 | -8% | 0 | 0 | — |
case-10 | fail→pass | 9,748 | 3,649 | -63% | 1 | 1 | 0% | 1,489 | 821 | -45% | 0 | 0 | — |
case-11 | pass→pass | 8,732 | 2,658 | -70% | 1 | 1 | 0% | 1,322 | 667 | -50% | 0 | 0 | — |
case-12 | pass→fail | 13,287 | 13,935 | +5% | 1 | 1 | 0% | 2,225 | 1,035 | -53% | 0 | 0 | — |
case-13 | fail→pass | 24,298 | 2,609 | -89% | 1 | 1 | 0% | 4,218 | 620 | -85% | 0 | 0 | — |
case-14 | pass→pass | 13,309 | 7,116 | -47% | 1 | 1 | 0% | 1,846 | 1,430 | -23% | 0 | 0 | — |
case-15 | pass→fail | 11,469 | 9,500 | -17% | 1 | 1 | 0% | 1,665 | 1,866 | +12% | 0 | 0 | — |
case-16 | fail→pass | 10,661 | 1,973 | -81% | 1 | 1 | 0% | 1,498 | 550 | -63% | 0 | 0 | — |
case-17 | pass→pass | 6,140 | 4,315 | -30% | 1 | 1 | 0% | 842 | 818 | -3% | 0 | 0 | — |
case-18 | pass→pass | 8,869 | 7,097 | -20% | 1 | 1 | 0% | 1,280 | 1,147 | -10% | 0 | 0 | — |
case-19 | pass→pass | 8,099 | 3,736 | -54% | 1 | 1 | 0% | 1,244 | 837 | -33% | 0 | 0 | — |
case-20 | fail→pass | 14,491 | 6,307 | -56% | 1 | 1 | 0% | 2,170 | 1,414 | -35% | 0 | 0 | — |
case-21 | pass→pass | 15,630 | 3,023 | -81% | 1 | 1 | 0% | 2,388 | 640 | -73% | 0 | 0 | — |
case-22 | pass→pass | 9,307 | 2,113 | -77% | 1 | 1 | 0% | 1,382 | 539 | -61% | 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 19 counted toward the lift figure. The other 3 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 +5 percentage points is the difference between those two pass rates over the 19 comparable cases. 3 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.