Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Get AI-powered match predictions for Premier League and Champions League including scores, next goal, and corners.
.claude/skills/davila7-footballbin-predictions/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -49% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -41% | 0% |
Get AI-powered predictions for Premier League and Champions League matches via the FootballBin MCP API.
Run scripts/footballbin.sh with the following commands:
bashscripts/footballbin.sh predictions premier_league scripts/footballbin.sh predictions champions_league
bashscripts/footballbin.sh predictions premier_league 27
bashscripts/footballbin.sh predictions premier_league --home arsenal scripts/footballbin.sh predictions premier_league --away liverpool scripts/footballbin.sh predictions premier_league --home chelsea --away wolves
bashscripts/footballbin.sh tools
| Input | League | |-------|--------| | premier_league, epl, pl, prem | Premier League | | champions_league, ucl, cl | Champions League |
Common aliases work: united (Man Utd), city (Man City), spurs (Tottenham), wolves (Wolverhampton), gunners (Arsenal), reds (Liverpool), blues (Chelsea), villa (Aston Villa), forest (Nottingham Forest), palace (Crystal Palace), barca (Barcelona), real (Real Madrid), bayern (Bayern Munich), psg (PSG), juve (Juventus), inter (Inter Milan), bvb (Dortmund), atleti (Atletico Madrid).
Each match prediction includes:
| URL | Data Sent | Purpose | |-----|-----------|---------| | https://ru7m5svay1.execute-api.eu-central-1.amazonaws.com/prod/mcp | League, matchweek, team filters | Fetch match predictions |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 3,713 | 26,509 | +614% | 1 | 1 | 0% | 399 | 827 | +107% | 0 | 0 | — |
case-02 | fail→fail | 5,060 | 6,041 | +19% | 1 | 1 | 0% | 846 | 1,058 | +25% | 0 | 0 | — |
case-03 | fail→fail | 8,483 | 6,788 | -20% | 1 | 1 | 0% | 1,375 | 879 | -36% | 0 | 0 | — |
case-04 | fail→fail | 11,271 | 7,565 | -33% | 1 | 1 | 0% | 1,684 | 856 | -49% | 0 | 0 | — |
case-05 | fail→fail | 7,923 | 5,562 | -30% | 1 | 1 | 0% | 1,248 | 791 | -37% | 0 | 0 | — |
case-06 | fail→pass | 12,222 | 5,867 | -52% | 1 | 1 | 0% | 2,125 | 1,087 | -49% | 0 | 0 | — |
case-07 | fail→fail | 8,643 | 5,107 | -41% | 1 | 1 | 0% | 1,223 | 814 | -33% | 0 | 0 | — |
case-08 | fail→pass | 12,914 | 1,878 | -85% | 1 | 1 | 0% | 1,979 | 806 | -59% | 0 | 0 | — |
case-09 | fail→pass | 6,510 | 5,546 | -15% | 1 | 1 | 0% | 1,016 | 844 | -17% | 0 | 0 | — |
case-10 | fail→fail | 6,612 | 6,379 | -4% | 1 | 1 | 0% | 312 | 883 | +183% | 0 | 0 | — |
case-11 | fail→fail | 11,769 | 5,228 | -56% | 1 | 1 | 0% | 1,775 | 885 | -50% | 0 | 0 | — |
case-12 | fail→fail | 14,705 | 6,107 | -58% | 1 | 1 | 0% | 2,128 | 791 | -63% | 0 | 0 | — |
case-13 | fail→fail | 12,538 | 6,435 | -49% | 1 | 1 | 0% | 1,966 | 826 | -58% | 0 | 0 | — |
case-14 | fail→fail | 11,909 | 5,128 | -57% | 1 | 1 | 0% | 1,950 | 813 | -58% | 0 | 0 | — |
case-15 | fail→fail | 11,226 | 5,086 | -55% | 1 | 1 | 0% | 1,787 | 762 | -57% | 0 | 0 | — |
case-16 | fail→fail | 9,760 | 1,762 | -82% | 1 | 1 | 0% | 1,512 | 843 | -44% | 0 | 0 | — |
case-17 | fail→fail | 13,130 | 5,384 | -59% | 1 | 1 | 0% | 2,175 | 819 | -62% | 0 | 0 | — |
case-18 | fail→pass | 9,397 | 5,902 | -37% | 1 | 1 | 0% | 1,409 | 1,053 | -25% | 0 | 0 | — |
case-19 | fail→pass | 7,488 | 1,614 | -78% | 1 | 1 | 0% | 1,426 | 848 | -41% | 0 | 0 | — |
case-20 | fail→pass | 8,164 | 1,901 | -77% | 1 | 1 | 0% | 1,373 | 873 | -36% | 0 | 0 | — |
case-21 | fail→pass | 12,772 | 1,998 | -84% | 1 | 1 | 0% | 2,243 | 957 | -57% | 0 | 0 | — |
case-22 | pass→pass | 4,434 | 3,412 | -23% | 1 | 1 | 0% | 602 | 1,161 | +93% | 0 | 0 | — |
case-23 | pass→pass | 5,737 | 4,021 | -30% | 1 | 1 | 0% | 761 | 1,117 | +47% | 0 | 0 | — |
case-24 | pass→pass | 15,674 | 4,749 | -70% | 1 | 1 | 0% | 2,444 | 1,013 | -59% | 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. 24 cases were attempted, and 11 counted toward the lift figure. The other 13 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 +29 percentage points is the difference between those two pass rates over the 11 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.