Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Query and manage Stripe data via the Stripe API. Use when you need to list charges, customers, invoices, subscriptions, payment intents, refunds, products, or prices. Supports filtering, pagination, and creating/updating customers and refunds. Calls api.stripe.com directly with no third-party proxy.
.claude/skills/evolution-foundation-int-stripe/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-19 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-15 | ✓→✗ | ▼ Worse | 150% | 0% |
| case-21 | ✓→✗ | ▼ Worse | -57% | 0% |
| case-22 | ✓→✗ | ▼ Worse | -33% | 0% |
| case-20 | ✓→✓ | ＝ Same ✓ | 103% | 0% |
Interact with your Stripe account directly via the Stripe API (api.stripe.com).
STRIPE_SECRET_KEY=sk_live_... Use sk_test_... for test mode.
bashpython3 /mnt/skills/user/stripe/scripts/stripe_query.py charges --limit 10
bashpython3 /mnt/skills/user/stripe/scripts/stripe_query.py customers --limit 20
bashpython3 /mnt/skills/user/stripe/scripts/stripe_query.py customers --email user@example.com
bashpython3 /mnt/skills/user/stripe/scripts/stripe_query.py subscriptions --limit 20
bashpython3 /mnt/skills/user/stripe/scripts/stripe_query.py subscriptions --status active --limit 20
bashpython3 /mnt/skills/user/stripe/scripts/stripe_query.py invoices --limit 20
bashpython3 /mnt/skills/user/stripe/scripts/stripe_query.py payment_intents --limit 20
bashpython3 /mnt/skills/user/stripe/scripts/stripe_query.py products --limit 20
bashpython3 /mnt/skills/user/stripe/scripts/stripe_query.py prices --limit 20
bashpython3 /mnt/skills/user/stripe/scripts/stripe_query.py refunds --limit 20
bashpython3 /mnt/skills/user/stripe/scripts/stripe_query.py get charges ch_abc123 python3 /mnt/skills/user/stripe/scripts/stripe_query.py get customers cus_abc123 python3 /mnt/skills/user/stripe/scripts/stripe_query.py get subscriptions sub_abc123
bashpython3 /mnt/skills/user/stripe/scripts/stripe_query.py create refunds --charge ch_abc123 python3 /mnt/skills/user/stripe/scripts/stripe_query.py create refunds --charge ch_abc123 --amount 1000
bashpython3 /mnt/skills/user/stripe/scripts/stripe_query.py update customers cus_abc123 --email new@example.com --name "New Name"
Formatted table for lists, JSON for single objects. Use --json flag for raw JSON on any command.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-12 | fail→fail | 3,178 | 4,542 | +43% | 1 | 1 | 0% | 525 | 984 | +87% | 0 | 0 | — |
case-11 | fail→fail | 5,134 | 5,461 | +6% | 1 | 1 | 0% | 241 | 1,011 | +320% | 0 | 0 | — |
case-01 | fail→fail | 4,391 | 5,704 | +30% | 1 | 1 | 0% | 673 | 903 | +34% | 0 | 0 | — |
case-02 | fail→fail | 4,666 | 4,207 | -10% | 1 | 1 | 0% | 807 | 886 | +10% | 0 | 0 | — |
case-03 | fail→fail | 6,439 | 6,513 | +1% | 1 | 1 | 0% | 1,182 | 1,030 | -13% | 0 | 0 | — |
case-04 | fail→fail | 3,044 | 4,760 | +56% | 1 | 1 | 0% | 482 | 848 | +76% | 0 | 0 | — |
case-05 | fail→fail | 4,471 | 4,628 | +4% | 1 | 1 | 0% | 704 | 912 | +30% | 0 | 0 | — |
case-06 | fail→fail | 7,233 | 3,987 | -45% | 1 | 1 | 0% | 1,165 | 887 | -24% | 0 | 0 | — |
case-07 | fail→fail | 4,512 | 4,772 | +6% | 1 | 1 | 0% | 802 | 955 | +19% | 0 | 0 | — |
case-08 | fail→fail | 7,318 | 3,802 | -48% | 1 | 1 | 0% | 1,259 | 891 | -29% | 0 | 0 | — |
case-09 | fail→fail | 10,058 | 5,368 | -47% | 1 | 1 | 0% | 1,776 | 937 | -47% | 0 | 0 | — |
case-10 | fail→fail | 6,271 | 6,744 | +8% | 1 | 1 | 0% | 1,064 | 939 | -12% | 0 | 0 | — |
case-13 | fail→fail | 3,309 | 4,001 | +21% | 1 | 1 | 0% | 462 | 855 | +85% | 0 | 0 | — |
case-14 | fail→fail | 3,936 | 5,675 | +44% | 1 | 1 | 0% | 717 | 986 | +38% | 0 | 0 | — |
case-15 | pass→fail | 2,462 | 5,130 | +108% | 1 | 1 | 0% | 417 | 1,044 | +150% | 0 | 0 | — |
case-16 | fail→fail | 6,333 | 4,615 | -27% | 1 | 1 | 0% | 341 | 979 | +187% | 0 | 0 | — |
case-17 | fail→fail | 8,715 | 4,722 | -46% | 1 | 1 | 0% | 1,472 | 901 | -39% | 0 | 0 | — |
case-18 | fail→fail | 4,228 | 8,554 | +102% | 1 | 1 | 0% | 564 | 938 | +66% | 0 | 0 | — |
case-19 | fail→pass | 5,302 | 1,159 | -78% | 1 | 1 | 0% | 861 | 863 | +0% | 0 | 0 | — |
case-20 | pass→pass | 6,137 | 8,047 | +31% | 1 | 1 | 0% | 1,051 | 2,133 | +103% | 0 | 0 | — |
case-21 | pass→fail | 11,636 | 4,757 | -59% | 1 | 1 | 0% | 2,156 | 920 | -57% | 0 | 0 | — |
case-22 | pass→fail | 9,572 | 7,884 | -18% | 1 | 1 | 0% | 1,880 | 1,254 | -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. 22 cases were attempted, and 2 counted toward the lift figure. The other 20 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 2 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.