Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Support for sending service/transactional emails. Don't use this for sending marketing emails or verification emails.
.claude/skills/aiskillstore-extension-email/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 46% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -27% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -2% | 0% |
Service/transactional email extension for Caffeine AI.
This skill adds support for sending service and transactional emails from the backend canister. Use sendServiceEmail for order confirmations, notifications, and similar one-off emails.
This component is for sending service/transactional emails.
There is the prefabricated module mo:caffeineai-email/emailClient.mo which cannot be modified.
mo:caffeineai-email/emailClient.momodule { public type SendResult = { #ok; #err : Text; }; public func sendServiceEmail( fromUsername : Text, recipients : [Text], subject : Text, htmlBody : Text, ) : async SendResult; };
Usage for sendServiceEmail:
motoko filepath=src/backend/main.moimport Runtime "mo:core/Runtime"; import EmailClient "mo:caffeineai-email/emailClient"; actor { public func sendOrderConfirmationEmail(recipientEmailAddress : Text, username : Text, orderReference : Text) : async () { let result = await EmailClient.sendServiceEmail( "no-reply", [recipientEmailAddress], "Order " # orderReference # " confirmed", "Hello " # username # ",\nYour order " # orderReference # " has been confirmed. Your items will ship tomorrow.", ); switch (result) { case (#ok) {}; case (#err(error)) { Runtime.trap("Failed to send order confirmation email: " # error); }; }; }; };
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 42,100 | 13,690 | -67% | 1 | 1 | 0% | 1,536 | 2,249 | +46% | 0 | 0 | — |
case-02 | fail→pass | 22,098 | 12,484 | -44% | 1 | 1 | 0% | 2,491 | 1,811 | -27% | 0 | 0 | — |
case-03 | fail→pass | 17,873 | 11,626 | -35% | 1 | 1 | 0% | 2,297 | 1,817 | -21% | 0 | 0 | — |
case-04 | fail→pass | 20,980 | 12,983 | -38% | 1 | 1 | 0% | 2,753 | 1,971 | -28% | 0 | 0 | — |
case-05 | fail→pass | 12,003 | 11,395 | -5% | 1 | 1 | 0% | 1,807 | 1,772 | -2% | 0 | 0 | — |
case-06 | fail→pass | 16,262 | 9,397 | -42% | 1 | 1 | 0% | 2,103 | 1,155 | -45% | 0 | 0 | — |
case-07 | fail→pass | 12,886 | 8,450 | -34% | 1 | 1 | 0% | 2,098 | 1,099 | -48% | 0 | 0 | — |
case-08 | fail→pass | 19,826 | 7,989 | -60% | 1 | 1 | 0% | 2,365 | 1,029 | -56% | 0 | 0 | — |
case-09 | fail→pass | 15,101 | 8,108 | -46% | 1 | 1 | 0% | 2,526 | 1,971 | -22% | 0 | 0 | — |
case-10 | fail→pass | 11,210 | 3,551 | -68% | 1 | 1 | 0% | 1,889 | 947 | -50% | 0 | 0 | — |
case-11 | pass→pass | 9,978 | 1,650 | -83% | 1 | 1 | 0% | 1,523 | 697 | -54% | 0 | 0 | — |
case-12 | pass→pass | 14,675 | 10,851 | -26% | 1 | 1 | 0% | 2,303 | 1,448 | -37% | 0 | 0 | — |
case-13 | fail→pass | 24,778 | 5,964 | -76% | 1 | 1 | 0% | 3,257 | 1,549 | -52% | 0 | 0 | — |
case-14 | pass→pass | 13,744 | 4,463 | -68% | 1 | 1 | 0% | 2,181 | 1,210 | -45% | 0 | 0 | — |
case-15 | pass→pass | 8,106 | 2,581 | -68% | 1 | 1 | 0% | 1,322 | 849 | -36% | 0 | 0 | — |
case-16 | fail→pass | 10,817 | 11,590 | +7% | 1 | 1 | 0% | 1,945 | 1,698 | -13% | 0 | 0 | — |
case-17 | pass→pass | 9,880 | 5,412 | -45% | 1 | 1 | 0% | 1,744 | 1,570 | -10% | 0 | 0 | — |
case-18 | pass→pass | 13,817 | 4,450 | -68% | 1 | 1 | 0% | 1,601 | 1,328 | -17% | 0 | 0 | — |
case-19 | pass→pass | 13,035 | 7,650 | -41% | 1 | 1 | 0% | 2,526 | 1,979 | -22% | 0 | 0 | — |
case-20 | fail→fail | 22,139 | 12,809 | -42% | 1 | 1 | 0% | 3,943 | 2,954 | -25% | 0 | 0 | — |
case-21 | fail→pass | 16,574 | 10,644 | -36% | 1 | 1 | 0% | 2,833 | 1,415 | -50% | 0 | 0 | — |
case-22 | fail→pass | 24,351 | 18,904 | -22% | 1 | 1 | 0% | 3,327 | 2,427 | -27% | 0 | 0 | — |
case-23 | fail→pass | 16,363 | 8,575 | -48% | 1 | 1 | 0% | 1,779 | 1,043 | -41% | 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, and 22 counted toward the lift figure. The other 1 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 +65 percentage points is the difference between those two pass rates over the 22 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.