Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Send transactional and marketing emails with Amazon SES. Verify domains and identities, create reusable email templates, configure receipt rules for incoming mail, and handle bounces and complaints with SNS notifications.
.claude/skills/terminalskills-aws-ses/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 135% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-01 | ✓→✓ | = Same ✓ | 90% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 31% | 0% |
Amazon Simple Email Service (SES) is a cost-effective email platform for sending transactional, marketing, and notification emails. It also receives incoming email and integrates with S3, SNS, and Lambda for processing.
bash# Verify a domain (creates DKIM records) aws sesv2 create-email-identity --email-identity example.com
bash# Get DKIM tokens to add as DNS CNAME records aws sesv2 get-email-identity --email-identity example.com \ --query 'DkimAttributes.Tokens'
bash# Verify a single email address (for testing) aws sesv2 create-email-identity --email-identity test@example.com
bash# List verified identities aws sesv2 list-email-identities --query 'EmailIdentities[].IdentityName'
bash# Send a simple email aws sesv2 send-email \ --from-email-address "noreply@example.com" \ --destination '{"ToAddresses":["user@example.com"]}' \ --content '{ "Simple": { "Subject": {"Data": "Order Confirmation #12345"}, "Body": { "Html": {"Data": "<h1>Thank you!</h1><p>Your order has been confirmed.</p>"}, "Text": {"Data": "Thank you! Your order has been confirmed."} } } }' \ --configuration-set-name prod-tracking
python# Send email with boto3 import boto3 ses = boto3.client('sesv2') ses.send_email( FromEmailAddress='noreply@example.com', Destination={ 'ToAddresses': ['user@example.com'], 'BccAddresses': ['archive@example.com'] }, Content={ 'Simple': { 'Subject': {'Data': 'Your Invoice'}, 'Body': { 'Html': {'Data': '<h1>Invoice #INV-001</h1><p>Amount: $99.99</p>'}, 'Text': {'Data': 'Invoice #INV-001\nAmount: $99.99'} } } }, ConfigurationSetName='prod-tracking' )
bash# Create a template aws sesv2 create-email-template \ --template-name order-confirmation \ --template-content '{ "Subject": "Order Confirmation #{{orderNumber}}", "Html": "<h1>Hi {{customerName}},</h1><p>Your order #{{orderNumber}} for {{itemName}} has been confirmed.</p><p>Total: ${{total}}</p>", "Text": "Hi {{customerName}},\nYour order #{{orderNumber}} for {{itemName}} has been confirmed.\nTotal: ${{total}}" }'
bash# Send using a template aws sesv2 send-email \ --from-email-address "orders@example.com" \ --destination '{"ToAddresses":["user@example.com"]}' \ --content '{ "Template": { "TemplateName": "order-confirmation", "TemplateData": "{\"orderNumber\":\"12345\",\"customerName\":\"Alice\",\"itemName\":\"Widget Pro\",\"total\":\"99.99\"}" } }'
python# Bulk templated sending with boto3 import boto3 ses = boto3.client('sesv2') ses.send_bulk_email( FromEmailAddress='marketing@example.com', DefaultContent={ 'Template': { 'TemplateName': 'weekly-newsletter', 'TemplateData': '{"week":"Jan 15"}' } }, BulkEmailEntries=[ { 'Destination': {'ToAddresses': ['alice@example.com']}, 'ReplacementEmailContent': { 'ReplacementTemplate': { 'ReplacementTemplateData': '{"name":"Alice","recommendations":"Widget A, Widget B"}' } } }, { 'Destination': {'ToAddresses': ['bob@example.com']}, 'ReplacementEmailContent': { 'ReplacementTemplate': { 'ReplacementTemplateData': '{"name":"Bob","recommendations":"Gadget X, Gadget Y"}' } } } ], ConfigurationSetName='marketing-tracking' )
bash# Create a configuration set with event destinations aws sesv2 create-configuration-set --configuration-set-name prod-tracking # Add SNS destination for bounces and complaints aws sesv2 create-configuration-set-event-destination \ --configuration-set-name prod-tracking \ --event-destination-name bounce-handler \ --event-destination '{ "Enabled": true, "MatchingEventTypes": ["BOUNCE", "COMPLAINT"], "SnsDestination": { "TopicArn": "arn:aws:sns:us-east-1:123456789:ses-bounces" } }'
python# Lambda handler for bounce/complaint SNS notifications import json def handler(event, context): for record in event['Records']: message = json.loads(record['Sns']['Message']) notification_type = message['notificationType'] if notification_type == 'Bounce': bounce = message['bounce'] for recipient in bounce['bouncedRecipients']: email = recipient['emailAddress'] bounce_type = bounce['bounceType'] # Permanent or Transient if bounce_type == 'Permanent': suppress_email(email) elif notification_type == 'Complaint': complaint = message['complaint'] for recipient in complaint['complainedRecipients']: unsubscribe_email(recipient['emailAddress'])
bash# Create a receipt rule set aws ses create-receipt-rule-set --rule-set-name inbound-rules aws ses set-active-receipt-rule-set --rule-set-name inbound-rules
bash# Create rule to store incoming email in S3 and trigger Lambda aws ses create-receipt-rule \ --rule-set-name inbound-rules \ --rule '{ "Name": "process-support-emails", "Enabled": true, "Recipients": ["support@example.com"], "Actions": [ {"S3Action": {"BucketName": "incoming-email", "ObjectKeyPrefix": "support/"}}, {"LambdaAction": {"FunctionArn": "arn:aws:lambda:us-east-1:123456789:function:process-support-email"}} ] }'
bash# Check sending quota and statistics aws sesv2 get-account --query '{SendQuota:SendQuota,SendingEnabled:SendingEnabled}'
bash# Get sending statistics aws ses get-send-statistics --query 'SendDataPoints[-5:]'
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 6,320 | 3,306 | -48% | 1 | 1 | 0% | 1,269 | 2,407 | +90% | 0 | 0 | — |
case-02 | pass→pass | 14,654 | 9,735 | -34% | 1 | 1 | 0% | 3,086 | 4,038 | +31% | 0 | 0 | — |
case-03 | pass→pass | 3,705 | 2,352 | -37% | 1 | 1 | 0% | 670 | 2,240 | +234% | 0 | 0 | — |
case-04 | pass→pass | 6,609 | 2,406 | -64% | 1 | 1 | 0% | 1,149 | 2,238 | +95% | 0 | 0 | — |
case-05 | fail→pass | 13,786 | 5,487 | -60% | 1 | 1 | 0% | 1,276 | 2,999 | +135% | 0 | 0 | — |
case-06 | fail→pass | 13,886 | 9,835 | -29% | 1 | 1 | 0% | 2,506 | 3,371 | +35% | 0 | 0 | — |
case-07 | pass→pass | 6,577 | 4,412 | -33% | 1 | 1 | 0% | 1,242 | 2,721 | +119% | 0 | 0 | — |
case-16 | pass→pass | 3,515 | 1,608 | -54% | 1 | 1 | 0% | 616 | 2,181 | +254% | 0 | 0 | — |
case-08 | pass→pass | 8,518 | 5,085 | -40% | 1 | 1 | 0% | 1,850 | 2,846 | +54% | 0 | 0 | — |
case-09 | pass→pass | 16,380 | 13,458 | -18% | 1 | 1 | 0% | 3,404 | 4,705 | +38% | 0 | 0 | — |
case-10 | fail→pass | 10,385 | 6,015 | -42% | 1 | 1 | 0% | 2,190 | 3,135 | +43% | 0 | 0 | — |
case-11 | pass→pass | 6,430 | 3,189 | -50% | 1 | 1 | 0% | 1,382 | 2,533 | +83% | 0 | 0 | — |
case-12 | pass→pass | 10,347 | 8,067 | -22% | 1 | 1 | 0% | 2,093 | 3,586 | +71% | 0 | 0 | — |
case-13 | pass→pass | 13,934 | 11,586 | -17% | 1 | 1 | 0% | 3,131 | 4,519 | +44% | 0 | 0 | — |
case-14 | pass→pass | 12,320 | 9,669 | -22% | 1 | 1 | 0% | 2,645 | 3,831 | +45% | 0 | 0 | — |
case-15 | pass→pass | 5,120 | 2,770 | -46% | 1 | 1 | 0% | 980 | 2,403 | +145% | 0 | 0 | — |
case-17 | pass→pass | 4,611 | 3,071 | -33% | 1 | 1 | 0% | 976 | 2,417 | +148% | 0 | 0 | — |
case-18 | pass→pass | 7,073 | 3,379 | -52% | 1 | 1 | 0% | 1,338 | 2,412 | +80% | 0 | 0 | — |
case-19 | pass→pass | 13,224 | 13,510 | +2% | 1 | 1 | 0% | 2,570 | 4,560 | +77% | 0 | 0 | — |
case-20 | pass→pass | 10,350 | 9,424 | -9% | 1 | 1 | 0% | 1,793 | 3,641 | +103% | 0 | 0 | — |
case-21 | pass→pass | 5,353 | 4,488 | -16% | 1 | 1 | 0% | 1,167 | 2,836 | +143% | 0 | 0 | — |
case-22 | pass→pass | 6,315 | 4,653 | -26% | 1 | 1 | 0% | 1,482 | 2,870 | +94% | 0 | 0 | — |
case-23 | pass→pass | 7,614 | 5,515 | -28% | 1 | 1 | 0% | 1,418 | 2,873 | +103% | 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. The headline lift of +13 percentage points is the difference between those two pass rates over the 23 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.