Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Automate Postmark email delivery tasks via Rube MCP (Composio): send templated emails, manage templates, monitor delivery stats and bounces. Always search tools first for current schemas.
.claude/skills/davepoon-postmark-automation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 188% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 73% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 393% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 87% | 0% |
Automate Postmark transactional email operations through Composio's Postmark toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/postmark
RUBE_MANAGE_CONNECTIONS with toolkit postmarkRUBE_SEARCH_TOOLS first to get current tool schemasGet Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
RUBE_SEARCH_TOOLS respondsRUBE_MANAGE_CONNECTIONS with toolkit postmarkWhen to use: User wants to send templated emails to multiple recipients in one call
Tool sequence:
POSTMARK_LIST_TEMPLATES - Find available templates and their IDs Prerequisite]POSTMARK_VALIDATE_TEMPLATE - Validate template with model data before sending Optional]POSTMARK_SEND_BATCH_WITH_TEMPLATES - Send batch emails using a template Required]Key parameters:
TemplateId or TemplateAlias: Identifier for the template to useMessages: Array of message objects with From, To, TemplateModelTemplateModel: Key-value pairs matching template variablesPitfalls:
TemplateId or TemplateAlias is required, not bothTemplateModel keys must match template variable names exactly (case-sensitive)When to use: User wants to create, edit, or inspect email templates
Tool sequence:
POSTMARK_LIST_TEMPLATES - List all templates with IDs and names Required]POSTMARK_GET_TEMPLATE - Get full template details including HTML/text body Optional]POSTMARK_EDIT_TEMPLATE - Update template content or settings Optional]POSTMARK_VALIDATE_TEMPLATE - Test template rendering with sample data Optional]Key parameters:
TemplateId: Numeric template ID for GET/EDIT operationsName: Template display nameSubject: Email subject line (supports template variables)HtmlBody: HTML content of the templateTextBody: Plain text fallback contentTemplateType: 'Standard' or 'Layout'Pitfalls:
When to use: User wants to check email delivery health, open/click rates, or outbound overview
Tool sequence:
POSTMARK_GET_DELIVERY_STATS - Get bounce counts by type Required]POSTMARK_GET_OUTBOUND_OVERVIEW - Get sent/opened/clicked/bounced summary Required]POSTMARK_GET_TRACKED_EMAIL_COUNTS - Get tracked email volume over time Optional]Key parameters:
fromdate: Start date for filtering stats (YYYY-MM-DD)todate: End date for filtering stats (YYYY-MM-DD)tag: Filter stats by message tagmessagestreamid: Filter by message stream (e.g., 'outbound', 'broadcast')Pitfalls:
messagestreamid defaults to all streams if not specifiedWhen to use: User wants to review bounced emails or spam complaints
Tool sequence:
POSTMARK_GET_BOUNCES - List bounced messages with details Required]POSTMARK_GET_SPAM_COMPLAINTS - List spam complaint records Optional]POSTMARK_GET_DELIVERY_STATS - Get bounce summary counts Optional]Key parameters:
count: Number of records to return per pageoffset: Pagination offset for resultstype: Bounce type filter (e.g., 'HardBounce', 'SoftBounce', 'SpamNotification')fromdate/todate: Date range filtersemailFilter: Filter by recipient email addressPitfalls:
count and offset, not page tokensWhen to use: User wants to view or modify Postmark server configuration
Tool sequence:
POSTMARK_GET_SERVER - Retrieve current server settings Required]POSTMARK_EDIT_SERVER - Update server configuration Optional]Key parameters:
Name: Server display nameSmtpApiActivated: Enable/disable SMTP API accessBounceHookUrl: Webhook URL for bounce notificationsInboundHookUrl: Webhook URL for inbound email processingTrackOpens: Enable/disable open trackingTrackLinks: Link tracking mode ('None', 'HtmlAndText', 'HtmlOnly', 'TextOnly')Pitfalls:
SmtpApiActivated affects SMTP relay access immediately1. Call POSTMARK_GET_TEMPLATE with TemplateId
2. Inspect HtmlBody/TextBody for {{variable}} placeholders
3. Build TemplateModel dict with matching keys
4. Call POSTMARK_VALIDATE_TEMPLATE to verify renderingcount for results per page (varies by endpoint)offset to skip previously fetched resultsAuthentication:
Rate Limits:
Response Parsing:
data or data.data| Task | Tool Slug | Key Params | |------|-----------|------------| | Send batch templated emails | POSTMARK_SEND_BATCH_WITH_TEMPLATES | Messages, TemplateId/TemplateAlias | | List templates | POSTMARK_LIST_TEMPLATES | Count, Offset, TemplateType | | Get template details | POSTMARK_GET_TEMPLATE | TemplateId | | Edit template | POSTMARK_EDIT_TEMPLATE | TemplateId, Name, Subject, HtmlBody | | Validate template | POSTMARK_VALIDATE_TEMPLATE | TemplateId, TemplateModel | | Delivery stats | POSTMARK_GET_DELIVERY_STATS | (none or date filters) | | Outbound overview | POSTMARK_GET_OUTBOUND_OVERVIEW | fromdate, todate, tag | | Get bounces | POSTMARK_GET_BOUNCES | count, offset, type, emailFilter | | Get spam complaints | POSTMARK_GET_SPAM_COMPLAINTS | count, offset, fromdate, todate | | Tracked email counts | POSTMARK_GET_TRACKED_EMAIL_COUNTS | fromdate, todate, tag | | Get server config | POSTMARK_GET_SERVER | (none) | | Edit server config | POSTMARK_EDIT_SERVER | Name, TrackOpens, TrackLinks |
Powered by Composio
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 10,017 | 4,623 | -54% | 1 | 1 | 0% | 473 | 2,249 | +375% | 0 | 0 | — |
case-02 | fail→fail | 8,137 | 4,996 | -39% | 1 | 1 | 0% | 1,268 | 2,313 | +82% | 0 | 0 | — |
case-03 | fail→fail | 6,277 | 4,941 | -21% | 1 | 1 | 0% | 552 | 2,225 | +303% | 0 | 0 | — |
case-04 | fail→pass | 8,145 | 5,526 | -32% | 1 | 1 | 0% | 1,774 | 3,091 | +74% | 0 | 0 | — |
case-05 | pass→pass | 7,220 | 4,435 | -39% | 1 | 1 | 0% | 1,293 | 2,717 | +110% | 0 | 0 | — |
case-06 | fail→pass | 5,287 | 4,552 | -14% | 1 | 1 | 0% | 967 | 2,789 | +188% | 0 | 0 | — |
case-07 | pass→pass | 11,023 | 6,037 | -45% | 1 | 1 | 0% | 1,882 | 3,144 | +67% | 0 | 0 | — |
case-08 | pass→fail | 9,673 | 6,428 | -34% | 1 | 1 | 0% | 1,610 | 2,272 | +41% | 0 | 0 | — |
case-09 | fail→pass | 8,374 | 4,914 | -41% | 1 | 1 | 0% | 1,660 | 2,868 | +73% | 0 | 0 | — |
case-10 | fail→pass | 2,647 | 2,271 | -14% | 1 | 1 | 0% | 466 | 2,299 | +393% | 0 | 0 | — |
case-11 | pass→pass | 4,402 | 2,917 | -34% | 1 | 1 | 0% | 755 | 2,412 | +219% | 0 | 0 | — |
case-12 | pass→pass | 7,913 | 4,563 | -42% | 1 | 1 | 0% | 1,303 | 2,750 | +111% | 0 | 0 | — |
case-13 | pass→pass | 5,519 | 4,234 | -23% | 1 | 1 | 0% | 1,032 | 2,634 | +155% | 0 | 0 | — |
case-14 | pass→pass | 5,168 | 4,066 | -21% | 1 | 1 | 0% | 1,058 | 2,625 | +148% | 0 | 0 | — |
case-15 | pass→pass | 8,988 | 4,113 | -54% | 1 | 1 | 0% | 1,516 | 2,671 | +76% | 0 | 0 | — |
case-16 | fail→pass | 8,804 | 3,197 | -64% | 1 | 1 | 0% | 1,356 | 2,534 | +87% | 0 | 0 | — |
case-17 | fail→fail | 3,621 | 5,076 | +40% | 1 | 1 | 0% | 587 | 2,264 | +286% | 0 | 0 | — |
case-18 | fail→pass | 6,137 | 6,478 | +6% | 1 | 1 | 0% | 1,110 | 2,453 | +121% | 0 | 0 | — |
case-19 | pass→pass | 4,378 | 3,240 | -26% | 1 | 1 | 0% | 750 | 2,462 | +228% | 0 | 0 | — |
case-20 | pass→pass | 8,084 | 3,022 | -63% | 1 | 1 | 0% | 1,386 | 2,441 | +76% | 0 | 0 | — |
case-21 | fail→fail | 10,884 | 5,026 | -54% | 1 | 1 | 0% | 1,751 | 2,163 | +24% | 0 | 0 | — |
case-22 | pass→fail | 9,861 | 4,881 | -51% | 1 | 1 | 0% | 1,842 | 2,239 | +22% | 0 | 0 | — |
case-23 | fail→fail | 3,328 | 4,053 | +22% | 1 | 1 | 0% | 498 | 2,111 | +324% | 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 15 counted toward the lift figure. The other 8 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 +17 percentage points is the difference between those two pass rates over the 15 comparable cases. 4 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.