postmark-automation
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.
Install with Tessl CLI
npx tessl i github:Lingjie-chen/MT5 --skill postmark-automation71
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Evaluation results
94%
54%Automated Pricing Change Notification Campaign
Batch templated email sending workflow
RUBE_SEARCH_TOOLS first
0%
100%
Connection verification
0%
100%
Template discovery step
70%
100%
Correct send tool
50%
100%
Batch size enforcement
100%
100%
TemplateId XOR TemplateAlias
0%
100%
TemplateModel key matching
100%
100%
Rate limit handling
10%
70%
Defensive response parsing
37%
100%
Template ID as integer
0%
62%
Workflow documented
50%
100%
Without context: $0.4883 · 2m 33s · 23 turns · 24 in / 9,177 out tokens
With context: $0.4901 · 1m 47s · 22 turns · 26 in / 6,782 out tokens
100%
53%Rebrand the Welcome Email Template
Template management and validation workflow
RUBE_SEARCH_TOOLS first
0%
100%
Connection setup
0%
100%
List templates first
100%
100%
Fetch before edit
100%
100%
Edit preserves all fields
50%
100%
Template ID as integer
100%
100%
Variable inspection step
0%
100%
Post-edit validation
50%
100%
TemplateModel keys match variables
0%
100%
Workflow documented
50%
100%
Without context: $0.8143 · 3m 29s · 49 turns · 752 in / 11,903 out tokens
With context: $0.4774 · 2m 3s · 18 turns · 20 in / 8,088 out tokens
92%
4%Weekly Email Delivery Health Report
Delivery monitoring and bounce management
RUBE_SEARCH_TOOLS first
100%
0%
Connection verification
0%
100%
Delivery stats tool
100%
100%
Outbound overview tool
100%
100%
Date format YYYY-MM-DD
100%
100%
Bounce retrieval tool
100%
100%
Bounce type enumeration
100%
100%
Hard bounce removal flag
100%
100%
Spam complaint retrieval
100%
100%
Pagination with count/offset
100%
100%
Workflow documented
100%
100%
Defensive response parsing
0%
100%
Without context: $1.1711 · 4m 32s · 39 turns · 167 in / 12,279 out tokens
With context: $0.6577 · 2m 43s · 23 turns · 30 in / 11,001 out tokens
- Evaluated
- Agent
- Claude Code
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.