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.
71
58%
Does it follow best practices?
Impact
95%
1.63xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/postmark-automation/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is strong in specificity and distinctiveness, clearly identifying Postmark email delivery as its niche and listing concrete actions. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. Trigger terms could also be broadened to include more natural user language variations.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about sending emails via Postmark, checking email delivery status, managing email templates, or handling bounces.'
Include additional natural trigger terms users might say, such as 'transactional email', 'email API', 'send email', or 'email notifications'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'send templated emails', 'manage templates', 'monitor delivery stats and bounces', and 'search tools first for current schemas'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the capabilities listed, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Postmark', 'email delivery', 'templated emails', 'templates', 'bounces', and 'delivery stats'. However, it misses common user variations like 'transactional email', 'email API', or 'send email' without 'templated'. The mention of 'Rube MCP (Composio)' is technical jargon users wouldn't naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific mention of 'Postmark' and 'Rube MCP (Composio)'. This is a clear niche — Postmark email delivery via a specific MCP tool — and is unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a competent API integration skill with good structural organization, clear tool sequencing, and a helpful quick reference table. Its main weaknesses are the lack of concrete executable examples (actual MCP call syntax), some redundancy in pitfalls across sections, and missing explicit error recovery/validation feedback loops in workflows involving batch operations. The content would benefit from being more concise and including at least one complete worked example.
Suggestions
Add at least one concrete, complete example showing actual MCP tool invocation syntax (e.g., a full RUBE_SEARCH_TOOLS call followed by a POSTMARK_SEND_BATCH_WITH_TEMPLATES call with real parameters) to improve actionability.
Consolidate repeated pitfalls (batch 500 limit, numeric template IDs, sender verification) into the 'Known Pitfalls' section only, removing duplicates from individual workflows to improve conciseness.
Add explicit validation/error-recovery feedback loops to the batch send workflow (e.g., 'Check response for ErrorCode per message; if any fail, log and retry or alert') since batch operations are semi-destructive.
Consider splitting detailed per-workflow content (parameters, pitfalls) into a separate reference file, keeping SKILL.md as a concise overview with the quick reference table and setup instructions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some redundancy—pitfalls are repeated across sections (e.g., batch 500 limit, template IDs being numeric, sender verification mentioned multiple times). The 'Known Pitfalls' section rehashes points already covered in individual workflows. Some explanatory text like 'Hard bounces indicate permanent delivery failures' explains concepts Claude already knows. | 2 / 3 |
Actionability | Tool sequences are clearly named and ordered with key parameters listed, which is helpful. However, there are no executable code examples or concrete MCP call syntax—just tool names and parameter lists. The 'Template Variable Resolution' pattern uses pseudocode-style numbered steps rather than actual invocation examples. A user/Claude would need to discover exact call syntax via RUBE_SEARCH_TOOLS anyway, but concrete examples of actual tool calls would improve actionability. | 2 / 3 |
Workflow Clarity | Workflows are well-sequenced with clear step ordering and labeled as Required/Optional/Prerequisite. However, validation checkpoints are weak—template validation is marked 'Optional' rather than recommended before batch sends, and there's no explicit error handling or feedback loop for failed sends or API errors. The setup section has a good verification flow, but core workflows lack 'if this fails, do that' recovery steps. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a useful quick reference table. However, at ~180 lines with detailed pitfalls and parameters for every workflow, this is a lot of inline content that could benefit from splitting detailed workflow guides into separate files. The single external link to Composio docs is appropriate, but there are no bundle files to offload the detailed per-workflow content. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- davepoon/buildwithclaude
- Commit
d065ead
- Reviewed
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.