CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/postmark-automation/SKILL.md

The canonical home for this skill is postmark-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, concrete operational guide whose tool sequences and pitfalls are genuinely actionable, but it is held back by redundant repetition across sections, a filler closing section, optionalized validation on a batch-send operation (capping workflow clarity at 3), and no use of bundle reference files to split the detailed material. The strongest aspect is actionability; the weakest are workflow validation and progressive disclosure.

Suggestions

Make template validation an enforced checkpoint for batch sends: mark POSTMARK_VALIDATE_TEMPLATE as required before POSTMARK_SEND_BATCH_WITH_TEMPLATES and add a fix-and-retry loop on validation errors.

Deduplicate the repeated pitfalls (500-message limit, sender-signature verification, numeric template IDs, RUBE_SEARCH_TOOLS-first instruction) into the Known Pitfalls section only, and delete the empty "When to Use" section.

Move the per-workflow parameter details and the quick-reference table into a references/ file (e.g., TOOL_REFERENCE.md) linked from a concise overview, and add a fully-specified example call for the batch-send case.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows and is dense with operational detail, but there is noticeable duplication: the 500-message batch limit, sender-signature verification, "template IDs are numeric integers", and "always call RUBE_SEARCH_TOOLS first" each appear twice, and the closing "When to Use" section ("This skill is applicable to execute the workflow or actions described in the overview.") is pure filler. This is more than the minor trimmable instances of anchor 4, fitting anchor 3.

3 / 5

Actionability

Concrete, executable guidance throughout: exact tool slugs (POSTMARK_SEND_BATCH_WITH_TEMPLATES etc.), precise parameter names and formats (YYYY-MM-DD, count/offset pagination), per-step Required/Optional markers, and a quick-reference table. It falls short of anchor 5 only in lacking a fully-specified example call (e.g., a sample Messages array with From/To/TemplateModel values) for the most common case.

4 / 5

Workflow Clarity

Sequences are clearly ordered with Required/Optional/Prerequisite markers and the setup section verifies connection status is ACTIVE, which would support a 4. However, the batch-send workflow marks POSTMARK_VALIDATE_TEMPLATE as merely [Optional] with no "only proceed when valid" checkpoint or fix-and-retry loop, and per the judging guideline a batch operation without enforced validation caps workflow clarity at 3.

3 / 5

Progressive Disclosure

The single ~190-line file is well-sectioned with headers and a quick-reference table, but there are no bundle files at all — all five workflows, the pitfalls catalog, and the per-tool parameter detail that could live in reference files are inlined in SKILL.md. This matches anchor 3 (content that should be separate is inline) rather than anchor 4, and the under-50-line simple-skill exception does not apply at this length.

3 / 5

Total

13

/

20

Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concrete description that names the domain and multiple specific actions, but it is missing an explicit when-to-use trigger clause, which caps its completeness and leaves a small conflict window with generic email-sending requests. Anchor 5 examples all pair a comprehensive what with explicit trigger phrases, which this description lacks.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions Postmark, transactional email, email bounces, or asks to send/monitor templated emails."

Include natural synonyms users say, such as "transactional email" and "spam complaints", to broaden trigger coverage.

Mention the server-configuration capability (or other body workflows) so the action list is fully comprehensive.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "send templated emails, manage templates, monitor delivery stats and bounces" — with only a minor gap (server-configuration tasks from the body are unmentioned), matching anchor 4 rather than the fully comprehensive anchor 5.

4 / 5

Completeness

The "what" is clear (automate Postmark delivery via Rube MCP with named actions), but there is no "Use when..." clause or equivalent trigger guidance — the trailing "Always search tools first for current schemas" is an instruction, not a when-to-use trigger. Per the judging guideline, a missing explicit trigger caps completeness at 3, and anchor 4 requires both a what and a when.

3 / 5

Trigger Term Quality

Good natural keyword coverage: "Postmark", "templated emails", "templates", "delivery stats", "bounces" are phrases users would actually say, though a few natural terms like "transactional email" or "spam complaints" are missing — anchor 4.

4 / 5

Distinctiveness Conflict Risk

The Postmark + Rube MCP (Composio) framing gives a clear niche with minimal conflict risk against non-email skills, but without a "Use when" clause a generic request like "send an email" could plausibly trigger it over other email-delivery skills — mostly distinct with minor overlap, anchor 4.

4 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/postmark-automation/SKILL.md

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.