postmark-inbound
Use when processing incoming emails with Postmark inbound webhooks — building reply-by-email, email-to-ticket, document extraction, or any workflow that receives and parses email.
91
87%
Does it follow best practices?
Impact
96%
1.71xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted description with excellent trigger terms and a clear 'Use when' clause that makes it easy for Claude to know when to select it. Its main weakness is that it describes use cases and workflows rather than listing the specific concrete actions the skill performs (e.g., parsing headers, handling attachments, validating signatures). The Postmark-specific focus makes it highly distinctive.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Parses email headers, extracts body content and attachments, validates webhook payloads' before the 'Use when' clause.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Postmark inbound webhooks) and lists several use cases (reply-by-email, email-to-ticket, document extraction), but these are more like workflow categories than concrete actions. It doesn't specify what concrete actions the skill performs (e.g., 'parses email headers', 'extracts attachments', 'validates webhook signatures'). | 2 / 3 |
Completeness | Opens with an explicit 'Use when' clause that clearly answers when to use the skill, and the listed workflows (reply-by-email, email-to-ticket, document extraction, receiving/parsing email) answer what it does. Both dimensions are explicitly addressed. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'Postmark', 'inbound webhooks', 'reply-by-email', 'email-to-ticket', 'document extraction', 'incoming emails', 'parses email'. These cover a good range of terms a user would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — 'Postmark inbound webhooks' is a very specific niche that is unlikely to conflict with other skills. The combination of Postmark + inbound + email processing creates a clear, unique trigger profile. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that provides actionable, concrete guidance for processing Postmark inbound emails. Its strengths are excellent progressive disclosure, clear workflow sequencing with error handling details, and executable code examples. The main weakness is moderate redundancy — several concepts (MailboxHash, StrippedTextReply, body size limits) are repeated across multiple sections, and the retry table, while useful, adds significant length.
Suggestions
Consolidate repeated explanations of MailboxHash, StrippedTextReply, and body size limits — each concept appears in 2-3 places (payload table, dedicated sections, common mistakes, and notes). Keep the primary explanation and the common mistakes entry, remove from Notes.
Consider summarizing the retry schedule more concisely (e.g., '10 retries over ~10.5 hours with escalating intervals from 1 min to 6 hours') and moving the full table to the references file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundancy — the MailboxHash concept is explained three times (payload table, dedicated section, and notes), the retry table is detailed but could be summarized, and the Notes section repeats points already made in the body. Some trimming would improve token efficiency. | 2 / 3 |
Actionability | Provides a fully executable Express.js endpoint with concrete code, specific payload field names, clear MailboxHash routing examples with actual email addresses, and a practical common mistakes table with specific fixes. The guidance is copy-paste ready. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (configure → set webhook → build endpoint → return 200), with explicit validation guidance (always return 200, what happens with non-200/403 responses), retry behavior documented with specific intervals, and error recovery paths clearly described. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview in the main file and well-signaled one-level-deep references to four separate files (inbound-setup.md, payload-structure.md, handler-examples.md, inbound-api.md) with clear descriptions of what each contains. The main file provides enough context to work with while pointing to detailed references. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ActiveCampaign/postmark-skills
- Commit
73ea6bf
- 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.