Content
75%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is highly actionable with executable commands and a well-structured connection state-machine, but carries a little product-explanation padding and a couple of placeholder guidance lines that could be tightened.
Suggestions
Cut the intro paragraph explaining what Postmaster Tools is and who uses it — Claude can infer this — and remove the empty "When to use which actions" line.
Either replace "When to use which actions: Use action names and parameters as needed." with concrete guidance mapping intents (e.g. reputation checks, traffic stats) to specific actions, or delete it.
Consider moving the full proxy flag reference table into a separate reference file and keeping only a one-line pointer, to slim the overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient command-based guidance, but the product-purpose intro ("used by email senders, marketers... This helps ensure their emails reach Gmail inboxes") and filler like "When to use which actions: Use action names and parameters as needed." could be trimmed. | 3 / 5 |
Actionability | Concrete, copy-paste-ready commands throughout ("npm install -g @membranehq/cli@latest", "membrane connection ensure ...", "membrane action run ... --input '{...}'") with full flag tables and JSON examples covering the common cases. | 5 / 5 |
Workflow Clarity | A clear install → authenticate → connect → poll-for-ready → search → run sequence exists with explicit state polling (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR), but "When to use which actions: Use action names and parameters as needed." leaves a minor guidance gap. | 4 / 5 |
Progressive Disclosure | Well-organized with clear section headers and no broken or nested references, all self-contained in SKILL.md; at ~140 lines it exceeds the simple-skill threshold, so it earns good-but-not-perfect structure rather than a 5. | 4 / 5 |
Total | 16 / 20 Passed |