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 copy-paste CLI commands and a well-structured connection workflow including validation checkpoints. Its main weaknesses are an unnecessary introductory explanation of what Semrush is and broken step cross-references (Step 2 / 1a).
Suggestions
Remove or trim the intro paragraph explaining what Semrush is and editorial asides like "so you can focus on the integration logic rather than auth plumbing" — Claude already knows the product.
Fix the broken cross-references: label an explicit 'Step 1'/'Step 2' sequence (or rename the '1b' heading) so 'skip to Step 2' resolves to a real section.
De-duplicate the action-discovery command, which appears in both 'Searching for actions' and 'Popular actions'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient command-focused content, but the intro paragraph explains what Semrush is (a concept Claude already knows), adds editorializing like "so you can focus on the integration logic rather than auth plumbing", and repeats the action-list command across two sections. | 3 / 5 |
Actionability | Fully executable, copy-paste ready commands cover the common cases — install, login, connection ensure, action list/run with JSON input, and proxy requests with a complete flags table. | 5 / 5 |
Workflow Clarity | The connection sequence has explicit state checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a poll-again feedback loop, but cross-references are broken — "skip to Step 2" with no labeled Step 2 and a "1b" heading with no "1a". | 4 / 5 |
Progressive Disclosure | No bundle files exist and the 146-line body is a single file with well-organized sections and no nested references; content is appropriately placed with only minor opportunities to split detail (e.g. clientAction state handling) into references. | 4 / 5 |
Total | 16 / 20 Passed |