Content
62%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 diagnostic framework with excellent workflow clarity and logical layering, but it falls short on actionability by not providing any concrete tool invocations, queries, or executable examples for the specific tools it names (Ahrefs MCP, Search Console). The content is moderately concise but includes some explanations of concepts Claude would already understand. The progressive disclosure is adequate but the main file carries a lot of weight that could be distributed to reference files.
Suggestions
Add concrete Ahrefs MCP tool call examples (e.g., specific function names, parameters, and expected output formats) for key diagnostic steps like checking rank history, SERP composition, and backlink changes.
Add a Search Console API query example or specific data export steps for the cross-check in Layer 1 and the CTR/index analysis in Layer 3.
Move the detailed failure patterns and/or the Layer 2 diagnostic table to a reference file to reduce main file length and improve progressive disclosure.
Trim explanatory content that Claude already knows (e.g., what branded vs non-branded queries are, what seasonality means) to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some content Claude already knows (e.g., explaining what seasonality is, what branded vs non-branded queries are, general SEO concepts). The failure patterns section, while useful, is verbose and some items are common-sense for an AI assistant. The 'When NOT to use' section and 'Required inputs' add useful boundaries but could be tighter. | 2 / 3 |
Actionability | The skill provides a clear diagnostic framework and workflow steps, but lacks concrete executable commands or code. There are no specific Ahrefs MCP tool calls, no Search Console API queries, no example commands to run. The guidance is structured and directional but remains at the level of 'check X' rather than 'run this specific query/command to check X.' For a skill that names specific tools (Ahrefs MCP), the absence of actual tool invocation examples is a notable gap. | 2 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced, logically ordered from confirmation through action. The layered framework (1-5) provides explicit progression with clear stopping criteria ('stop when you have enough evidence'). Step 8 includes a validation checkpoint ('validate the hypothesis') before proceeding to fixes, which is a proper feedback loop for a diagnostic process. The diagnostic table in Layer 2 provides clear pattern-to-cause mapping. | 3 / 3 |
Progressive Disclosure | The skill references one external file (references/diagnosis-checklist.md) which is appropriate for deeper detail, but no bundle files were provided, meaning the reference is unverifiable. The main SKILL.md itself is quite long (~200+ lines) and some content (like the detailed Layer 2 table, the extensive failure patterns list) could potentially be moved to reference files. The structure within the file is good with clear headers, but the single-file density is borderline. | 2 / 3 |
Total | 9 / 12 Passed |