Content
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a persona description and a table of contents with no actionable content. It tells Claude to be an 'elite software architect' but provides zero concrete guidance on how to actually perform architectural reviews—no evaluation frameworks, no example outputs, no checklists, no specific patterns to apply. The sub-skill references suggest structure but the main file adds almost nothing Claude doesn't already know.
Suggestions
Replace the vague 4-step workflow with a concrete architectural review checklist (e.g., specific questions to ask about coupling, data flow, failure modes, with example outputs for each).
Add at least one concrete example showing an input (e.g., a system design description) and the expected architectural review output format with specific findings, risk ratings, and recommendations.
Remove the 'Expert Purpose' section entirely—it restates the description and adds no actionable information Claude can use.
Add validation steps to the workflow, such as 'Verify the architecture satisfies these quality attributes: [list]' with specific criteria for pass/fail.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is verbose and explains concepts Claude already knows well (SOLID principles, microservices, DDD, clean architecture). The 'Expert Purpose' section largely restates the description. Phrases like 'Elite software architect' and 'Masters modern architecture patterns' are filler that add no actionable value. | 1 / 3 |
Actionability | The instructions are entirely abstract ('Gather system context', 'Evaluate architecture decisions', 'Recommend improvements') with no concrete examples, specific commands, code snippets, checklists, or templates. There is nothing executable or copy-paste ready—it describes rather than instructs. | 1 / 3 |
Workflow Clarity | The four-step workflow is vague and lacks any validation checkpoints, specific criteria for evaluation, or feedback loops. Steps like 'Evaluate architecture decisions and identify risks' provide no guidance on how to actually perform the evaluation or what constitutes a risk. | 1 / 3 |
Progressive Disclosure | The skill does reference 10 sub-skill files with clear one-level-deep links, which is good structure. However, no bundle files were provided to verify these references exist, and the main SKILL.md itself contains very little substantive content—it's mostly a table of contents with no useful overview content to anchor the references. | 2 / 3 |
Total | 5 / 12 Passed |