Content
38%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a comprehensive SEO guide or textbook chapter than a concise, actionable skill for Claude. While it covers the legal local SEO domain thoroughly with good domain-specific details (OAB, Jusbrasil, forensic expert considerations), it is excessively verbose, explains many concepts Claude already knows, and lacks executable actions or tool-based workflows. The encoding issues with special characters (Portuguese text) also suggest quality control problems.
Suggestions
Cut the content by 50-60% by removing explanations of concepts Claude already knows (what YMYL is, what E-E-A-T stands for, basic technical SEO) and keeping only legal-specific guidance that adds unique value.
Split detailed checklists (directory lists, E-E-A-T criteria, technical SEO checks) into separate bundle files and reference them from the main SKILL.md to improve progressive disclosure.
Add concrete, executable examples: a sample audit output snippet, specific tool commands for checking NAP consistency, example schema markup JSON-LD for LegalService, or a template for the audit report.
Fix character encoding issues throughout the document (e.g., 'â€â€Â' appearing instead of dashes, garbled Portuguese characters) to ensure readability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is significantly verbose at ~300+ lines. It explains many concepts Claude already knows (what YMYL means, what E-E-A-T stands for, what NAP consistency is, basic technical SEO concepts like HTTPS and robots.txt). Many sections read like a general SEO guide rather than providing only what Claude wouldn't already know. The 'When to Use' section and extensive context-gathering questions add bulk without proportional value. | 2 / 5 |
Actionability | The skill provides structured checklists and specific items to check, but lacks executable code, concrete commands, or copy-paste ready outputs. It's mostly a checklist of things to look for rather than specific steps to execute. There are no tool invocations, no example API calls, no scripts for checking NAP consistency, and no concrete examples of audit output. The guidance is specific enough to follow but remains at the 'check for X' level rather than 'do X with this command/tool.' | 3 / 5 |
Workflow Clarity | There is a clear priority order (GBP → E-E-A-T → On-Page → Technical → Directories → Content → Reviews) and an output format structure, but there are no validation checkpoints, no feedback loops for error recovery, and no explicit sequencing of when to stop or iterate. The audit report structure at the end provides a good output template but the process of getting there lacks verification steps. | 3 / 5 |
Progressive Disclosure | The entire skill is a monolithic document with no bundle files to support it. Content like the full directory lists (Brazil vs International), detailed E-E-A-T checklists, technical SEO details, and content strategy sections could easily be split into separate reference files. The 'Related Skills' section references other skills but the body itself contains everything inline with no delegation to supporting files. | 2 / 5 |
Total | 10 / 20 Passed |