seo-optimizer
SEO optimization with keyword analysis, readability assessment, technical validation, content quality. Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors.
56
63%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/seo-optimizer/skills/seo-optimizer/SKILL.mdQuality
Discovery
92%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates both capabilities and trigger conditions. It lists concrete actions and includes a good variety of natural trigger terms spanning both user-facing language and technical SEO terminology. The main weakness is potential overlap with general content writing or editing skills due to terms like 'blog posts' and 'content quality'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: keyword analysis, readability assessment, technical validation, content quality. These are distinct, identifiable capabilities rather than vague language. | 3 / 3 |
Completeness | Clearly answers both 'what' (SEO optimization with keyword analysis, readability assessment, technical validation, content quality) and 'when' ('Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'search rankings', 'blog posts', 'content audits', 'keyword density', 'readability scores', 'meta tags', 'schema markup'. These cover a good range of terms a user working on SEO would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | While SEO is a fairly specific domain, terms like 'blog posts', 'content quality', and 'readability assessment' could overlap with general writing or content creation skills. The SEO-specific terms (keyword density, meta tags, schema markup) help but the broader terms introduce some conflict risk. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews 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 for a human marketer than a concise, actionable instruction set for Claude. It over-explains well-known SEO concepts, includes decorative rather than executable code, and lacks validation checkpoints in its workflow. The structure attempts progressive disclosure with external references but undermines it by including too much detail inline while the referenced files don't exist.
Suggestions
Cut the content by 50-60%: remove explanations of what meta descriptions, E-A-T, and readability scores are—Claude already knows these. Focus only on the specific targets, thresholds, and report format you want.
Replace the decorative JavaScript snippet with either a concrete analysis algorithm Claude should follow or remove it entirely—it's not executable in context.
Add validation checkpoints to the workflow: e.g., 'After calculating keyword density, verify it falls within 1-2% before proceeding; if not, flag as critical issue' and 'After generating the report, cross-check that all critical issues have specific fix recommendations.'
Move the detailed report template and priority level definitions into the referenced bundle files (references/output-templates.md) and keep only a brief summary in the main SKILL.md to properly implement progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~180+ lines, explaining many concepts Claude already knows (what E-A-T is, what meta descriptions are, basic SEO concepts). The readability metrics JavaScript example is decorative rather than functional. Much of the content is generic SEO knowledge that doesn't add actionable value beyond what Claude already understands. | 1 / 3 |
Actionability | The skill provides structured checklists, target ranges (keyword density 1-2%, Flesch 60-70), and a report template, which gives some concrete guidance. However, there's no executable code for actually performing analysis—the JavaScript snippet is illustrative only, and most guidance is descriptive rather than providing copy-paste-ready implementations or tool commands. | 2 / 3 |
Workflow Clarity | The 'Example Analysis Flow' section provides a 9-step sequence, and priority levels help with ordering. However, there are no validation checkpoints or feedback loops—no step says 'verify your density calculation is correct' or 'if readability score is below threshold, iterate on these specific elements before proceeding.' | 2 / 3 |
Progressive Disclosure | The skill references two external files (references/analysis-framework.md and references/output-templates.md) with clear descriptions of what each contains, which is good structure. However, no bundle files are provided, so these references are broken. Additionally, the main file contains extensive inline content (the full report template, detailed tables) that should arguably live in those referenced files. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- secondsky/claude-skills
- Commit
5e92b71
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.