seo-audit

When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," or "SEO health check." For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup.

1.06x

Quality

62%

Does it follow best practices?

Impact

88%

1.06x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/seo-audit/SKILL.md

Quality

Discovery

89%

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 with excellent trigger term coverage and clear boundary-setting against related skills. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., checking meta tags, analyzing page speed, reviewing internal links). The cross-references to related skills are a notable strength for disambiguation.

Suggestions

Add more specific concrete actions to the 'what' portion, e.g., 'Audits meta tags, checks page speed, reviews internal linking, analyzes crawlability, and identifies on-page SEO issues.'

Dimension	Reasoning	Score
Specificity	The description names the domain (SEO) and some actions ('audit, review, or diagnose SEO issues'), but does not list multiple specific concrete actions like checking meta tags, analyzing page speed, reviewing crawlability, etc. The actions remain somewhat high-level.	2 / 3
Completeness	Clearly answers both 'what' (audit, review, diagnose SEO issues) and 'when' (explicit 'Use when' equivalent with detailed trigger terms). It also helpfully distinguishes from related skills (programmatic-seo, schema-markup), adding clarity on boundaries.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'SEO audit,' 'technical SEO,' 'why am I not ranking,' 'SEO issues,' 'on-page SEO,' 'meta tags review,' 'SEO health check.' The phrase 'why am I not ranking' is particularly good as a natural user query.	3 / 3
Distinctiveness Conflict Risk	The description explicitly differentiates itself from related skills (programmatic-seo for building pages at scale, schema-markup for structured data), creating a clear niche around SEO auditing and diagnostics with distinct triggers unlikely to conflict.	3 / 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 audit textbook than an efficient instruction set for Claude. It contains extensive domain knowledge that Claude already possesses (E-E-A-T definitions, Core Web Vitals thresholds, basic meta tag best practices), making it highly token-inefficient. The structure and output format are reasonable, but the skill would benefit enormously from being condensed to project-specific conventions and non-obvious guidance, with detailed checklists moved to reference files.

Suggestions

Reduce the body to ~50-80 lines focusing on: the initial assessment flow, the priority order framework, the output format template, and references to detailed checklists in separate files. Move the Technical SEO, On-Page SEO, Content Quality, and Site Type checklists to reference files.

Add a concrete example of a completed audit finding (with Issue/Impact/Evidence/Fix filled in) so Claude knows exactly what the expected output looks like.

Remove explanations of standard SEO concepts Claude already knows (E-E-A-T definitions, what Core Web Vitals are, meta description character limits) and instead focus on project-specific conventions or non-obvious decision criteria.

Add specific actionable commands or code snippets for checks Claude can actually perform (e.g., how to parse robots.txt, how to check for canonical tags in HTML, regex patterns for common issues) rather than just listing what to check.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~300+ lines, largely consisting of checklist items that Claude already knows as an SEO expert. Sections like 'what is E-E-A-T,' Core Web Vitals thresholds, meta description character counts, and basic concepts like 'HTTPS across entire site' are standard SEO knowledge that don't need to be spelled out. The 'Common Issues by Site Type' section alone is a wall of bullet points Claude could generate on its own.	1 / 3
Actionability	The skill provides structured checklists and a clear output format, which gives some concrete guidance on what to check and how to report findings. However, there are no executable code snippets, no specific commands to run, no example audit output, and many items are just labels ('Check for: Descriptive file names') rather than instructions on how to actually perform the check.	2 / 3
Workflow Clarity	There is a clear priority order (Crawlability → Technical → On-Page → Content → Authority) and the audit report structure provides a reasonable output workflow. However, there are no validation checkpoints, no feedback loops for when issues are found, and no clear decision points for when to go deeper vs. move on. The initial assessment questions are good but the transition from assessment to audit execution is implicit.	2 / 3
Progressive Disclosure	The skill references two external files (ai-writing-detection.md and aeo-geo-patterns.md) and links to related skills, which is good. However, the massive amount of inline content (all the checklists for technical SEO, on-page SEO, content quality, site-type issues) should be split into separate reference files rather than being included in the main SKILL.md. The file is a monolithic wall of checklists.	2 / 3
	Total	7 / 12 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: tibelf/ai_project_init
Commit: 56f4516

Reviewed: about 2 months ago

Table of Contents

Discovery Implementation Validation

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.