seo-geo

Audit and improve content for AI Overviews and answer engines, including citability, entity clarity, crawler access, brand signals, and passage structure.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/seo-geo/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, information-rich audit skill with strong actionability (output template, real commands, error handling) whose main weaknesses are repetition of its own key points, a never-explicitly-sequenced audit workflow, and a monolithic body that inlines material better split into its existing references/ pattern. The skill is functional but would improve from restructuring rather than from new content.

Suggestions

State the audit as an explicit ordered workflow (e.g., 1. fetch URL and robots.txt, 2. score the five criteria, 3. check the update ledger via the script, 4. generate GEO-ANALYSIS.md) so the sequence and checkpoints are visible rather than implied.

Move the full crawler table, the claim/bot matrix, and the llms.txt format spec into a references/ file (e.g., references/ai-crawlers.md) and keep only the recommendation and the routinely-conflated pairs in SKILL.md, mirroring the existing google-ai-optimization-guide.md pattern.

Deduplicate the training-vs-search crawler distinction and the llms.txt carries-no-weight note, which each appear three times; state each once in the crawler section and once in the output requirements.

Dimension	Reasoning	Score
Conciseness	The body is mostly high-value domain data Claude cannot be assumed to know (dated statistics, crawler capability matrices), but key points are repeated: the GPTBot/OAI-SearchBot training-vs-search distinction is explained in the crawler table, again in the claim/bot table, and again in bullets; the llms.txt 'carries no weight' point appears three times. This repetition goes beyond 'minor instances that could be trimmed', placing it below the 4 anchor.	3 / 5
Actionability	Concrete, executable guidance throughout: a numbered GEO-ANALYSIS.md output template, a runnable command ('scripts/claude-seo run seo_updates.py --kind product --kind core --json'), a ready-to-use llms.txt template, and an error-handling table with specific actions per failure. Not a 5 because several checks (SSR/JavaScript dependency analysis, brand mention analysis) name what to check without giving a concrete command or method for doing it.	4 / 5
Workflow Clarity	The audit criteria, weighted scoring breakdown, output checklist, and error-handling paths imply a workflow, but the actual sequence (fetch URL, retrieve robots.txt, apply the five criteria, run the update ledger, generate the report) is never explicitly ordered. Not a 4 because checkpoints like 'treat a stale ledger as incomplete' exist but the step sequence itself remains implicit rather than listed.	3 / 5
Progressive Disclosure	The two references (google-ai-optimization-guide.md, llmstxt-evidence.md) are real files, clearly signaled, and one level deep, but the ~400-line body inlines large blocks that belong in separate reference files: the full 15-row crawler table, the llms.txt format specification, and the platform-specific optimization tables. Not a 4 because this inline bulk is more than a 'minor organization gap'.	3 / 5
	Total	13 / 20 Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description with good natural keywords and a distinct AI-search-audit niche. Its main deficiency is the absence of any explicit 'when to use' trigger guidance, which both caps completeness and slightly raises conflict risk with general content/SEO requests.

Suggestions

Append a trigger clause such as 'Use when the user asks about AI Overviews, AI search visibility, GEO/generative engine optimization, or why a site is or is not cited by ChatGPT, Perplexity, or Google AI features.'

Add the synonyms users actually say — GEO, generative engine optimization, AI search optimization, LLM visibility — to strengthen trigger term coverage.

Dimension	Reasoning	Score
Specificity	'Audit and improve content for AI Overviews and answer engines, including citability, entity clarity, crawler access, brand signals, and passage structure' enumerates five concrete capability areas, matching the 4 anchor's 'several specific actions; minor gaps'. Not a 5 because the only verbs are the generic 'audit and improve' while the anchor example shows multiple distinct concrete actions.	4 / 5
Completeness	The 'what' is clear and specific (audit and improve content for AI Overviews and answer engines across five named dimensions), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric guidelines cap at 3. The 'when' is only weakly implied by the domain nouns.	3 / 5
Trigger Term Quality	'AI Overviews', 'answer engines', 'crawler access', and 'citability' are terms users of this skill would naturally say, giving good keyword coverage. Not a 5 because common variations users actually type are missing: 'GEO', 'generative engine optimization', 'AI search optimization', 'AI search visibility', 'LLM visibility'.	4 / 5
Distinctiveness Conflict Risk	The AI Overviews / answer-engine audit niche with named facets (citability, passage structure) is mostly distinct with only minor overlap risk against generic SEO or content-audit skills. Not a 5 because 'audit and improve content' could still surface for plain content-quality requests absent a trigger clause.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: AgriciDaniel/claude-seo
Path: skills/seo-geo/SKILL.md
Commit: 4b99de2

Reviewed: 3 days 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.