improve-aeo-geo

Audits a website codebase and makes code changes so AI engines (ChatGPT, Claude, Perplexity, Google AI Overviews) can better discover, parse, quote, and cite the site. Covers structured data, content structure, technical signals, and freshness.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./improve-aeo-geo/SKILL.md

Quality

Content

77%

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

The skill body is highly actionable with extensive executable code and a clear, validated workflow, but it is over-long for a single file. It would benefit from offloading framework-specific patterns and research citations into reference files and trimming conceptual preamble.

Suggestions

Move the framework-specific patterns section (Next.js through Remix) into one or more reference files (e.g. references/framework-patterns.md), keeping only a concise index in SKILL.md.

Trim the conceptual preamble ('The web is shifting...') and condense the inline research citations / references table to only the actionable thresholds.

Consider moving the research references table to a reference file so the main body stays a lean overview pointing to detailed evidence.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and actionable, but includes unnecessary preamble ('The web is shifting from human-first to AI-first discovery. AI agents don't browse like humans...') and heavy inline research-citation baggage plus a full references table that compete with the context window. Not level 3 because of this padding, and not level 1 because the core is domain-specific actionable guidance rather than explanations of concepts Claude already knows.	2 / 3
Actionability	Provides fully executable, copy-paste-ready code across eight frameworks (Next.js, Nuxt, SvelteKit, Astro, WordPress, Hugo, Jekyll/11ty, Remix) plus templates for robots.txt, llms.txt, and JSON-LD, with specific numeric thresholds. Not level 2 because the examples are complete and executable rather than pseudocode.	3 / 3
Workflow Clarity	Defines a clear five-step sequence (Baseline, Discover, Audit, Fix, Verify) with an explicit validation checkpoint in Step 5 ('Re-run the audit and compare against the Step 1 baseline') and a verification checklist. Not level 2 because validation/feedback is explicit rather than implicit.	3 / 3
Progressive Disclosure	Sections are well-organized, but the file is a monolithic ~560 lines with the ~225-line framework-specific patterns block and research references inlined rather than split into reference files; no bundle files exist. Not level 3 because substantial content that should be separate is inline, and not level 1 because organization is clear with no nested references.	2 / 3
	Total	10 / 12 Passed

Description

82%

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

The description is specific, actionable, and distinctive, naming concrete coverage areas and the AI engines it targets. Its main weakness is the absence of an explicit 'Use when...' trigger clause, leaving the invocation conditions implied rather than stated.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants their website cited or quoted by AI engines like ChatGPT, Claude, Perplexity, or Google AI Overviews.'

Include natural umbrella terms users say ('AI search', 'AI Overviews', 'AI SEO', 'AEO/GEO') alongside the named engines to broaden trigger coverage.

Consider adding one concrete example action verb (e.g. 'adds JSON-LD schema, llms.txt, and AI-bot robots rules') to make the actions even more tangible.

Dimension	Reasoning	Score
Specificity	Lists concrete actions ('Audits a website codebase and makes code changes') and names specific coverage areas ('structured data, content structure, technical signals, and freshness'). Not level 2 because it goes beyond naming a domain to enumerate multiple concrete actions and sub-domains.	3 / 3
Completeness	Clearly states what the skill does but provides no explicit 'Use when...' trigger clause, so the 'when' is only implied; per guidelines a missing explicit trigger caps completeness at 2. Not level 3 because there is no explicit when-trigger, and not level 1 because the 'what' is clearly and specifically stated.	2 / 3
Trigger Term Quality	Includes natural terms users would say — 'ChatGPT, Claude, Perplexity, Google AI Overviews' and 'website codebase' — giving good coverage of how users refer to AI discovery. Not level 2 because the named engines are exactly the trigger phrases a user would voice.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear AEO/GEO niche targeting AI engine citation, making it unlikely to trigger for unrelated skills. Not level 2 because the named AI engines and citation focus distinguish it from generic SEO/audit skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (561 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: onvoyage-ai/gtm-engineer-skills
Path: improve-aeo-geo/SKILL.md
Commit: 3777930

Reviewed: about 18 hours 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.