aeo

Check and improve your brand's visibility across AI search engines (ChatGPT, Perplexity, Gemini, Grok, Claude, DeepSeek). Set up tracking, run visibility analyses, audit your website for AI readability, and get actionable recommendations. Uses the npx goose-aeo@latest CLI.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/seo/capabilities/aeo/SKILL.md

Quality

Content

88%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.

The skill body is a strong operational guide: routing logic, exact CLI invocations, cost gates with user confirmation, and an error-recovery section make it fully executable. Its only real weaknesses are mild conversational padding and a monolithic single-file structure that could move per-workflow detail into reference files.

Suggestions

Trim conversational filler (e.g. 'Have a natural conversation with the user to gather what's needed') and compress the six audit-dimension glosses into a compact table.

Consider splitting long per-workflow detail (Setup, Website Audit, Recommendations) into references/ files with one-level-deep links from the routing overview in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is dominated by executable commands, a routing table, and terse bullets with little padding; minor conversational overhead ('Have a natural conversation with the user', the one-line glosses on each audit dimension) keeps it just below the 'lean and efficient' anchor.	4 / 5
Actionability	Every workflow gives copy-paste-ready commands with full flags (e.g. 'npx goose-aeo@latest init --domain <domain> --name ... --json', 'run --dry-run --json', 'run --confirm --json'), a working env-var probe script, and concrete next-step options, covering all common cases.	5 / 5
Workflow Clarity	The state-based routing table plus each workflow's pre-flight → dry-run cost estimate → explicit user confirmation → execute → analyze → report sequence provides explicit validation checkpoints, and the Error Handling section supplies feedback loops for recovery (partial failures, missing keys, empty audits).	5 / 5
Progressive Disclosure	Well-organized single file with clear section headers, routing, and no nested references, and the inline content is mostly workflow guidance that belongs in SKILL.md; however at ~270 lines with all four workflows fully inlined and no external reference files, the audit-dimension and recommendation details could be split out.	4 / 5
	Total	18 / 20 Passed

Description

61%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.

The description clearly communicates a distinct domain (AI search visibility across named engines) with four concrete capabilities, but it never tells Claude when to invoke it and is written in second-person voice. Adding an explicit 'Use when...' clause would address the biggest gap.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about brand visibility in ChatGPT/Perplexity/Gemini, AI search rankings, or AI readability of their site.'

Rewrite in third person to avoid the second-person penalty: 'Checks and improves a brand's visibility...' instead of 'your brand's visibility'.

Include common synonyms users actually say — 'AI SEO', 'GEO (generative engine optimization)', 'answer engine' — to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Set up tracking, run visibility analyses, audit your website for AI readability, and get actionable recommendations') which fits the anchor 4 example, but 'Check and improve your brand's visibility' uses second-person voice, which the guidelines penalize by reducing specificity by 1.	3 / 5
Completeness	The 'what' is clear (tracking, visibility analyses, website audit, recommendations) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the guidelines state should cap completeness at 3.	3 / 5
Trigger Term Quality	Good natural keyword coverage — 'AI search engines', 'ChatGPT, Perplexity, Gemini, Grok, Claude, DeepSeek', 'visibility', 'audit your website', 'AI readability', 'tracking' — but misses common synonyms users would say like 'AI SEO', 'GEO', or 'answer engine'.	4 / 5
Distinctiveness Conflict Risk	Naming six specific AI engines and the goose-aeo CLI carves a distinct niche with clear triggers; only minor overlap risk with generic SEO skills, so it sits above 'somewhat specific' but below fully minimal conflict.	4 / 5
	Total	14 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/seo/capabilities/aeo/SKILL.md
Commit: cc3e518

Reviewed: 7 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.