CtrlK
BlogDocsLog inGet started
Tessl Logo

cs-aeo

/cs:aeo — Answer Engine Optimization workflow. Audit content for E-E-A-T + structure signals that drive LLM citation (ChatGPT, Perplexity, Claude, Gemini, Mistral). Optimize content in 3 modes (conservative/balanced/aggressive). Track which LLMs cite which pages via local ledger. Industry-aware thresholds (8 industries with YMYL calibration). Distinct from SEO — refuses to optimize one at expense of the other.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/cmd-cs-aeo/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 content is highly actionable with concrete executable commands and a clearly sequenced workflow, organized into clean sections. Its main weakness is the absence of an explicit post-optimization validation/re-audit feedback loop.

Suggestions

Add an explicit validation step after optimize — e.g., re-run the audit on the optimized variant to confirm the composite score meets the industry threshold before publish — to close the workflow validation gap.

Consider moving the industry threshold table and anti-pattern catalog into a references file (with a short summary inline) to push progressive disclosure toward the ideal one-level-deep structure now that the skill exceeds 50 lines.

DimensionReasoningScore

Conciseness

The body is mostly lean — tables, concrete commands, and terse rationale columns — and does not over-explain concepts Claude already knows, but a few narrative lines like 'The cs-aeo agent will surface this and recommend running both' could be trimmed, placing it just below the fully-lean anchor.

4 / 5

Actionability

It provides copy-paste-ready CLI examples for every action (audit/optimize/track/report/export) and a five-phase workflow with concrete python3 script invocations and real argument flags, matching the fully-executable anchor.

5 / 5

Workflow Clarity

The audit → optimize → publish → track → report sequence is explicitly phased with an 'if audit < industry threshold' gate and a manual review-before-deploy checkpoint, but it lacks an explicit validate/re-audit step after optimization, leaving a minor validation gap.

4 / 5

Progressive Disclosure

The file is organized into clear, well-labeled sections with one-level-deep references in a Related block (agent, skill, companion, source), but no bundle files exist and some inlineable detail (industry thresholds, anti-patterns) is not split out, keeping it just below the ideal anchor.

4 / 5

Total

17

/

20

Passed

Description

71%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 is specific and well-differentiated with strong natural trigger terms, but it lacks an explicit 'Use when' clause, capping its completeness. Third-person voice is used correctly throughout, incurring no voice penalty.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when optimizing content to be cited by ChatGPT, Perplexity, or other LLMs') to lift completeness above 3.

Include a natural-language synonym a user might actually say, such as 'get cited by AI' or 'AI search optimization', to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Audit content for E-E-A-T + structure signals', 'Optimize content in 3 modes (conservative/balanced/aggressive)', 'Track which LLMs cite which pages via local ledger' — giving comprehensive coverage of capabilities, matching the score-5 anchor.

5 / 5

Completeness

The 'what' is clearly stated (audit, optimize, track, industry-aware thresholds), but there is no explicit 'Use when...' or equivalent trigger guidance; the distinct-from-SEO line is a boundary statement, not a when-to-use clause, so completeness is capped at 3 per the guideline.

3 / 5

Trigger Term Quality

Natural terms like 'AEO', 'Answer Engine Optimization', 'LLM citation', and the named LLMs (ChatGPT, Perplexity, Claude, Gemini, Mistral) give good coverage, but common user phrasings such as 'get cited by AI' or 'AI search optimization' are missing, so it sits below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (LLM citation vs search ranking) and explicitly states 'Distinct from SEO — refuses to optimize one at expense of the other', leaving only minor overlap risk with the closely related SEO-audit skill rather than minimal conflict risk.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing, 2 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
alirezarezvani/claude-skills
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.