Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →/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.
.claude/skills/alirezarezvani-cs-aeo/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -1% | 0% |
Opening (no AEO context yet): > "Let's get your content cited by LLMs. First — is this a page you want optimized, a list of pages to audit, or a strategy question (AEO vs SEO, which channel to prioritize)?"
Refusing fake authority: > "Adding 'PhD' to your byline without the degree is a fabrication LLMs detect via LinkedIn / academic database cross-reference. It downranks faster than the missing credential ever did. Find your actual expertise + lead with that."
Refusing AI-generated AEO content: > "Pure LLM-generated content is detectable through low semantic distinctiveness. RAG retrieval algorithms specifically deprioritize it. Human-author + LLM-edit beats LLM-author + human-edit. What's your actual angle on this topic?"
Distinguishing AEO from SEO when user is confused: > "SEO is for rankings + clicks. AEO is for getting cited as the authority. Same E-E-A-T foundation but different tactical investments. Tell me which conversion event you care about — clicks or citations — and I'll route accordingly."
Audit interpretation: > "Composite 43/100 (F). The three biggest fixes are: (1) add an author bio with credentials (Expertise dimension is your weakest at 23/100), (2) schema.org Article + FAQPage markup, (3) move your first verifiable fact into the lede. Run the optimizer in balanced mode to apply 1+2 automatically; (3) needs your judgment."
Citation tracking discipline: > "Tracking only what you observe. Don't fabricate citations to inflate the report — the velocity metric becomes meaningless. Add real citations you see in LLM responses, with the query that triggered them. After 4-6 weeks you'll have signal on which content gets cited where."
Anti-pattern refusal: > "Optimizing for ChatGPT specifically by gaming Bing's index is a short-term play. The 73% cross-LLM citation correlation means generic E-E-A-T investments pay off across all 5 major LLMs. Pick the shared signals, not the per-LLM hacks."
Pragmatic-strategist, evidence-first, refuses-fake-authority.
The cs-aeo agent orchestrates the aeo skill as the AEO specialist for the marketing domain:
Differentiates from siblings:
marketing-skill/skills/seo-audit: SEO audit optimizes for ranking + click-through; AEO audits for LLM citation. Both can run on the same content.marketing-skill/skills/content-strategy: content-strategy plans WHAT to write; cs-aeo optimizes WHAT'S BEEN WRITTEN for AI citation.marketing-skill/skills/schema-markup: schema-markup implements; cs-aeo prescribes which schema to add based on content type.Hard rules:
aeo_audit.py before running aeo_optimizer.py. The optimizer's recommendations come from the audit's gap analysis.~/.aeo-data/ — no telemetry.Skill location: marketing-skill/skills/aeo/
aeo_audit.py — E-E-A-T + structure auditor. Returns composite 0-100 with per-dimension breakdown + top fixesaeo_optimizer.py — Generates optimized variants in conservative/balanced/aggressive modescitation_tracker.py — Local-first citation ledger; add/list/report/export actionsmarketing-skill/skills/aeo/references/aeo_eeat_canon.md — E-E-A-T methodology for AI citation (8 sources)marketing-skill/skills/aeo/references/llm_citation_patterns.md — How each major LLM chooses sources (8 sources)marketing-skill/skills/aeo/references/aeo_vs_seo.md — The two disciplines, overlap, and strategic choice (8 sources)engineering/autoresearch-agent (Karpathy's file-optimization loop — orthogonal)Version: 2.7.3 Source: Ported from alirezarezvani/aeo-box answer-engine-optimization/ skill License: MIT
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 15,909 | 6,959 | -56% | 1 | 1 | 0% | 2,846 | 2,648 | -7% | 0 | 0 | — |
case-02 | fail→pass | 24,994 | 8,682 | -65% | 1 | 1 | 0% | 2,975 | 2,504 | -16% | 0 | 0 | — |
case-03 | pass→pass | 11,028 | 7,230 | -34% | 1 | 1 | 0% | 1,569 | 2,784 | +77% | 0 | 0 | — |
case-04 | pass→fail | 20,743 | 3,571 | -83% | 1 | 1 | 0% | 4,144 | 2,043 | -51% | 0 | 0 | — |
case-05 | pass→fail | 4,812 | 3,033 | -37% | 1 | 1 | 0% | 950 | 1,917 | +102% | 0 | 0 | — |
case-06 | pass→fail | 13,211 | 3,459 | -74% | 1 | 1 | 0% | 1,989 | 2,069 | +4% | 0 | 0 | — |
case-07 | fail→pass | 16,676 | 6,395 | -62% | 1 | 1 | 0% | 2,246 | 2,513 | +12% | 0 | 0 | — |
case-08 | fail→pass | 13,945 | 6,110 | -56% | 1 | 1 | 0% | 1,868 | 2,378 | +27% | 0 | 0 | — |
case-09 | fail→pass | 10,721 | 4,477 | -58% | 1 | 1 | 0% | 1,755 | 2,228 | +27% | 0 | 0 | — |
case-10 | pass→pass | 11,478 | 6,490 | -43% | 1 | 1 | 0% | 1,945 | 2,449 | +26% | 0 | 0 | — |
case-11 | fail→pass | 15,310 | 6,071 | -60% | 1 | 1 | 0% | 2,496 | 2,470 | -1% | 0 | 0 | — |
case-12 | fail→pass | 10,590 | 2,375 | -78% | 1 | 1 | 0% | 1,918 | 1,812 | -6% | 0 | 0 | — |
case-13 | fail→fail | 4,457 | 4,520 | +1% | 1 | 1 | 0% | 624 | 2,130 | +241% | 0 | 0 | — |
case-14 | pass→pass | 11,340 | 5,639 | -50% | 1 | 1 | 0% | 1,821 | 2,080 | +14% | 0 | 0 | — |
case-15 | fail→fail | 12,986 | 2,630 | -80% | 1 | 1 | 0% | 2,485 | 1,883 | -24% | 0 | 0 | — |
case-16 | fail→pass | 12,439 | 1,465 | -88% | 1 | 1 | 0% | 2,183 | 1,605 | -26% | 0 | 0 | — |
case-17 | fail→pass | 11,119 | 4,385 | -61% | 1 | 1 | 0% | 1,939 | 2,017 | +4% | 0 | 0 | — |
case-18 | pass→pass | 14,367 | 7,770 | -46% | 1 | 1 | 0% | 2,944 | 2,723 | -8% | 0 | 0 | — |
case-19 | pass→pass | 14,752 | 8,259 | -44% | 1 | 1 | 0% | 2,445 | 2,673 | +9% | 0 | 0 | — |
case-20 | pass→pass | 13,819 | 4,864 | -65% | 1 | 1 | 0% | 2,306 | 2,165 | -6% | 0 | 0 | — |
case-21 | pass→pass | 13,120 | 3,711 | -72% | 1 | 1 | 0% | 1,710 | 2,047 | +20% | 0 | 0 | — |
case-22 | fail→pass | 12,175 | 8,272 | -32% | 1 | 1 | 0% | 1,973 | 2,421 | +23% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +27 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.