agentleFS
6t9xstar6t9xstar/one-step-seo/skills/answer-engine-optimization/SKILL.md

answer-engine-optimization

Skill5 starsChanged 35 days agoMITView on GitHub

Optimize content structure for featured snippets, Google AI Overviews, Perplexity, and ChatGPT Search with direct answer capsules, question H2s, labeled comparison tables, quantified facts, and FAQ parity.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 0 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Ensure snippet controls (G09-snippet-controls P2) do not block passage extraction.

    line 14
  2. Very specific:

    Ensure neither <meta name="robots"> nor X-Robots-Tag contains nosnippet or max-snippet:0 (G09-snippet-controls P2), which blocks both …

    line 28
  3. Very specific:

    Add ordered <ol> step lists for procedural "How-to" queries and semantic <table> grids with explicit <th> column headers (C03-extractable …

    line 34
  4. Very specific:

    Add 3–6 genuine user questions and concise answers on-page (C04-faq), and keep <script type="application/ld+json"> FAQPage nodes 1:1 …

    line 36
  5. Very specific:

    Never invent statistics, benchmarks, or citations: When remediating G03-facts or G08-stat-density, extract real numbers already stated on …

    line 69
  6. Very specific:

    Never add FAQPage JSON-LD for questions that are hidden or absent from the visible page (S03-faq-parity).

    line 70

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

answer-engine-optimization — Answer Engine & Featured Snippet Optimization (AEO)

1. Description & Activation Criteria

Activate answer-engine-optimization when the user wants to:

  • Win featured snippets, "People Also Ask" (PAA) expansions, Google AI Overviews, Perplexity citations, and ChatGPT Search passages.
  • Structure prose into high-signal answer capsules (C02-answer P1), extractable lists/tables (C03-extractable P2, C05-table-headers P3), natural question headings (G07-question-headings P3), quantified facts (G03-facts P2, G08-stat-density P3), and synchronized visible + JSON-LD FAQs (C04-faq P1/P2, S03-faq-parity P3).
  • Ensure snippet controls (G09-snippet-controls P2) do not block passage extraction.

2. Inputs & Prerequisites

  • Target: Informational guides, documentation pages (--profile docs), comparison articles, or landing pages (live URL or local HTML).
  • Key CLI filters:
    • --skills answer-engine-optimization (alias: aeo, featured-snippets).
    • --profile docs: Elevates C04-faq and G01-llms to P1 for documentation hubs where Q&A retrieval is primary.

3. Step-by-Step Workflow

  1. Run an AEO-focused audit:
    • Execute npx one-step-seo page <url> --skills answer-engine-optimization --out ./seo-report and npx one-step-seo ai <url> --json.
  2. Verify snippet eligibility (G09-snippet-controls):
    • Ensure neither <meta name="robots"> nor X-Robots-Tag contains nosnippet or max-snippet:0 (G09-snippet-controls P2), which blocks both classic featured snippets and AI Overview passage quoting. Use data-nosnippet selectively on cookie banners or nav chrome instead.
  3. Craft the 40–60 word Answer-First Capsule (C02-answer):
    • Worth 25/100 points on the AI Visibility score (GEO_WEIGHTS).
    • Within the first ~120 words of body copy, pose the core user question (What/Why/How/When/Where/Which/Who ...?) or a TL;DR: / In short: lead-in followed immediately by a self-contained 40–60 word factual definition or direct answer.
  4. Convert walls of prose into extractable structures (C03-extractable, C05-table-headers, G07-question-headings):
    • Phrase at least half of <h2> headings (on pages with 3+ H2s) as real user questions (G07-question-headings P3).
    • Add ordered <ol> step lists for procedural "How-to" queries and semantic <table> grids with explicit <th> column headers (C03-extractable P2, C05-table-headers P3) for comparisons, specs, and pricing.
  5. Synchronize visible FAQs with FAQPage JSON-LD (C04-faq, S03-faq-parity):
    • Add 3–6 genuine user questions and concise answers on-page (C04-faq), and keep <script type="application/ld+json"> FAQPage nodes 1:1 synchronized with visible copy (S03-faq-parity P3).

4. Tools & CLI Commands

# Audit answer-engine and snippet signals on a guide or docs page
npx one-step-seo page https://example.com/guides/what-is-rag --skills aeo --out ./seo-report

# Audit documentation pages with docs profile calibration
npx one-step-seo audit https://example.com/docs --pages 15 --profile docs --skills answer-engine-optimization --out ./seo-report

# Generate a starter FAQPage JSON-LD block to pair with visible FAQ copy
npx one-step-seo schema https://example.com/guides/what-is-rag --generate faq

5. Evidence Requirements

  • Report both report.scores.ai.score (report.scores.ai.band) and report.scores.search.score (report.scores.search.band) separately.
  • Quote C02-answer, C03-extractable, C04-faq, C05-table-headers, G03-facts, G07-question-headings, G08-stat-density, G09-snippet-controls, and S03-faq-parity evidence strings from report.findings.

6. Expected Outputs

  1. AEO Readiness Breakdown: Status of snippet eligibility, answer capsule, question H2 ratio, table header hygiene, stat density, and FAQ parity.
  2. Answer Capsule & Heading Rewrite: A crisp 40–60 word opening answer block and question-shaped H2 outline derived strictly from existing page facts.
  3. Synchronized FAQ HTML + JSON-LD: Matching <section> FAQ markup and FAQPage JSON-LD.

7. Limitations & External Data

  • Structural readiness vs SERP volatility: Featured snippets and AI Overviews depend on live query intent and search index competition; one-step-seo verifies deterministic structural extractability, never guaranteed SERP placement.
  • Offline support: 100% supported on local Markdown-rendered HTML and static builds (--offline).

8. Safety & Approval Rules

  • Never invent statistics, benchmarks, or citations: When remediating G03-facts or G08-stat-density, extract real numbers already stated on the page or use explicit [TODO: insert verified metric + source] markers.
  • Never add FAQPage JSON-LD for questions that are hidden or absent from the visible page (S03-faq-parity).

9. Examples

# Inspect the answer-engine-optimization skill checks and aliases
npx one-step-seo skills answer-engine-optimization

# Run an offline AEO audit on built documentation HTML
npx one-step-seo audit ./dist/docs --pages 10 --profile docs --skills aeo --offline --out ./seo-report

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.