aicraftbook/aicraftbook-skills / skills/answer-ready
answer-ready
VerifiedAudits one web page's content for how well people, search engines and AI answer engines (Google AI Overviews and AI Mode, Bing Copilot, ChatGPT search, Perplexity) can understand and quote it. Checks the answer-first opening, question-style headings, self-contained sections, unsourced claims, dates and authorship, and unclear entities, then returns prioritised fixes and rewritten passages that keep every fact. Use when someone asks to make a page "AI search ready", optimise it for AI Overviews, GEO or AEO, improve how quotable or citable it is, or review a page's structure for search. Makes no ranking or citation promises.
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 903 B |
| LICENSE | other | 1.0 KB |
| README.md | markdown | 10.1 KB |
| SKILL.md | skill md | 5.1 KB |
| evals/independent-2026-10-21.json | config | 66.9 KB |
| evals/results-2026-10-22.json | config | 5.2 KB |
| evals/tasks.json | config | 8.4 KB |
| examples/requests.md | markdown | 1.1 KB |
| references/checklist.md | markdown | 5.6 KB |
| references/guidance.md | markdown | 5.3 KB |
| references/rewrites.md | markdown | 3.6 KB |
| skill.json | config | 1.3 KB |
references/guidance.md
View on GitHub# Official guidance this skill relies on
Checked on 2026-10-21. Search engines change their guidance; if a source below says something different
today, the source wins. Cite these by name in the Basis column. Anything not covered here is
**Judgement**. No OpenAI or Perplexity guidance is used; fixes for them are Judgement.
## G1. Google: Creating helpful, reliable, people-first content
https://developers.google.com/search/docs/fundamentals/creating-helpful-content (page last updated 2026-10-05)
- Self-assessment questions ask whether content is original and complete, whether the title and main
heading give a descriptive, helpful summary rather than an exaggerated one, and whether the page makes
trustworthiness clear through sourcing, evidence of expertise, and information about the author or
publisher. Easily verified factual errors are a warning sign.
- "Who, How, and Why": make it clear who created the content, with accurate bylines where readers expect
them, linked to author background. Explain how content was produced, including automation or AI where
readers would reasonably wonder. Fabricated authors or credentials are deceptive.
- Trust is the most important part of E-E-A-T (experience, expertise, authoritativeness,
trustworthiness). E-E-A-T is not itself a ranking factor. Topics that affect health, financial
stability, safety or society ("YMYL") get more weight on these signals.
- Do not change a page's date to look fresh when the content has not substantially changed. Google has no
preferred word count.
## G2. Google: AI features and your website
https://developers.google.com/search/docs/appearance/ai-features (page last updated 2025-12-10)
- "There are no additional requirements to appear in AI Overviews or AI Mode, nor other special
optimizations necessary." No special files or schema.org markup are needed.
- A page must be indexed and eligible to be shown with a snippet. Meeting the requirements does not
guarantee it will be shown.
- Practices listed: allow crawling, internal links, good page experience, important content in text form,
supporting images and video where relevant, structured data that matches the visible text.
- Controls: `nosnippet`, `data-nosnippet`, `max-snippet` and `noindex` limit or block use in these
features.
## G3. Google: General structured data guidelines
https://developers.google.com/search/docs/appearance/structured-data/sd-policies (page last updated 2026-07-10)
- Do not mark up content that is not visible to readers. Structured data must be a true representation
of the page content. Do not mark up irrelevant or misleading content.
- Use the most specific applicable schema.org type. Put markup on the page it describes.
- Google does not guarantee that structured data produces a rich result.
## G4. Google: byline dates and Article markup
- Byline dates: https://developers.google.com/search/docs/appearance/publication-dates (last updated
2025-12-10). Show a visible date labelled, for example, "Published" or "Last updated". Use
`datePublished` and `dateModified` in Article-type markup. Keep visible and structured dates
consistent. Dates describe the page, not events in it.
- Article markup: https://developers.google.com/search/docs/appearance/structured-data/article (last
updated 2026-09-08). No required properties. Include every author shown on the page; `author.name`
holds only the name; add `url` or `sameAs`; use `Person` or `Organization`; ISO 8601 dates with a
timezone.
## G5. Google: FAQ and HowTo rich results
https://developers.google.com/search/updates
- HowTo rich results were removed in September 2023. FAQ rich results were limited to well-known
government and health sites in September 2023, deprecated in May 2026 and are no longer shown in Google
Search (documentation removed June 2026).
- So FAQPage markup is not a route to a Google rich result. A visible Q&A section can still help readers
and is judged on its content; recommend it only for questions the page really answers.
## M1. Microsoft Bing: Optimizing your content for inclusion in AI search answers
https://about.ads.microsoft.com/en/blog/post/october-2025/optimizing-your-content-for-inclusion-in-ai-search-answers
(Krishna Madhavan, Microsoft Bing, 8 October 2025)
- AI search assistants such as Copilot break pages into sections and assess them; the article says
"These modular pieces are what get ranked and assembled into answers."
- Recommends descriptive H2 and H3 headings (not generic labels such as "Learn more"); concise one-to-two
sentence answers that make sense when lifted out; lists, tables and Q&A blocks; questions phrased as
people search with brief answers; structured data aligned with visible content; title, H1 and meta
description consistent; specific, measurable details instead of vague claims.
- Warns against long walls of text, key answers hidden in tabs or expandable menus, core information only
in PDFs, critical details only in images without alt text or HTML equivalents, and vague words such as
"innovative".
- Says nothing guarantees selection; these practices improve eligibility.
## What no official source says
No source above promises that any content pattern earns rankings or citations. Claims elsewhere that a
specific word count, "citability score" or markup type gets pages cited are not official guidance. Do not
repeat them.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |