AgriciDaniel/claude-blog / brain
claude-blog-brain
UnverifiedScaffold and operate Claude Blog Brain, a source-cited Obsidian brain for blog content creation, optimization, and management dual-optimized for Google rankings (E-E-A-T, the 2026 core updates) and AI citations (GEO/AEO), spanning writing, rewriting and freshness, SERP-informed briefs and outlines, editorial calendars and strategy, semantic topic clusters, schema and internal linking, multilingual publishing, the FLOW framework, factchecking, personas, distribution, and the blog delivery contract, grounded in the claude-blog skill. Use when the user says "claude-blog-brain", "Claude Blog Brain", "create a blog content creation, optimization, and management dual-optimized for Google rankings (E-E-A-T, the 2026 core updates) and AI citations (GEO/AEO), spanning writing, rewriting and freshness, SERP-informed briefs and outlines, editorial calendars and strategy, semantic topic clusters, schema and internal linking, multilingual publishing, the FLOW framework, factchecking, personas, distribution, and the blog delivery contract, grounded in the claude-blog skill brain", "import sources", "synthesize plan", "render report", or wants a persistent vault-backed operating system for blog content creation, optimization, and management dual-optimized for Google rankings (E-E-A-T, the 2026 core updates) and AI citations (GEO/AEO), spanning writing, rewriting and freshness, SERP-informed briefs and outlines, editorial calendars and strategy, semantic topic clusters, schema and internal linking, multilingual publishing, the FLOW framework, factchecking, personas, distribution, and the blog delivery contract, grounded in the claude-blog skill.
references/claim-ledger.md
View on GitHub# Claim Ledger
High-impact, fast-moving blog SEO and GEO claims need adversarial review before
they appear in recommendations or deliverables. Keep this ledger aligned with
`source-ledger.json`. Rows marked `source-ledger gap` are useful research
evidence, but they are not release-satisfying until the source is backfilled in
`source-ledger.json` with retrieval metadata and raw provenance.
| Claim ID | Research question | Claim | Confidence | Verdict | Primary source URL + date | Corroborating second source | Refresh-due date |
| --- | --- | --- | --- | --- | --- | --- | --- |
| claim-faq-rich-results-retired | Can FAQPage markup still produce Google FAQ rich results? | No. FAQ rich results no longer appear in Google Search, effective 2026-05-07. Do not sell FAQPage as a current Google rich-result tactic. | high / EVIDENCE-BASED | CONFIRMED | <https://developers.google.com/search/updates#deprecating-the-faq-rich-result-feature>, living document, updated 2026-10-01, retrieved/reviewed 2026-10-12, source_id `g-faqpage-sd` | Same Google updates page, 2026-06-15 documentation-removal entry. Same publisher, not independent. | 2026-11-12 |
| claim-faqpage-ai-citation-unsupported | Does FAQPage markup have documented Google AI citation value? | No Google source found documents FAQPage markup as an AI Overview, AI Mode, or machine-citation signal. Visible Q and A content can help readers, but the markup claim is unsupported. | low / FOLKLORE | CONTESTED | <https://developers.google.com/search/docs/fundamentals/ai-optimization-guide>, living document, updated 2026-07-10, retrieved/reviewed 2026-10-12, source_id `g-ai-opt-guide` | <https://developers.google.com/search/docs/appearance/structured-data/intro-structured-data>, updated 2025-12-10, retrieved/reviewed 2026-10-07 | 2026-11-12 |
| claim-llms-txt-google-unused | Does Google Search use `llms.txt` for Search, AI Overviews, or AI Mode visibility? | Google says `llms.txt` is not needed for Google Search and does not positively or negatively affect visibility or rankings. It may be maintained for non-Google systems with that caveat. | high / EVIDENCE-BASED | CONFIRMED | <https://developers.google.com/search/docs/fundamentals/ai-optimization-guide>, living document, updated 2026-07-10, retrieved/reviewed 2026-10-12, source_id `g-ai-opt-guide` | <https://developers.google.com/search/updates>, 2026-06-15 llms.txt changelog event, retrieved/reviewed 2026-10-07, source_id `g-update-2026-06-15-llms-txt-clarified-as-unused-by-google-search` | 2026-11-12 |
| claim-inp-replaced-fid | Is FID still a current Core Web Vital for blog audits? | No. INP became a stable Core Web Vital on 2024-03-12 and replaced FID for responsiveness. Blog audits should use INP, LCP, and CLS. | high / EVIDENCE-BASED | CONFIRMED | <https://web.dev/blog/inp-cwv-march-12>, published 2024-01-31, updated 2024-01-31, retrieved/reviewed 2026-10-12, source_id `wd-inp-mar12` | `wd-inp` and `wd-vitals`, reviewed 2026-10-07, support the current metric set. Same publisher, not independent. | 2027-04-10 |
| claim-zero-click-2026-us | How much US Google search behavior was zero-click in early 2026? | SparkToro reported 68.01% of US Google searches ended without a click in January through April 2026, using a Similarweb mobile and desktop web panel. This is panel research, not Google first-party data. | medium / PRACTITIONER | AS-REPORTED | <https://sparktoro.com/blog/in-2026-less-than-one-third-of-google-searches-still-send-a-click/>, published 2026-06-08, retrieved/reviewed 2026-10-07, source_id `sparktoro-zero-click-2026` | <https://www.pewresearch.org/short-reads/2025/07/22/google-users-are-less-likely-to-click-on-links-when-an-ai-summary-appears-in-the-results/>, 2025-07-22, retrieved/reviewed 2026-10-07, supports zero-click direction, not the 68.01% figure | 2027-01-05 |
| claim-ai-mode-034-share | Was AI Mode a large share of US Google searches in early 2026? | SparkToro reported AI Mode was about 0.34% of US Google searches in January through April 2026. Use only with geography, channel, and panel caveats. | medium / PRACTITIONER | AS-REPORTED | <https://sparktoro.com/blog/in-2026-less-than-one-third-of-google-searches-still-send-a-click/>, published 2026-06-08, retrieved/reviewed 2026-10-07, source_id `sparktoro-zero-click-2026` | <https://blog.google/products-and-platforms/products/search/search-io-2026/>, 2026-05-19, retrieved/reviewed 2026-10-07, corroborates AI Mode growth but not query share | 2027-01-05 |
| claim-ai-mode-1b-users | Did Google report AI Mode crossing 1B plus monthly users at I/O 2026? | At I/O in May 2026, Google reported AI Mode had surpassed 1B monthly users. This is a dated self-reported reach milestone, not query or referral share. | high / EVIDENCE-BASED | CONFIRMED | <https://blog.google/products-and-platforms/products/search/search-io-2026/>, published 2026-05-19, retrieved/reviewed 2026-10-07, source_id `blog-io2026` | <https://sparktoro.com/blog/in-2026-less-than-one-third-of-google-searches-still-send-a-click/>, 2026-06-08, retrieved/reviewed 2026-10-07, cites the Google I/O claim while contrasting query share | 2027-04-05 |
| claim-aio-ctr-effect-contested | What is the AI Overview click-through effect? | The direction is credible, but no single universal CTR loss should be used. Seer, Pew, and Ahrefs measure different samples and report materially different effects. Use client GSC data when available. | medium / CONTESTED | CONTESTED | <https://www.seerinteractive.com/insights/aio-impact-on-google-ctr-2026-update>, published 2026-04-24, retrieved/reviewed 2026-10-07, source_id `seer-aio-impact-ctr-2026` | <https://www.pewresearch.org/short-reads/2025/07/22/google-users-are-less-likely-to-click-on-links-when-an-ai-summary-appears-in-the-results/>, 2025-07-22, and <https://ahrefs.com/blog/ai-overviews-reduce-clicks-update/>, 2026-02-04, retrieved/reviewed 2026-10-07 | 2027-01-05 |
| claim-seer-aio-ctr-rebound | What exactly did Seer report for AIO CTR in early 2026? | Seer's 53-brand Jan2025-Feb2026 cohort reported AIO-present organic CTR rising from 1.3% in Dec2025 to 2.4% in Feb2026. Its informational-query comparison associates citation with about 120% more clicks per impression. March values were projections; citation effects are not causal. | medium / PRACTITIONER | AS-REPORTED | <https://www.seerinteractive.com/insights/aio-impact-on-google-ctr-2026-update>, published 2026-04-24, retrieved/reviewed 2026-10-07, source_id `seer-aio-impact-ctr-2026` | The former secondary `seer-aio-ctr` record is retired after inaccessible content. No independent source corroborates this exact cohort; the primary report supports the attributed result. | 2027-01-05 |
| claim-pew-ai-summary-clicks | What did Pew observe when Google AI summaries appeared? | Pew observed traditional-result clicks in 8% of visits with an AI summary versus 15% without one, and summary-link clicks in 1%. Scope: 900 US adults, March2025 browsing. These are per-visit observations, not per-result CTR or causal effects. | medium / PRACTITIONER | AS-REPORTED | <https://www.pewresearch.org/short-reads/2025/07/22/google-users-are-less-likely-to-click-on-links-when-an-ai-summary-appears-in-the-results/>, published 2025-07-22, retrieved/reviewed 2026-10-07, source_id `pew-ai` | None in source-ledger for the same panel. Treat as first-party Pew research, not Google data. | 2027-01-05 |
| claim-eeat-scope | Is E-E-A-T a direct ranking factor? | Google says E-E-A-T itself is not a specific ranking factor, but its systems use a mix of factors that can identify content demonstrating experience, expertise, authoritativeness, and trust. YMYL topics receive stronger scrutiny. | high / EVIDENCE-BASED | CONFIRMED | <https://developers.google.com/search/docs/fundamentals/creating-helpful-content>, living document, updated 2026-10-05, retrieved/reviewed 2026-10-12, source_id `g-helpful-content` | <https://guidelines.raterhub.com/searchqualityevaluatorguidelines.pdf>, 2025-09-11, retrieved/reviewed 2026-10-07 | 2026-11-12 |
| claim-gen-ai-gsc-reports | Can Search Console report generative AI Search visibility? | Google announced dedicated generative-AI impressions reports June3 for a subset. The August31 update says rollout to all websites worldwide. Separate August13-17 missing genAI data was restored August21; a logging loss does not prove traffic loss. | high / EVIDENCE-BASED | CONFIRMED | <https://developers.google.com/search/blog/2026/06/gen-ai-performance-reports>, published 2026-06-03, updated 2026-08-31, retrieved/reviewed 2026-10-12, source_id `g-genai-reports` | <https://developers.google.com/search/updates>, 2026-06 documentation update, retrieved/reviewed 2026-10-07 | 2026-11-12 |
| claim-ai-mode-aio-citation-overlap | Do AI Mode and AI Overviews cite the same URLs? | Ahrefs reported only 13.7% citation overlap between AI Overviews and AI Mode across 540,000 September 2025 US query pairs. Treat as a practitioner benchmark, not a Google guarantee. | medium / PRACTITIONER | AS-REPORTED | <https://ahrefs.com/blog/ai-overviews-vs-ai-mode/>, published 2025-12-15, retrieved/reviewed 2026-10-07, source_id `ahrefs-aio-vs-aimode` | No independent second source for this exact September2025 US query-pair dataset. | 2027-01-05 |
| claim-chatgpt-cited-pages-zero-google-visibility | Do ChatGPT citations always overlap with Google organic visibility? | seoClarity reported 25% of its top1,000 ChatGPT-cited URLs lacked Google top100 visibility in its Research Grid keyword set, US desktop Nov9-15,2025. This does not establish zero Google traffic or zero visibility for every query. | medium / PRACTITIONER | AS-REPORTED | <https://www.seoclarity.net/research/analysis-of-top-cited-pages-from-chatgpt>, published 2025-11-20, retrieved/reviewed 2026-10-07, source_id `seoclarity-chatgpt` | No independent second source for this exact sample; other providers measure different datasets. | 2027-01-05 |
| claim-gen-ai-website-visit-mix-similarweb | What website-visit mix did Similarweb estimate? | Similarweb estimated worldwide generative-AI website-visit share shifted from about 76% ChatGPT in June 2025 to about 53% in May 2026, while Gemini reached roughly 27-28% in May 2026. | medium / PRACTITIONER | AS-REPORTED | <https://aisearch.similarweb.com/blog/gen-ai-stats/>, published 2026-07-29, retrieved/reviewed 2026-10-07, source_id `similarweb-gen-ai-stats-2026` | No independent source for this modeled worldwide website-visit panel; excludes native apps and does not measure client referrals. | 2027-01-05 |
| claim-ai-mode-links-per-answer | How citation-heavy are AI Mode answers? | SE Ranking reported an average of 12.6 links per AI Mode answer across 9,734 triggered responses from a 10,000-keyword US sample collected on 2025-06-20. Use with single-source practitioner caveats. | medium / PRACTITIONER | SINGLE-SOURCE | <https://seranking.com/blog/ai-mode-research/>, published 2025-08-29, retrieved/reviewed 2026-10-07, source_id `se-ranking-ai-mode-research` | <https://www.semrush.com/blog/ai-mode-comparison-study/>, 2025-07-21, retrieved/reviewed 2026-10-07, source_id `semrush-ai-mode-comparison`, related AI Mode study but does not corroborate the 12.6 figure | 2027-01-05 |
| claim-semrush-aio-saturation | How common were AI Overviews in Semrush's 2025 keyword sample? | Semrush reported AIO-triggering keywords moved from 6.49% in 2025-01 to 24.61% in 2025-07 and 15.69% in 2025-11 across its 10M plus keyword analysis. Treat as Semrush data, not Search-wide truth. | medium / PRACTITIONER | AS-REPORTED | <https://www.semrush.com/blog/semrush-ai-overviews-study/>, published 2025-12-15, retrieved/reviewed 2026-10-07, source_id `semrush-aio` | None in source-ledger for the same dataset. | 2027-01-05 |
| claim-product-category-sale-duration | Did Google add Product.category and sale-duration guidance on 2026-07-07? | Yes. Google added `Product.category` guidance for merchant listing structured data and sale-duration guidance for `validFrom`, `validThrough`, and `priceValidUntil`. Applies to product and merchant-listing contexts, not generic blog posts. | high / EVIDENCE-BASED | CONFIRMED | <https://developers.google.com/search/updates#july-2026>, living document, updated 2026-10-01, retrieved/reviewed 2026-10-12, source_id `g-search-docs-updates-2026-07-07-product-structured-data` | <https://developers.google.com/search/docs/appearance/structured-data/merchant-listing>, retrieved/reviewed 2026-10-07, `g-merchant-listing-sd`. Same publisher, not independent. | 2027-04-10 |
| claim-crux-history-window | What history does CrUX expose? | Detailed docs specify default25 and maximum40 weekly rolling28-day periods; an older introduction conflicts by saying six months. Specify collectionPeriodCount and overlapping-window scope. | high / EVIDENCE-BASED | QUALIFIED | <https://developer.chrome.com/docs/crux/history-api>, source_id `chrome-crux-history`, retrieved/reviewed 2026-10-12 | No authenticated API call; primary documentation review only. | 2026-11-12 |
| claim-soft-navigation-version | Which Chrome version evidence applies? | The final origin trial covered Chrome147-149. Current documentation says soft navigations are enabled by default in Chrome151; actual tool coverage must be checked. | high / EVIDENCE-BASED | CONFIRMED | <https://developer.chrome.com/docs/web-platform/soft-navigations>, source_id `chrome-soft-nav`, retrieved/reviewed 2026-10-12 | `chrome-softnav-final` supports the historical147-149 trial only. | 2026-11-12 |
| claim-site-reputation-eea | Where does site-reputation manual-action impact apply? | From Aug30,2026 it applies to results for searchers outside the EEA. Inside the EEA manual-action impact does not apply, while sections may be separated to rank independently. Searcher region governs. | high / EVIDENCE-BASED | CONFIRMED | <https://developers.google.com/search/blog/2026/08/update-site-reputation-policy>, source_id `g-site-reputation-eea-2026-08-28`, retrieved/reviewed 2026-10-07 | `g-spam-policies`, same publisher; no automatic exemption from the underlying policy. | 2027-04-05 |
| claim-gen-ai-logging-restored | Is August genAI logging loss still missing? | Google says missing Aug13-17 genAI impression data was restored Aug21. The separate Discover incident and logging loss do not prove lost traffic. | high / EVIDENCE-BASED | CONFIRMED | <https://support.google.com/webmasters/answer/6211453?hl=en>, source_id `gsc-reporting-anomalies-2026-08-13`, retrieved/reviewed 2026-10-12 | No independent incident corroboration required for an attributed official reporting status. | 2026-11-12 |
| claim-platform-property-availability | Are platform properties available to every account? | The July29 announcement says globally available, while current Help says gradual rollout and not yet all users. Preserve the official conflict and check the actual account UI. | medium / CONTESTED | CONTESTED | <https://support.google.com/webmasters/answer/17148418?hl=en-GB>, source_id `search-console-platform-help-2026-08-25`, retrieved/reviewed 2026-10-12 | `search-console-platform-properties-2026-07-29` states the conflicting broader rollout. | 2026-11-12 |
| claim-passage-self-containment | What does ZipTie support? | ZipTie recommends answer-first self-contained sections and clear headings as an editorial heuristic. It does not validate causal uplift, fixed lengths, entity density, source-proximity ranking rules, or FAQ/HowTo citation effects. | medium / PRACTITIONER | AS-REPORTED | <https://ziptie.dev/blog/google-ai-overviews-source-selection/>, source_id `ziptie-aio-source-selection`, retrieved/reviewed 2026-10-07 | No independent causal support; Google docs establish general eligibility, not this optimization mechanism. | 2027-01-05 |
| claim-news-subscription-links | What did Google announce for subscription links? | Google announced highlighting links from users' news subscriptions in AI Mode and AI Overviews on May6,2026. This does not establish a generic loyal-audience ranking signal. | high / EVIDENCE-BASED | CONFIRMED | <https://blog.google/products-and-platforms/products/search/explore-web-generative-ai-search/>, source_id `g-ai-search-subscription-links-2026-05-06`, retrieved/reviewed 2026-10-07 | The former Nieman Lab secondary record is retired; its dependent causal claims are not transferred. | 2027-04-05 |
| claim-bing-grounding | What does the accessible Bing evidence support? | Microsoft describes current authoritative grounding and announced citation/grounding visibility in Bing Webmaster Tools. The inaccessible guidelines record is retired; detailed guideline claims remain unsupported by this replacement. | high / EVIDENCE-BASED | QUALIFIED | <https://blogs.bing.com/search/2026/2/Elevating-the-Role-of-Grounding-on-the-AI-Web/>, source_id `bing-grounding-ai-web-2026-02-12`, retrieved/reviewed 2026-10-07 | No guarantee of inclusion or complete report coverage is established. | 2027-04-05 |
Review boundary: all rows were checked against the October 7 source review.
Historical study windows remain historical; review does not make them current
market measurements. Retired records preserve provenance and do not support
active claims. Source IDs and per-source limitations govern every row.
## Verdict Rules
- `CONFIRMED`: directly supported by an official, primary, standards, or first-party source.
- `AS-REPORTED`: a dated study or vendor report says this, but the claim should retain that source's methodology and scope.
- `SINGLE-SOURCE`: one dated source supports the claim and no corroborating source is available in the ledger.
- `QUALIFIED`: the supported narrow claim retains an explicit conflict or limitation.
- `CONTESTED`: credible sources conflict, the source does not prove the operational claim, or the claim is a common SEO/GEO overreach.
## Verification Flow
1. Draft the claim in plain language.
2. Attack what the source does not prove.
3. Assign `confidence`, `evidence_tier`, and `verdict`.
4. Seek an independent second source for market, traffic, ranking, AI visibility, or named-site impact claims. If none exists, preserve SINGLE-SOURCE or AS-REPORTED status and scope; a secondary retelling is not corroboration.
5. Record limits before the claim is used in a deliverable.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |