entity-seo.md:148 says "sameAs pointing to dead profiles — validate each URL
resolves", and STEP 7 asks "does the target resolve and match?". Nothing
implemented it: zero curl against a sameAs anywhere in the repo. A dead
sameAs is worse than a missing one — it asserts an identity link that fails
on follow, in the exact graph AI engines walk to confirm who you are.
The naive version of this check is a false-positive generator, which is
presumably why it stayed unimplemented. Verified live rather than assumed:
999 linkedin.com/company/anthropic <- blocks non-browsers
200 wikidata.org/wiki/Q108162414
200 x.com/anthropicai
404 <known-dead URL> <- correctly detected
So the check classifies by code, not by liveness guess: 404/410 = dead
(finding with direction), 401/403/429/999 = bot-blocked (inconclusive, NO
finding, never "dead"), 000/5xx = inconclusive. No G2/G6 item may remove a
sameAs on anything but 404/410 — same shape as the NAP direction rule: an
unreliable signal read confidently is worse than no signal.
Note: the spec draft asserted "X/Twitter and Instagram commonly 403" from
plausibility. The live test returned 200 for x.com and contradicted it —
corrected to classify by observed code, never by platform folklore. Third
unverified-plausible claim caught this session (I1, I6, here); the pattern
is exactly what these fixes exist to stop.
Verified: pipeline exercised end-to-end against real endpoints; make test
35 GREEN / 0 RED.
Audited each statistic in agents/resources/ against primary sources after
the VSI fiction (I2) showed WebSearch launders SEO-blog consensus.
The failure mode is not invention — it is plausible recombination, which is
what a model half-remembering a search result produces:
- "Adding statistics increases AI visibility by up to 40% (Aggarwal et al.)"
— paper real (KDD 2024), number real, SCOPE WRONG: 40% is the aggregate
over the whole method set, domain-dependent. No per-technique figure
exists.
- "Pages not updated quarterly are 3x more likely to lose AI citations
(LLMRefs)" — LLMrefs' actual 3x says brand mentions correlate ~3x more
strongly with AI visibility than backlinks. DIFFERENT SUBJECT. No source
supports a quarterly decay multiplier.
- "QAPage cited 58% more often than Article" — uncited. Nearest real number:
AccuraCast 2025, `Person` schema at 58.9% PREVALENCE among cited sources —
wrong type, and its FAQPage figure (1.8%) points the opposite way to the
claim it propped up. This one drove Tier 1 ranking.
- "62% of searches involve voice" — uncited; 62% circulates as smart-speaker
ADOPTION. Same family as the "50% by 2020" myth ComScore denied (origin: a
2014 Andrew Ng interview).
Corrected my own framing too: I claimed three times these stats "drive axis
weights". They do not — the weight tables carry no citations. They drive
Tier/priority recommendations and, worse, geo-analyzer's "Cite sources" rule
pushed them into CLIENT reports as research-backed.
Fixes: recommendations kept on mechanism, fabricated numbers removed with
the incident documented inline so they are not re-added. Unverified stats
(48% AI Overviews, 2.5B queries/day, Gartner -25%) labelled [UNVERIFIED]
rather than asserted or deleted — I did not check them.
Structural, not just exhortation: resources/README.md now mandates
`<claim> — <source, year, venue|vendor> — measured: <what the source ACTUALLY
measured> — <link>`. `measured:` is the field that catches this — all four
errors survive a source name; none survives stating the real measurement
next to the claim. WebSearch demoted from verification to crawler/tool-name
lookup only.
Verified: make test 35 GREEN / 0 RED.
Both agents sample (seo-analyzer.md:403 "sample 5-15 key pages",
geo-analyzer.md:460 "Sample 5-10 key pages") and neither states it. The
report says "audit". On a 500-page site a 12-page sample is 2.4%, and the
reader cannot know that unless it is printed. /client-handover gates on
these scores.
The denominator was already within reach: STEP 4 fetches sitemap.xml. Count
its URLs and the coverage ratio is free — same data C1 will use for
sitemap-driven crawl later.
- Mandatory COVERAGE line in both scoring blocks: N of M sitemap URLs (P%),
or "total UNKNOWN" when no sitemap. Never omitted, never rounded up.
- seo: <25% coverage repeats in §0 as a major alert. Sample by risk (one
page per template + GSC position 4-10 quick wins), name skipped templates
— an un-sampled template is an un-audited template.
- geo: scoped honestly rather than blanket — COVERAGE bounds the per-page
axes (Content Shape, page-level Schema.org) but NOT the site-wide ones
(AI Crawlers Policy, llms.txt are single files, fully read). One ratio
should not discredit axes it does not govern.
Verified: make test 35 GREEN / 0 RED.
Surfaced by pointing /harden at zenquality.fr from the claude-config CWD.
A1 — no CWD/target coherence guard (systemic: /seo, /geo, /harden all
lack it; grep confirms). A URL is supplied, the agent greps whatever CWD
it landed in, nobody checks they are the same site. Demonstrated live:
from claude-config, /harden would curl zenquality.fr while grepping
claude-config, then score "Config hardening" on a codebase that is not the
site. The live half looks right, the code half is fiction, and the report
reads as authoritative.
Fixed in both agents' STEP 2 rather than the 3 dispatchers: the agent does
the grepping, so the guard binds whoever calls — same principle as I3.
/harden inherits it free.
A2 — seo-analyzer had zero origin-vs-edge awareness while geo-analyzer
has the full CDN/WAF-override check (geo-analyzer.md:246-261). seo-analyzer
does the infra detection AND is reused by /harden for its whole
config-hardening axis (20/100). On zenquality — Apache origin behind a
Scaleway nginx front — repo .htaccess + `server: nginx` invites the wrong
call "nginx serves this, .htaccess is dead". I made that exact inference
myself before reading the file. Rule added at STEP 2 infra detection:
`server:` names the edge, not the origin; live-but-not-in-repo = "set
upstream", never "missing".
Verified: live probe of zenquality.fr (read-only, nothing written to the
client repo); make test 35 GREEN / 0 RED.
geo-analyzer owns JSON-LD NAP (ownership matrix, seo/SKILL.md:261) and can
rewrite it via G2 — AUTO tier, no confirmation (geo-analyzer.md:660). The
LRN-032 protection lived ONLY in the /seo dispatcher prompt
(seo/SKILL.md:339-343), so standalone /geo reconciled NAP with no canonical
and no anti-seed guard — the exact zenquality trap, writing into client
structured data.
Root cause: a safety invariant that depended on the caller. Fixed at the
layer that owns the data.
- Data integrity: NAP direction rule, caller-independent, binds G2/G6.
Covers CREATE (LocalBusiness from scratch) not just rewrite — geo builds
missing schemas, seo-analyzer's wording only covered rewrite.
- STEP 6 checklist: pointer at the line that triggers the action.
Absent canonical is already the safe default (no directional fix), so no
NAP collection step is needed in /geo — that would duplicate seo/SKILL.md
STEP 0 and risk drift.
Verified: make test 25+5+5 GREEN / 0 RED (incl. G3 strict-YAML frontmatter).
geo-analyzer asserted 'PERMISSIVE default per user CLAUDE.md' in 2 sites (L224,
L867-869) but CLAUDE.md carries no PERMISSIVE/RESTRICTIVE crawler policy. Reframed
as the agent's own policy grounded in GEO's purpose (an AI-visibility audit defaults
to allowing AI crawlers); default unchanged. Completes job3 C6/C7/C8 scrub (which
missed geo) — job9's later rewrite also left it. User-approved wording. Review A5.
Both blind judges flagged the same residual: without a detection
criterion, a /seo-dispatched subagent could misread itself as headless
and degrade to report-only. Unreachable = no answer obtainable at all
(cron/CI, user explicitly absent); orchestrator dispatch with a main
thread that can relay questions is reachable.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Live darwin test: with the user unreachable, the triage table's
"Confirmation: No" batches edited 2 source HTML files unsupervised.
Autonomous batches presume a reachable user who saw the printed plan;
headless -> all batches report-only with ready-to-apply content.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Post-review hardening of the parallel seo+geo dispatch:
- skills/seo/SKILL.md: shared-file edit discipline embedded in both dispatch prompts (Edit-only on shared templates, Write only on sole-owned files). CROSS-AGENT NOTES flow clarified — dispatcher escalates to SEO.md §11 as user action with automation options (Option B).
- agents/seo-analyzer.md: STEP 2 detects 8 CMS (WordPress/Drupal/Magento/Shopify/Joomla/PrestaShop/Ghost/Wix-Squarespace-Webflow) and presence of SEO plugins. STEP 10 emits P0 quick win "install CMS plugin" when CMS detected without plugin. STEP 5 expands topic clusters / silos sémantiques. Framework notes in STEP 12 cover all 8 CMS explicitly.
- agents/geo-analyzer.md: STEP 6 checks /faq path + FAQPage schema presence. STEP 11 mandates 3 AI-index user actions per FULL audit (Bing Webmaster Tools / GSC / IndexNow) + Apple Business Connect for local business.
- agents/resources/automation-catalog.md: new structured CMS plugin section (install links + pricing per platform). AI-index submission section rewritten with Bing Webmaster as canonical entry for ChatGPT Search/Copilot/DuckDuckGo, IndexNow protocol details, Brave Web Discovery, Apple Business Connect.
- agents/resources/llms-txt-template.md: explicit note that /ai.txt and /about-data are NOT real standards; llms.txt (Jeremy Howard) remains the only proposed one.
Rationale: third-party AI review of the skill surfaced 5 gaps — race condition on shared templates (Layout.astro holds meta + JSON-LD), ambiguous cross-agent flow, missing CMS-plugin-first logic (Gemini), under-exposed Bing Webmaster (ChatGPT Search channel), and minor accuracy items.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Refactor the monolithic seo-analyzer into two specialist agents
orchestrated in parallel by the /seo skill, plus a standalone /geo
skill for AI-only audits.
Changes
- agents/seo-analyzer.md: refocused on classical engines (Google, Bing,
DuckDuckGo). Adds Core Web Vitals 2.0 (LCP/INP/CLS + VSI), CSP + full
security headers, hreflang audit, video SEO (transcripts), accessibility
as ranking signal, image/video sitemaps.
- agents/geo-analyzer.md: new agent for AI engines (ChatGPT, Claude,
Perplexity, Gemini, Google AI Overviews, Copilot). Covers AI crawler
policy, llms.txt/llms-full.txt, Schema.org for AI extraction (QAPage,
Speakable, Person+Article, Organization graph), entity SEO (Wikidata,
sameAs, Knowledge Panel), content shape (Definition Lead, TL;DR,
Q->A, citable stats, freshness), AI visibility testing.
- agents/resources/: shared knowledge base referenced by both agents —
ai-crawlers-2026.md (25+ bots, training vs retrieval categories,
permissive/restrictive templates), llms-txt-template.md, geo-schemas.md
(incl. deprecated list: ClaimReview, CourseInfo, etc. removed June 2025),
entity-seo.md, content-shape-for-ai.md, ai-visibility-tools.md,
automation-catalog.md.
- skills/seo/SKILL.md: becomes parallel dispatcher. Collects context
once (depth + business), spawns both agents in a single message for
concurrent execution, merges envelopes into unified SEO.md. Includes
authoritative file-ownership matrix to prevent parallel-edit races.
- skills/geo/SKILL.md: new standalone wrapper for GEO-only audits.
Scoring
- Combined score: GLOBAL = 0.80 * SEO + 0.20 * GEO (local B2C),
0.75 * SEO + 0.25 * GEO (SaaS/national/content).
- GEO axis weight raised from 5% (old) to first-class dimension.
Policy
- AI crawlers: permissive default (maximise AI citations). Restrictive
template available for premium/regulated content.
- Every user action in SEO.md section 11 must cite automation options
from automation-catalog.md.
Tools
- WebFetch + WebSearch added to allowed-tools of both skills and
both agents (needed for live CWV via PageSpeed API, AI visibility
testing, Wikidata/Knowledge Panel lookups, competitor analysis).
Research basis (2026 state of the art validated via WebSearch):
- Core Web Vitals 2.0 (VSI signal, Google core update March 2026)
- AI Overviews trigger on ~48% of Google searches
- ClaimReview + 6 other schema types deprecated June 2025
- Definition Lead Architecture (CMU KDD 2024, +impression score)
- Citations + stats add up to 40% AI visibility (Aggarwal 2024)
- Wikidata grounds every major LLM (ChatGPT, Claude, Gemini, Perplexity)
Backup
- agents/seo-analyzer.md.bak kept for rollback reference.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Bastien Chanot