Turn a finished SEO + GEO audit into a client-ready PDF report with a fixed, polished layout. Input: the findings of an audit (usually from seo-geo-audit and the skills it hands off to). Output: one A4 PDF where no block is ever split across two pages, with a verdict, measured strengths, top priorities, every finding by category, an ordered action plan with no dates or delays, what was not verified, and the method. Use when an audit must be sent as a PDF, attached to an email, forwarded to a developer, or when the user asks for an audit report, a PDF audit, or a client deliverable.

Market analysis that reads every sitemap of every competitor and finds the keywords, topics and page models they cover and you do not. Always starts by asking the user for up to 5 known competitors, or whether to find them autonomously, before anything runs. Input: your site, plus competitors given or found. Output: competitor_sitemaps.py run on all of them (every sitemap followed, every URL sorted into a page model, publishing pace with real publication dates, slugs turned into topics), a page-model gap table (comparison, alternatives, glossary, free tools, integrations, use cases, locations, case studies, data studies), a topic and keyword gap validated against real demand, the publishing pace to match, and a ranked build plan handed to the page skills. Use for competitor analysis, market analysis, content gap, competitor keywords, 'they publish 200 articles a month', 'which pages do my competitors have that I do not', or scaling content to catch up.

Spec, audit, competitor benchmark and build for blog articles and the blog template, so a post ranks on Google and gets cited by AI engines (ChatGPT, Perplexity, AI Overviews). Input: a keyword, topic, draft or post URL. Phase 1 spec: BLOG rows on top of the common page spec, covering the 12-element answer-first skeleton and the page template (author line with photo and dates, sticky table of contents, sidebar author and CTA cards, in-content CTA, author box with real social profiles, related posts, key takeaways, sources, hub cards with covers). Phase 2 audits the article, the hub and the home with seo_audit.py and section_audit.py. Phase 3 benchmarks the top 3-5 SERP results with page_benchmark.py and names the information gain. Phase 4 builds and re-runs the scripts. Output: spec scorecard, findings, benchmark, the publish-ready article with metadata and JSON-LD, acceptance. Use when writing, rewriting, refreshing or auditing a blog post or the blog template, or when one will not rank or get cited.

Spec, audit, competitor benchmark and build for e-commerce collection, category and product listing pages (PLPs) on Shopify, WooCommerce, Magento, BigCommerce, PrestaShop or a custom store. Runs four phases: the collection spec (COL-01 to COL-24 plus the common rows), an audit of the live page with the bundled scripts, a benchmark against the stores and marketplaces ranking on the category term, and the build: Search Console demand mining, a 1-2 sentence top intro, a 400-800 word bottom block (buying guide, comparison table, definitions, FAQ of real questions), product cards with images, metadata, faceted-navigation and filter URL control, self-canonical pagination, thin or empty collection cleanup, internal links, CollectionPage, ItemList and BreadcrumbList JSON-LD, then the scripts re-run as the acceptance test. Use to create, write or audit a category page or PLP, or to handle filtered URLs, pagination, duplicate or empty categories and store crawl budget.

The ideal structure of a comparison hub, the 'best X' ranking page that lists many items (10 to 60 tools, apps, providers or platforms): 'best {category} in {year}', top 10 and ranking pages, tool directories, marketplace comparisons. Gives the order of the sections from the head to the footer and, for each section, its role, its content and its organization: H1 with the exact count, short answer, quick picks computed from the data, disclosure and ordering rule, comparison table usable on a phone, the publisher's own offer kept apart, method, one fixed card per item, items considered, buying guide, related pages, FAQ, changelog and sources, author, and the structured data that mirrors the page. Use to plan, write, rebuild or review a best X list or ranking hub.

Spec, audit, competitor benchmark and build for the bottom-funnel pages that capture buyers at the decision moment: 'X vs Y', 'alternatives to X', 'best X for Y', the comparison hub, and audience or segment pages ('for agencies', 'for freelancers'). Runs four phases: the CMP spec with stable IDs on top of the common page spec, an audit of the existing page with seo_audit.py and section_audit.py, a benchmark against the comparison and alternatives pages that rank on the query (review sites, affiliate lists, the competitors' own vs pages) with page_benchmark.py, then the build: which comparisons deserve a page, URL mapping, a comparison table with sourced and dated competitor facts, the verdict, honest limitations, segment pages that are not find-and-replace, FAQ, schema and the acceptance re-run. Use when planning, auditing or writing comparison, alternatives, best-for or segment pages, when competitors rank for your brand plus alternatives, or when AI assistants recommend competitors on comparison prompts.

Get a prioritized SEO + GEO action plan for any website. Input: a URL (and optional competitors). Output: ranked fixes across technical health, content, keywords, e-commerce, local, backlinks, and AI visibility (ChatGPT, Perplexity, Google AI Overviews), or a plain-language summary. Use to audit or review a site, find why it does not rank or is not cited by AI, compare against competitors, or set a baseline before a bigger SEO project.

Get a keyword map and an AI prompt panel grounded in how buyers actually search. Input: a site, niche, or seed topics (plus Google Search Console if available). Output: keywords mapped one-to-one to intent and pages, quick wins, a cannibalization check, an on-page placement matrix, and a 50-100 buyer prompt panel for ChatGPT, Perplexity, and Google AI Mode. Works without paid tools. Use for keyword research, search intent, keyword mapping, cannibalization, content gaps, prompt research, or deciding what to write and which queries to target.

Generic page auditor and entry point for every page type: runs spec, audit, competitor benchmark and build. Phase 1 spec: site archetype (Shopify, Webflow or WordPress, marketplace), the page types it needs, then the page type's block list plus the common spec and the site-level, header and footer rules (SEC IDs). Phase 2 audit: section_audit.py and seo_audit.py mark rows Pass, Fail or Not verifiable. Phase 3: page_benchmark.py on 3-5 competitors of the same page type. Phase 4: write the missing blocks (FAQ, breadcrumb, definitions, comparison and spec tables, reviews, trust badges, CTA, cross-links), then re-run the scripts as the acceptance test. Covers 21 page types: routes product, collection, service, location, comparison, top 10, segment, article and homepage copy to their dedicated skills; owns pricing, about, contact, blog hub, call, author, free tool, wall of love, affiliate, 404, listing, login. Use when a clean page underperforms, to find the pages and blocks a site lacks, or for a checklist.

Get valid Schema.org JSON-LD that still earns surfaces in 2026. Input: a page and its type (article, product, local business, person, and so on). Output: ready-to-adapt JSON-LD (Organization with sameAs, Article, Product, Offer, AggregateRating, LocalBusiness, BreadcrumbList, Person, WebSite, VideoObject, Event), entity graph linking with @id, a what-Google-dropped status table, and a two-validator routine. Use for schema, structured data, JSON-LD, rich results, review stars, breadcrumbs, sameAs, knowledge panel, or Rich Results Test errors.

Diagnose a traffic or ranking loss before fixing anything. Input: Search Console exports from a healthy period and a damaged one, plus what changed on the site. Output: whether the drop is real or a reporting artifact, the exact date and shape of the loss (visibility, ranking, click-through, demand), the pages and queries carrying it, a differential diagnosis with the test that confirms each cause, and the handoff to the skill that fixes it. Bundled zero-dependency script compares two exports and dates the drop. Use when traffic fell, rankings dropped, impressions or clicks collapsed, a core update landed, pages got deindexed, a migration or redesign went wrong, or a client asks what happened.