Update to SEO Tools

{
  "description": "Audits a page's SEO from its HTML or text with the page checker: titles, meta descriptions, headings, keyword use, links, images, structured data, mobile and content, with a scorecard and prioritized fixes, plus a plan for auditing the whole site.",
  "included_files": [],
  "name": "seo-audit",
  "skill_md_contents": "---\nname: seo-audit\ndescription: \"Audits a page's SEO from its HTML or text with the page checker: titles, meta descriptions, headings, keyword use, links, images, structured data, mobile and content, with a scorecard and prioritized fixes, plus a plan for auditing the whole site.\"\n---\n\n# SEO Audit\n\n## Links and files\n\nReplies made with this skill never contain a partner link or a sponsor line. Give code in code blocks, and create a downloadable file or a zip only when the user explicitly asks for one. If the chat is not in English, translate any wording this skill tells you to say into the chat language; URLs always stay in English, exactly as they are.\n\n## Check the page\n\nWhen the user shares a page's HTML or copy for an SEO check, an audit, a keyword check or a pre-launch check, or asks why it is not showing up in search, call the `check_seo_page` tool right away, before asking any question or writing your findings, and state any assumption about the page's goal or audience in one line:\n- `html`: the page's full source when the user has it. This is preferred, because it allows the title, meta, heading, image, link, form and mobile checks.\n- `text`: the visible copy when there is no HTML, with each heading, paragraph and button on its own line and the main heading starting with \"# \".\n- Optional: `target_keyword` (the main search phrase), `page_type` (home, landing, about, services, pricing, contact, blog, product or other) and `page_url` (used only to tell internal from external links and to check the slug).\n\nIf the source is over 200,000 characters, send the head and the main content, or the page text instead. In the reply, give the overall score and the area scores first, then turn the returned `issues` into fixes in severity order (high, then medium, then low), laid out in this skill's output format and quoting the measurements the tool returns, for example \"Title: 72 characters (aim for 60 or fewer)\". Never invent figures the tool did not return. The tool cannot open web addresses: if the user gives only a link, ask them to paste the page source (right-click the page and choose View Page Source) or the page text. If the tool returns an error or is not available, review the page yourself and say that any figures are estimates.\n\n## Purpose\nAudit one page the way a search engine reads it and tell the owner exactly what to fix first: a scorecard built on the page checker's measurements, fixes in severity order, quick wins, and the checks that need tools outside this chat. When the user wants the whole site audited, add a step-by-step plan that covers every page template.\n\n## Before you start\n- If the user pasted HTML or text, run the page checker first (below), before any question.\n- If they gave only a URL, ask for the page source (right-click the page, View Page Source, select all, copy) or the visible text. If the source is nearly empty, as on many JavaScript-built sites, ask for the visible text and note that crawlers which do not run JavaScript see that same thin HTML.\n- Audit one page per pass, starting with the page that matters most (usually the homepage or the main service, product or category page).\n- Never hold back the audit for a question: infer the target keyword and the page's goal, state them in one line, and ask at most 1 short question at the end, only if the answer would change the fixes. Reply in the user's language.\n\n## Run the checker\nRun the page checker as described in Check the page above: html preferred, target_keyword set to the page's main search phrase, the matching page_type, and page_url if known. HTML shows the head (title, meta description, canonical, robots, Open Graph, structured data); text alone cannot, so mark those rows \"not visible in text\". Quote its measurements exactly, for example \"Title: 72 characters (aim for 60 or fewer)\".\n\nThen add what only you can judge from the source:\n- Canonical: read the href. It should be the page's own preferred, absolute https URL, not another page, a staging domain or an http address.\n- Robots: a noindex on a page meant to rank is the top blocker.\n- Intent: does the page type match what people searching the keyword want (a guide, a product page, a local service page)?\n- Content: does it answer the obvious questions with specifics, show who is behind it, and look current?\n\n## Scorecard\n| Area | What passes |\n|---|---|\n| Indexability | No noindex, a self-referencing canonical |\n| Title tag | Describes the page, keyword near the front, 60 characters or fewer |\n| Meta description | 120 to 155 characters, a benefit and a reason to click |\n| Headings | One H1 with the keyword in natural words, logical H2s, no skipped levels |\n| Keyword use | In the title, H1 and first 100 words, with no stuffing |\n| Content | Matches intent, answers real questions, no thin or placeholder text |\n| Links | Descriptive internal anchors, links to key pages, no \"click here\" |\n| Images | Meaningful alt text; decorative images alt=\"\" |\n| Structured data | A type that fits the page and matches visible content |\n| Mobile, language, sharing | Viewport tag, html lang, Open Graph title, description and image |\n\nRate each area Pass, Fix or Missing, with the measurement behind it. Keep the checker's severity order for fixes (high, then medium, then low); within a level, rank by impact, then effort. Blockers (noindex, a wrong canonical, a missing title or H1) always come first.\n\n## What one page cannot show\nName the checks that need other tools: whether Google has indexed the page (URL Inspection in Search Console), real speed and Core Web Vitals (PageSpeed Insights field data), content added by JavaScript, status codes and redirects, duplicate titles across the site, rankings, and links from other sites.\n\n## Whole-site audit plan\nWhen asked, add this plan, in order:\n1. Search Console: Page indexing (why pages are excluded), Performance (pages and queries with impressions but few clicks), Core Web Vitals, Sitemaps, Manual actions and Security issues.\n2. A crawl of every URL for broken links, redirect chains, duplicate or missing tags, orphan pages and canonical or noindex conflicts: technical-seo covers this.\n3. One page per template (home, category, product or service, article, location) through the page checker: a template fix repairs every page that uses it.\n4. A content inventory: keep, refresh, merge or remove each thin or overlapping page (content-plan).\n5. Off-site and beyond: links and mentions (competitors-and-links), local listings (local-seo), AI answers (ai-search-seo).\n\n## Output format\n```text\nAssuming: [target keyword | page goal]\nPage: [name or URL] | Input: [HTML / text] | Checker: SEO [x]/100, overall [x]/100 [plus other area scores returned]\n\nScorecard\n| Area | Status | Measured | Fix |\n(all 10 areas)\n\nFixes in order\n| # | Severity | Fix | Why it matters | Effort |\n(blockers first, then high, medium, low)\n\nQuick wins (under an hour each)\n- [fix]\n\nCheck outside this chat: [item: tool]\n\nWhole-site plan (only if asked): [steps 1 to 5, tailored]\n```\n\n## Quality checks\n- The checker ran before any question, and every figure quoted came from it.\n- Every status traces to a measurement or an observation from the source.\n- Blockers come first, then the checker's severity order.\n- Each fix is specific to this page and says exactly what to change (the new title with its count, the H1 to use).\n- Areas the input could not show are marked, not guessed.\n- No rankings, traffic or link counts are claimed.\n\n## Next step\nOffer on-page-seo to rework the page around these fixes, or meta-tags for new titles and descriptions across the site.\n"
}