{"id":"618717c4-33b0-4a9f-8e75-004a68a03964","shortId":"m3zaaE","kind":"skill","title":"anycap-ai-tool-seo","tagline":"Guide for planning and auditing SEO for AI tool, SaaS, and product-led websites. Powered by AnyCap -- the capability runtime that equips AI agents with web search and web crawl through a single CLI. Use when Codex needs to define SEO ICPs, map search intent to page types, inspect","description":"# AnyCap AI Tool SEO\n\n> **Read this entire file before starting.** It covers the full SEO planning and audit workflow for AI tool websites.\n\nPlan and audit SEO for AI tool websites. Focus on product-led SEO where each page should help a searcher complete a task, evaluate options, or enter the product with high intent.\n\n**Map intent. Shape pages. Add evidence. Protect quality.**\n\n## Before You Start\n\n**Read all three reference files before taking any action.** They contain the working framework, page planning rules, and quality guardrails.\n\n1. Read this file for the overview and process\n2. Read the references in this order:\n   - [framework.md](references/framework.md)\n   - [page-planning.md](references/page-planning.md)\n   - [guardrails.md](references/guardrails.md)\n3. Then begin the workflow below\n\nFor detailed command syntax, flags, and output parsing, refer to the **anycap-cli** skill.\n\n## Prerequisites\n\n- `anycap` CLI installed and authenticated (`anycap status` to verify)\n- A local workspace for notes, saved search results, and page briefs\n\n## When to Use This Skill\n\n- AI tool website SEO planning\n- SaaS or product-led SEO audits\n- Search intent to page type mapping\n- Page brief creation for tool, comparison, alternatives, pricing, and tutorial pages\n- Technical SEO prioritization for new or growing tool websites\n- Citation, directory, or backlink planning\n- Programmatic SEO evaluation and rollout gating\n\n## SEO Planning Process\n\n```mermaid\ngraph LR\n    A[Understand Site and ICP] --> B[Inspect Live SERP]\n    B --> C[Choose Page Type]\n    C --> D[Define Information Gain]\n    D --> E[Check Technical and Trust Signals]\n    E --> F[Prioritize and Deliver]\n```\n\nWork through the steps below in order. Skip only when you already have high-confidence answers.\n\n### 1. Understand the site and the searcher\n\n- Crawl the homepage, pricing page, docs/help center, and one representative tool or feature page.\n- Infer:\n  - the core job-to-be-done\n  - primary user, buyer, and learner\n  - target geography and language\n  - primary conversion event\n- Use the 6-field ICP template in [framework.md](references/framework.md).\n- If the user only provides a URL, infer first and ask follow-up questions only when the missing context would materially change the plan.\n\n### 2. Inspect the live SERP before recommending content\n\n- Do not decide the content format from the keyword alone.\n- Use `anycap search --query \"<keyword>\" --no-crawl --max-results 10` to classify dominant page types, recurring modules, and SERP mix.\n- Treat search intent as a page-shape constraint, not just a label.\n- If the SERP is mixed, decide whether the keyword deserves one page with a dominant intent or multiple pages.\n- Use [page-planning.md](references/page-planning.md) for page type mapping and module requirements.\n\n### 3. Evaluate page viability through four lenses\n\n- Review every page or keyword cluster through:\n  - **Search-Fit Product**: Can the user complete the task on the page or move naturally into the product?\n  - **Information Gain**: What first-hand evidence, screenshots, data, tests, workflows, or examples make this page stronger than the current SERP?\n  - **Technical Readiness**: Can search systems crawl, index, render, and understand the page?\n  - **Trust Distribution**: What internal links, external mentions, backlinks, directory placements, or trust blocks support the page?\n- Use \"Last-Click\" only as a user-satisfaction heuristic. Do not present it as an official Google ranking factor. See [guardrails.md](references/guardrails.md).\n\n### 4. Prioritize the plan\n\n- Default prioritization:\n  1. money pages with clear transactional or commercial intent\n  2. comparison, alternatives, and pricing pages\n  3. tutorials that support discovery, trust, and internal linking\n  4. pSEO only after a small set of hard pages proves quality and indexation\n- Separate:\n  - high-confidence rules\n  - practitioner heuristics\n  - assumptions that still need validation\n\n### 5. Deliver concrete outputs\n\n- Default deliverables:\n  - ICP summary\n  - keyword cluster -> intent -> page type table\n  - priority page briefs\n  - technical baseline checklist\n  - citations / backlinks backlog\n  - pSEO go / no-go decision with safeguards\n  - 30 / 60 / 90 day sequencing\n\n## Human-in-the-Loop\n\nThis skill benefits from light user input up front, but should otherwise run autonomously.\n\n- Ask for the site URL, target market, and conversion goal if they are not clear.\n- If the user already gave a concrete site or keyword set, do not over-clarify.\n- Once direction is clear, continue through SERP inspection, planning, and prioritization without repeated interruptions.\n\n## Core Principles\n\n**Define the searcher before the keyword.** A keyword only makes sense once you know who is searching, why, and what they need to finish.\n\n**Inspect the live SERP before choosing a page type.** Do not recommend a tutorial, comparison, or tool page until you know what the current SERP rewards.\n\n**Treat page type as intent execution.** A page is not just content; it is the shape through which the intent gets fulfilled.\n\n**Require evidence, not generic prose.** Information gain should come from screenshots, examples, data, workflows, benchmarks, or other concrete proof.\n\n**Protect quality before scale.** Do not recommend pSEO until high-value sample pages have proven useful, indexable, and maintainable.\n\n**Separate rules from heuristics.** Be explicit about what is a hard constraint versus what is a useful but situational tactic.\n\n## Quick Reference\n\n```bash\n# Inspect a target site\nanycap crawl https://example.com\n\n# Inspect the SERP shape for a keyword\nanycap search --query \"best ai headshot generator\" --no-crawl --max-results 10\n\n# Ask for a grounded summary when the SERP is unclear\nanycap search --prompt \"What page types dominate the SERP for 'best ai headshot generator' and which content blocks recur?\"\n```\n\nSave important search and crawl outputs locally when the task is large or when you expect to revisit evidence.\n\n## Guardrails\n\n- Do not promise rankings.\n- Do not recommend doorway pages, spun pages, or low-value mass AI pages.\n- Do not copy a competitor layout blindly; infer the SERP expectation, then add original evidence.\n- Treat numeric thresholds, directory filters, and DR/DA cutoffs as heuristics rather than fixed rules.\n- Flag compliance risk when recommending paid placements, sponsored links, or directory submissions.\n- When suggesting pSEO, require unique fields, update mechanisms, quality checks, and pruning rules.\n\n## Resources\n\n- [framework.md](references/framework.md) -- core model, support levels, and default prioritization\n- [page-planning.md](references/page-planning.md) -- intent mapping, page modules, and page brief outputs\n- [guardrails.md](references/guardrails.md) -- quality boundaries, safety checks, and pSEO gating","tags":["anycap","tool","seo","anycap-ai","agent","agent-skills","claude-code","cli","coding-agent","skills"],"capabilities":["skill","source-anycap-ai","skill-anycap-ai-tool-seo","topic-agent","topic-agent-skills","topic-claude-code","topic-cli","topic-coding-agent","topic-skills"],"categories":["anycap"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/anycap-ai/anycap/anycap-ai-tool-seo","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add anycap-ai/anycap","source_repo":"https://github.com/anycap-ai/anycap","install_from":"skills.sh"}},"qualityScore":"0.466","qualityRationale":"deterministic score 0.47 from registry signals: · indexed on github topic:agent-skills · 32 github stars · SKILL.md body (6,873 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-01T12:57:23.543Z","embedding":null,"createdAt":"2026-04-18T22:22:31.060Z","updatedAt":"2026-05-01T12:57:23.543Z","lastSeenAt":"2026-05-01T12:57:23.543Z","tsv":"'1':143,315,583 '10':418,896 '2':152,390,592 '3':165,471,598 '30':664 '4':577,607 '5':633 '6':358 '60':665 '90':666 'action':131 'add':116,976 'agent':30 'ai':3,13,29,57,76,84,212,887,918,962 'alon':407 'alreadi':309,706 'altern':236,594 'answer':314 'anycap':2,23,56,183,187,192,409,873,883,907 'anycap-ai-tool-seo':1 'anycap-c':182 'ask':375,688,897 'assumpt':628 'audit':10,73,81,223 'authent':191 'autonom':687 'b':272,276 'backlink':253,544,654 'backlog':655 'baselin':651 'bash':868 'begin':167 'benchmark':821 'benefit':676 'best':886,917 'blind':970 'block':549,924 'boundari':1041 'brief':206,231,649,1036 'buyer':346 'c':277,281 'capabl':25 'center':328 'chang':387 'check':288,1014,1043 'checklist':652 'choos':278,764 'citat':250,653 'clarifi':718 'classifi':420 'clear':587,702,722 'cli':40,184,188 'click':556 'cluster':483,642 'codex':43 'come':815 'command':173 'commerci':590 'comparison':235,593,773 'competitor':968 'complet':100,492 'complianc':994 'concret':635,709,824 'confid':313,624 'constraint':437,857 'contain':133 'content':397,402,796,923 'context':384 'continu':723 'convers':354,696 'copi':966 'core':338,733,1021 'cover':67 'crawl':36,322,414,530,874,892,930 'creation':232 'current':523,782 'cutoff':986 'd':282,286 'data':512,819 'day':667 'decid':400,447 'decis':661 'default':581,637,1026 'defin':46,283,735 'deliv':297,634 'deliver':638 'deserv':451 'detail':172 'direct':720 'directori':251,545,982,1003 'discoveri':602 'distribut':538 'docs/help':327 'domin':421,456,913 'done':343 'doorway':953 'dr/da':985 'e':287,293 'enter':106 'entir':62 'equip':28 'evalu':103,257,472 'event':355 'everi':479 'evid':117,510,808,944,978 'exampl':516,818 'example.com':875 'execut':790 'expect':941,974 'explicit':851 'extern':542 'f':294 'factor':573 'featur':334 'field':359,1010 'file':63,127,146 'filter':983 'finish':758 'first':373,508 'first-hand':507 'fit':487 'fix':991 'flag':175,993 'focus':87 'follow':377 'follow-up':376 'format':403 'four':476 'framework':136 'framework.md':159,363,1019 'front':682 'fulfil':806 'full':69 'gain':285,505,813 'gate':260,1046 'gave':707 'generat':889,920 'generic':810 'geographi':350 'get':805 'go':657,660 'goal':697 'googl':571 'graph':265 'ground':900 'grow':247 'guardrail':142,945 'guardrails.md':163,575,1038 'guid':6 'hand':509 'hard':615,856 'headshot':888,919 'help':97 'heurist':563,627,849,988 'high':110,312,623,836 'high-confid':311,622 'high-valu':835 'homepag':324 'human':670 'human-in-the-loop':669 'icp':48,271,360,639 'import':927 'index':531,620,843 'infer':336,372,971 'inform':284,504,812 'input':680 'inspect':55,273,391,726,759,869,876 'instal':189 'intent':51,111,113,225,431,457,591,643,789,804,1030 'intern':540,605 'interrupt':732 'job':340 'job-to-be-don':339 'keyword':406,450,482,641,712,740,742,882 'know':748,779 'label':441 'languag':352 'larg':937 'last':555 'last-click':554 'layout':969 'learner':348 'led':19,91,221 'lens':477 'level':1024 'light':678 'link':541,606,1001 'live':274,393,761 'local':197,932 'loop':673 'low':959 'low-valu':958 'lr':266 'maintain':845 'make':517,744 'map':49,112,229,467,1031 'market':694 'mass':961 'materi':386 'max':416,894 'max-result':415,893 'mechan':1012 'mention':543 'mermaid':264 'miss':383 'mix':428,446 'model':1022 'modul':425,469,1033 'money':584 'move':499 'multipl':459 'natur':500 'need':44,631,756 'new':245 'no-crawl':412,890 'no-go':658 'note':200 'numer':980 'offici':570 'one':330,452 'option':104 'order':158,304 'origin':977 'otherwis':685 'output':177,636,931,1037 'over-clarifi':716 'overview':149 'page':53,95,115,137,205,227,230,240,279,326,335,422,435,453,460,465,473,480,497,519,536,552,585,597,616,644,648,766,776,786,792,839,911,954,956,963,1032,1035 'page-planning.md':161,462,1028 'page-shap':434 'paid':998 'pars':178 'placement':546,999 'plan':8,71,79,138,216,254,262,389,580,727 'power':21 'practition':626 'prerequisit':186 'present':566 'price':237,325,596 'primari':344,353 'principl':734 'priorit':243,295,578,582,729,1027 'prioriti':647 'process':151,263 'product':18,90,108,220,488,503 'product-l':17,89,219 'programmat':255 'promis':948 'prompt':909 'proof':825 'prose':811 'protect':118,826 'prove':617 'proven':841 'provid':369 'prune':1016 'pseo':608,656,833,1007,1045 'qualiti':119,141,618,827,1013,1040 'queri':411,885 'question':379 'quick':866 'rank':572,949 'rather':989 'read':60,123,144,153 'readi':526 'recommend':396,770,832,952,997 'recur':424,925 'refer':126,155,179,867 'references/framework.md':160,364,1020 'references/guardrails.md':164,576,1039 'references/page-planning.md':162,463,1029 'render':532 'repeat':731 'repres':331 'requir':470,807,1008 'resourc':1018 'result':203,417,895 'review':478 'revisit':943 'reward':784 'risk':995 'rollout':259 'rule':139,625,847,992,1017 'run':686 'runtim':26 'saa':15,217 'safeguard':663 'safeti':1042 'sampl':838 'satisfact':562 'save':201,926 'scale':829 'screenshot':511,817 'search':33,50,202,224,410,430,486,528,751,884,908,928 'search-fit':485 'searcher':99,321,737 'see':574 'sens':745 'seo':5,11,47,59,70,82,92,215,222,242,256,261 'separ':621,846 'sequenc':668 'serp':275,394,427,444,524,725,762,783,878,904,915,973 'set':613,713 'shape':114,436,800,879 'signal':292 'singl':39 'site':269,318,691,710,872 'situat':864 'skill':185,211,675 'skill-anycap-ai-tool-seo' 'skip':305 'small':612 'source-anycap-ai' 'sponsor':1000 'spun':955 'start':65,122 'status':193 'step':301 'still':630 'stronger':520 'submiss':1004 'suggest':1006 'summari':640,901 'support':550,601,1023 'syntax':174 'system':529 'tabl':646 'tactic':865 'take':129 'target':349,693,871 'task':102,494,935 'technic':241,289,525,650 'templat':361 'test':513 'three':125 'threshold':981 'tool':4,14,58,77,85,213,234,248,332,775 'topic-agent' 'topic-agent-skills' 'topic-claude-code' 'topic-cli' 'topic-coding-agent' 'topic-skills' 'transact':588 'treat':429,785,979 'trust':291,537,548,603 'tutori':239,599,772 'type':54,228,280,423,466,645,767,787,912 'unclear':906 'understand':268,316,534 'uniqu':1009 'updat':1011 'url':371,692 'use':41,209,356,408,461,553,842,862 'user':345,367,491,561,679,705 'user-satisfact':560 'valid':632 'valu':837,960 'verifi':195 'versus':858 'viabil':474 'web':32,35 'websit':20,78,86,214,249 'whether':448 'without':730 'work':135,298 'workflow':74,169,514,820 'workspac':198 'would':385","prices":[{"id":"d946a73d-da44-47e3-ad21-5905263722ab","listingId":"618717c4-33b0-4a9f-8e75-004a68a03964","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"anycap-ai","category":"anycap","install_from":"skills.sh"},"createdAt":"2026-04-18T22:22:31.060Z"}],"sources":[{"listingId":"618717c4-33b0-4a9f-8e75-004a68a03964","source":"github","sourceId":"anycap-ai/anycap/anycap-ai-tool-seo","sourceUrl":"https://github.com/anycap-ai/anycap/tree/main/skills/anycap-ai-tool-seo","isPrimary":false,"firstSeenAt":"2026-04-18T22:22:31.060Z","lastSeenAt":"2026-05-01T12:57:23.543Z"}],"details":{"listingId":"618717c4-33b0-4a9f-8e75-004a68a03964","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"anycap-ai","slug":"anycap-ai-tool-seo","github":{"repo":"anycap-ai/anycap","stars":32,"topics":["agent","agent-skills","claude-code","cli","coding-agent","skills"],"license":"mit","html_url":"https://github.com/anycap-ai/anycap","pushed_at":"2026-04-23T15:05:30Z","description":"The capability harness for AI agents. Skills over SDKs.","skill_md_sha":"a2b80c8da3a2296aab5808764647dfd426fcaa3f","skill_md_path":"skills/anycap-ai-tool-seo/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/anycap-ai/anycap/tree/main/skills/anycap-ai-tool-seo"},"layout":"multi","source":"github","category":"anycap","frontmatter":{"name":"anycap-ai-tool-seo","license":"MIT","description":"Guide for planning and auditing SEO for AI tool, SaaS, and product-led websites. Powered by AnyCap -- the capability runtime that equips AI agents with web search and web crawl through a single CLI. Use when Codex needs to define SEO ICPs, map search intent to page types, inspect live SERPs, write page briefs for tool/comparison/alternatives/pricing/tutorial pages, prioritize technical SEO foundations, plan citations or backlinks, or decide whether programmatic SEO is safe and worthwhile. Trigger on mentions of AI tool SEO, SaaS SEO, product-led SEO, search intent, page type mapping, vs pages, alternatives pages, pricing pages, directory submissions, backlink plans, citations, or pSEO.","compatibility":"Requires anycap CLI binary and internet access. Works with any agent that supports shell commands."},"skills_sh_url":"https://skills.sh/anycap-ai/anycap/anycap-ai-tool-seo"},"updatedAt":"2026-05-01T12:57:23.543Z"}}