本文へ移動
cccskills
無料GitHub で公開

information-architecture-seo

Convert a semantic core into crawlable SEO and LLM-friendly information architecture. Use this skill when the user asks for URL structure, page taxonomy, canonical rules, hreflang groups, page roles, pillar/topic/news/article/blog/project separation, multilingual route strategy, or a durable content model such as one short brief plus one longform article. It prevents duplicate public content bodies and hands link-graph work to internal-link-graph-architect.

インストール方法を見る

含まれるファイル(6)

  • SKILL.md4.1 KB
  • agents/openai.yaml401 B
  • assets/url-map.template.yaml3.1 KB
  • evals.json2.2 KB
  • references/url-architecture.md3.2 KB
  • validation-report.md1.4 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Information Architecture SEO

Use this skill after semantic-core-architect and before internal linking, schema, or LLM-readable layers.

Read references/url-architecture.md before producing a full URL map.

Owns

  • URL strategy;
  • page taxonomy;
  • page roles and content ownership;
  • canonical model;
  • hreflang groups;
  • index/noindex policy;
  • pillar/topic/news/article/blog/project role separation;
  • duplicate-content prevention.

Does Not Own

  • semantic core creation;
  • final page copy;
  • internal link graph details;
  • JSON-LD implementation;
  • rendered UI design;
  • external backlinks.

Workflow

  1. Read the semantic core, entity-topic map, site constraints, languages, and content model.
  2. Identify the canonical page role for each cluster/entity/topic.
  3. Define route patterns before individual URLs.
  4. Set canonical policy per page role.
  5. Define hreflang groups for localized equivalents.
  6. Mark page status: planned, draft, published, noindex, or deferred.
  7. Record duplicate-content risks and ownership boundaries.
  8. Produce url-map.yaml using assets/url-map.template.yaml.
  9. Hand off to internal-link-graph-architect and technical-seo-schema-engineer.

Canonical Rules

  • A page can be self-canonical when it has a distinct user/search role and visible content.
  • A short news brief and one expanded longform article can both be self-canonical when the brief is the fast news surface and the longform is the durable explanation surface.
  • Do not canonicalize a standalone brief to its longform by default.
  • Do not create extra public story variants beyond the declared model.
  • Topic and pillar pages must summarize and organize; they must not duplicate article bodies.
  • Locale alternates use hreflang; they do not replace canonical self-reference.

Multilingual Rules

  • Default language owns x-default unless the site has a separate language selector page.
  • Every localized page must declare its own canonical URL.
  • Hreflang groups must contain only true equivalents, not loosely related pages.
  • If translation quality is unknown, mark the localized page as draft or deferred, not published.

Safety And Privacy Boundaries

  • Do not expose admin, API, private dashboards, raw analytics, raw IP logs, secret files, or staging URLs as public indexable pages.
  • Use noindex or blocked internal routing for low-value utility pages; do not rely on public navigation hiding.
  • Do not weaken authentication, access control, or security headers for crawlability.
  • Do not place private source URLs, credentials, tokens, unpublished drafts, or internal notes in url-map.yaml, sitemap plans, or public LLM-facing artifacts.

Validation

Before marking work complete:

  • every page has URL, page type, locale, canonical, index policy, and rationale;
  • every language alternate has a coherent hreflang group;
  • every story has at most one brief and one longform per language;
  • topic pages do not duplicate article bodies;
  • final link graph details are left for internal-link-graph-architect;
  • schema implementation is left for technical-seo-schema-engineer.

Validate skill edits with:

python3 <codex-skills-dir>/senior-skill-architect/scripts/lint_production_skill.py ./skills/information-architecture-seo
python3 ./plans/seo-llm-skill-cluster/scripts/lint_skill_cluster.py .

Forward tests live in evals.json.

Output Shape

Return:

  1. URL strategy summary.
  2. Page role table.
  3. Canonical and hreflang policy.
  4. Duplicate-content risks.
  5. Handoff notes for internal linking and technical SEO/schema.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Validate proposed or existing backlinks for relevance, editorial legitimacy, link attributes, spam/toxicity risk, platform compliance, anchor quality, target-page fit, and monitoring evidence. Use this skill when the user asks whether an external link opportunity or placed backlink is safe and useful, and reject toxic, irrelevant, paid-undisclosed, fake, or spam placements.

日本語の概要は準備中です。原文の説明を表示しています。

sergekostenchuk/seo-llm-skill-cluster402026年6月12日 更新

Review public site content for editorial quality, source support, prompt residue, duplicate blocks, translation drift, hidden filler, and human usefulness before SEO or LLM-friendly publication. Use this skill when the user asks to quality-gate news briefs, longform explainers, blog posts, topic pages, project pages, translated content, or generated article drafts without changing the live publishing pipeline.

日本語の概要は準備中です。原文の説明を表示しています。

sergekostenchuk/seo-llm-skill-cluster402026年6月12日 更新

Find and score legitimate external authority and backlink opportunities as a dry-run register, using relevance, platform rules, risk, target-page fit, and explicit user approval gates. Use this skill when the user asks where links to a target site could be placed effectively, but never post, submit, DM, email, open PRs, or edit external accounts without separate explicit approval.

日本語の概要は準備中です。原文の説明を表示しています。

sergekostenchuk/seo-llm-skill-cluster402026年6月12日 更新

Design intentional internal link graphs for SEO, UX, and LLM-readable sites. Use this skill when the user asks for links between short briefs, longform articles, topics, projects, author pages, breadcrumbs, source trails, related stories, orphan-page checks, overlink checks, anchor intent, or validation that a link graph reinforces the canonical content model without creating duplicate story bodies or hidden links.

日本語の概要は準備中です。原文の説明を表示しています。

sergekostenchuk/seo-llm-skill-cluster402026年6月12日 更新

Plan and record evidence-backed LLM and AI-search citation checks across approved assistant/search surfaces with timestamped queries, locales, modes, cited URLs, snippets, screenshots or transcripts, and caveats. Use this skill when the user asks whether ChatGPT, Perplexity, Claude, Gemini, Copilot, or another assistant cites a target site, but do not claim citation without direct evidence.

日本語の概要は準備中です。原文の説明を表示しています。

sergekostenchuk/seo-llm-skill-cluster402026年6月12日 更新

Design human-visible, machine-readable website layers for AI assistants, RAG, and agentic search. Use this skill when the user asks for llms.txt, LLM discovery plans, visible TLDR or direct-answer blocks, source trails, entity pages, markdown alternates, AI crawler policy, topic-to-URL maps, assistant-readable public content, or LLM-friendly architecture that must preserve canonical SEO strategy without hidden bot-only facts or duplicate story bodies.

日本語の概要は準備中です。原文の説明を表示しています。

sergekostenchuk/seo-llm-skill-cluster402026年6月12日 更新

sergekostenchuk のスキルをすべて見る

このスキルの問題を報告する