Communitygithub.com

Rylaispirit/rylai-codex-hermes-skills

Perform an evidence-led SEO audit using accessible pages, source code, crawl data, and current search documentation without assuming missing plugins.

rylai-codex-hermes-skills 是什麼?

rylai-codex-hermes-skills is a Claude Code agent skill that perform an evidence-led SEO audit using accessible pages, source code, crawl data, and current search documentation without assuming missing plugins.

相容平台✓Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/Rylaispirit/rylai-codex-hermes-skills/tree/HEAD/skills/seo

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

Rylai Codex-Hermes-Claude Edition | Maintained and adapted by Rylai

Runtime Compatibility

  • Codex: install under ~/.agents/skills/seo.
  • Hermes: install under ~/.hermes/skills/seo or expose the bundle through skills.external_dirs.
  • Claude Code: install under ~/.claude/skills/seo or <project>/.claude/skills/seo.
  • Claude.ai and Cowork: upload and enable the matching per-skill ZIP.
  • Resolve bundled files relative to this skill directory; do not depend on paths from another machine.
  • Check tools, packages, credentials, network access, and runtime capabilities before execution.
  • Upstream package status: adapted-core. The main workflow was rewritten to avoid missing legacy resources; advanced upstream features may remain unavailable.

Portable SEO Audi

Audit the exact website or page using evidence available to the current runtime.

Workflow

  1. Confirm the target URL, market, language, business type, and audit scope.
  2. Fetch or browse the live page and inspect rendered content, HTML, metadata, links, and indexability signals.
  3. Review technical basics: status codes, canonicals, robots directives, sitemap exposure, headings, structured data, mobile behavior, and performance evidence.
  4. Review search intent, page usefulness, internal linking, duplication, and content gaps.
  5. Separate observed defects from recommendations that need Search Console, analytics, backlink, or crawl data.
  6. Prioritize findings by impact, confidence, effort, and affected routes.
  7. Re-check current search-engine documentation before asserting time-sensitive rules.

Boundaries

  • Do not claim a full crawl, Search Console result, Core Web Vitals measurement, or backlink audit without the relevant data.
  • Do not invent rankings, traffic, index status, or competitor metrics.
  • Prefer narrow implementation fixes tied to evidence.

Individual skills in this repo

This repo contains 1 individual skill — each has its own dedicated page.

相關技能