メニュー
Audit websites and pages for technical SEO, on-page SEO, schema markup, content discoverability, and answer-engine readiness. Use when prioritizing search visibility improvements.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Spec-Driven Development (SDD) methodology for AI software factories — where structured specifications are the input, AI agents generate the code, and quality gates enforce correctness at each pipeline phase. Use when designing a spec → review → decompose → implement → verify pipeline that any AI coding tool (Claude Code, Cursor, Hermes Agent, Devin, OpenHands) can follow.
Query your Jellyfin media server from the terminal — recently added media, search, item details, next-up episodes, library browsing, server info, and stats. Use when the user asks about Jellyfin, media server, movies, TV shows, next episodes, or their media library.
Multi-agent structured debate system. Spawn a panel of expert agents to debate any question, with convergence-aware iteration and typed synthesis output. Run via `agent-council` CLI. Compatible with any AI agent harness that supports agentskills.io skills (Claude Code, Cursor, Hermes Agent, OpenHands, etc.).
Reference for the Agent Skills open format — the directory structure, SKILL.md frontmatter schema, naming conventions, progressive disclosure model, and best practices for creating skills. Use this whenever creating, reviewing, or editing skills in this repository to ensure they follow the standard spec.
Verify work against explicit criteria using evidence, reproducible checks, and clear pass, conditional, or blocked verdicts. Use before declaring an artifact, implementation, or claim complete.
Manage Linear teams, projects, cycles, issues, comments, workflow state, and documents from a terminal through Linear's public GraphQL API. Use when a user asks to list, search, inspect, create, update, move, or comment on Linear work, or to find Linear documents. Do not use to embed a live agent inside Linear or to build an MCP integration.
| name | seo-audit |
| description | Audit websites and pages for technical SEO, on-page SEO, schema markup, content discoverability, and answer-engine readiness. Use when prioritizing search visibility improvements. |
| license | MIT |
| compatibility | Requires access to the site or page being audited. Platform-specific references are optional and must be applied only when relevant. |
| metadata | {"source_repo":"https://github.com/magnus919/hermes-profiles","source_commit":"867a555"} |
Full-spectrum audit for sites, articles, and content strategies. Covers both traditional SEO and Answer Engine Optimization (AEO/GEO) — the practice of structuring content so LLMs and AI answer engines (ChatGPT, Perplexity, Gemini, Claude, Google AI Overviews) extract and cite it.
Use assets/audit-report-template.md for a portable audit deliverable. If the host workflow uses artifact pyramids, that structure can be an optional presentation format rather than a prerequisite.
Overall Health: [Good / Fair / Poor] Score: [N/100]
[One paragraph summarizing the single most important thing to fix and expected impact.]
## Contents
| File | What it covers |
|------|----------------|
| `references/technical-seo.md` | Crawlability, indexability, robots.txt, sitemaps, page speed, Core Web Vitals, mobile-friendliness, HTTPS, canonical URLs, hreflang |
| `references/onpage-seo.md` | Title tags, meta descriptions, heading hierarchy, keyword placement, content quality, internal linking, image optimization |
| `references/schema-markup.md` | Schema.org types (TechArticle, FAQPage, HowTo, Article, BlogPosting, BreadcrumbList, Organization), JSON-LD format, Google rich results, validation |
| `references/content-strategy-seo.md` | Topic clusters, pillar pages, keyword research, gap analysis, SERP feature targeting, topical authority |
| `references/ghost-metadata.md` | Ghost CMS metadata fields (meta_title, meta_description, custom_excerpt), social media cards (OG, Twitter), code-injected schema (JSON-LD, FAQPage, TechArticle, @graph), per-post and site-wide injection, validation |
| `references/aeo-methodology.md` | Answer Engine Optimization — LLM RAG pipeline, answer-first content architecture, AEO-specific schema (FAQPage 3.2× boost), Ethan Smith/Graphite frameworks, question clusters, llms.txt, content negotiation, measurement |
| `assets/audit-report-template.md` | Blank report scaffold for new audits |
## When to Use
Load this skill when:
- Auditing a site for technical SEO issues
- Optimizing a new article for search and AI citation before publication
- Validating structured data on an existing page
- Completing Ghost CMS metadata (meta, social cards, schema injection) before publish
- Running an AEO readiness audit (llms.txt, content negotiation, question-cluster coverage)
- Developing a content strategy with SEO + AEO in parallel
- Diagnosing why a site or page isn't performing in search or AI citation
Do NOT load when:
- Only mechanical content fixes are needed; use the host agent's copy-editing workflow.
- Only writing is needed; use the host agent's writing workflow.
## Portability
This skill is intentionally host-neutral. Use your agent's normal mechanisms to load the references, templates, and scripts listed here. Do not assume a particular profile system, task orchestrator, memory service, or response-handoff format.