MCP HubMCP Hub
SKILL·CE41F2

seo-audit-orchestration

rampstackco
更新日 23 days ago
5 閲覧
953
132
953
GitHubで表示
メタmcpdesign

について

このスキルは、専門的なAhrefs MCPツールを単一のワークフローに順序立てて組み合わせることで、包括的なSEO監査を調整します。ヘルスチェック、デューデリジェンス、移行後の検証などの全シナリオ監査を想定して設計されています。結果として、バックリンク、キーワード、コンテンツ、トラフィック、技術的な健全性、ランキングを網羅した統合された要約レポートが生成されます。

クイックインストール

Claude Code

推奨
メイン
npx skills add rampstackco/claude-skills -a claude-code
プラグインコマンド代替
/plugin add https://github.com/rampstackco/claude-skills
Git クローン代替
git clone https://github.com/rampstackco/claude-skills.git ~/.claude/skills/seo-audit-orchestration

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

SEO Audit Orchestration

Run a complete SEO audit by sequencing the sibling audit skills in a defined order. Stack-agnostic. Assumes the Ahrefs MCP is connected. Produces a single rollup report that synthesizes findings across backlinks, keywords, content, traffic, technical health, and rankings.


When to use

  • Running a full SEO audit (quarterly, biannual, annual)
  • Pre-acquisition SEO due diligence
  • Post-migration verification (after content move, replatform, or domain change)
  • Onboarding a new client or new property
  • Building a baseline before a major SEO investment
  • Diagnosing chronic underperformance

When NOT to use

  • Single-dimension audits (use the specific child skill: seo-onpage, seo-backlink-audit, etc.)
  • Investigating a specific traffic drop (use seo-traffic-diagnosis)
  • Tactical questions like "which keywords should we target" (use seo-keyword-gap-audit)
  • Routine monitoring (use seo-rank-tracking)

Required inputs

  • The site or properties in scope
  • Target market and primary languages
  • Competitor set (3-5 properties)
  • Goal of the audit (baseline, due diligence, fix plan, growth roadmap)
  • Time and reporting constraints
  • Confirmation that the Ahrefs MCP is connected and the workspace has access to the target property

The framework: 6 phases of an end-to-end audit

A complete audit moves through six phases in order. Skipping phases produces gaps. Reordering them produces rework.

Phase 1: Scope and baseline

Define the audit before running it.

  • What is in scope (subdomains, paths, languages)
  • What is out of scope
  • Goal of the audit (baseline, fix plan, growth roadmap, due diligence)
  • Stakeholders and their priorities
  • Reporting format and length expectations

Output: a 1-page audit charter.

Phase 2: Data gather

Pull the raw data from Ahrefs and any companion sources.

Required pulls:

  • Site Explorer: organic keywords, organic traffic, top pages, top countries, referring domains, backlinks, anchor text profile
  • Site Audit: full crawl results
  • Keywords Explorer: target keyword universe and competitor keyword overlap
  • Content Explorer: top performing content in target topics
  • Rank Tracker: current tracked positions if set up

Companion pulls (not Ahrefs-native):

  • Search Console: query and page data, coverage issues
  • Analytics: traffic, conversions, segment by source
  • Server logs (if available): bot crawl behavior

Document data freshness for every pull. Stale data yields wrong conclusions.

Phase 3: Run the sub-audits

Run each child audit. Each produces its own findings doc.

Sub-auditSkillWhat it produces
Site healthseo-site-health-auditPrioritized technical fix backlog
Backlinksseo-backlink-auditProfile health, toxic list, reclamation list
Keywordsseo-keyword-gap-auditPrioritized opportunity list
Contentseo-content-gap-auditCreate/update/merge roadmap
Page-levelseo-onpagePer-page audit on top pages
AI searchseo-aeo-geoAI search readiness gaps

The child skills do the analysis. This skill sequences them and integrates the outputs.

Phase 4: Synthesize

Combine findings into themes. A list of 200 issues is not an audit. A short list of themes is.

Themes typically emerge in categories like:

  • Technical foundation gaps that cap upside
  • Content depth gaps in priority topics
  • Backlink profile concentration risks
  • Keyword opportunities the site is leaving on the table
  • Cannibalization or thin coverage
  • AI search readiness

Each theme should answer: what is happening, why it matters, what is the size of prize, what is the fix.

Phase 5: Prioritize

Rank the themes. Use a simple impact/effort matrix.

  • Quick wins: high impact, low effort. Do now.
  • Strategic plays: high impact, high effort. Plan and resource.
  • Maintenance: low impact, low effort. Backlog.
  • Avoid: low impact, high effort. Drop.

Tie each theme to a measurable target (organic clicks, ranked keywords in target band, conversions from organic).

Phase 6: Deliver

Produce the rollup report. See references/audit-rollup-template.md.

Structure:

  • Executive summary (1 page)
  • Themes and recommendations (1 page each; count per audit type, from the template's length-targets table)
  • Sub-audit findings (linked or appended)
  • Roadmap (next 90 days)

Walk stakeholders through it. Get commitment to the next 90 days of work.


Workflow

  1. Charter the audit. 1-page scope, goal, stakeholders, format.
  2. Confirm Ahrefs MCP access. Verify the workspace has the target property and recent data.
  3. Pull all data. Run the gather list in phase 2. Document freshness.
  4. Run each sub-audit. Use the child skills. Each produces its own findings doc.
  5. Synthesize themes. Hold to the theme count the template's length-targets table gives for this audit type. Each theme ties to an impact and a fix.
  6. Prioritize. Impact/effort matrix. Quick wins surface to the top.
  7. Draft the rollup. Use the template. Executive summary first.
  8. Review with the team. Pressure-test conclusions before stakeholder readout.
  9. Deliver. Walk stakeholders through. Get commitment to next 90 days.
  10. Schedule the next one. Audits decay. Rerun on a cadence.

Failure patterns

  • Audit without a goal. Produces a 60-page document nobody reads. Charter the audit first.
  • All findings, no themes. A list of 200 issues is data, not an audit. Synthesize into themes.
  • Skipping the sub-audits. Running one big audit instead of six focused ones produces shallow analysis everywhere.
  • No prioritization. "Here are 47 things to fix" gets nothing fixed. Rank them.
  • Stale data. Ahrefs index updates on a delay. Note freshness. Do not draw conclusions from week-old movement.
  • Tool worship. Ahrefs is one source. Search Console, analytics, and logs add ground truth. Triangulate.
  • Audit-to-audit drift. Running every audit differently makes trends impossible to spot. Standardize the structure.
  • No 90-day roadmap. Without a plan after the audit, the audit is shelfware.
  • Solo audit. Audits done alone miss context. Pull in the people who own the work.

Output format

A rollup audit report with:

  1. Executive summary.
  2. Audit charter (scope, goal, methodology).
  3. Themes and recommendations (each theme with what, why, size of prize, fix).
  4. Sub-audit appendix (linked outputs from each child skill).
  5. 90-day roadmap (sequenced work with owners and targets).
  6. Methodology notes (data sources, pull dates, caveats).

Total length, executive summary length, and theme count all vary by audit type: a quarterly health check is not a due-diligence audit. The length-targets table in references/audit-rollup-template.md owns those numbers per type. Whatever the type, the executive summary stays readable in 5 minutes.


If required data is unavailable

This skill's output depends on data, measurements, or tool results it cannot generate on its own. When a required input, tool, or data source is unavailable or unverifiable, the sanctioned output is the deliverable with the gap stated: what was needed, what was actually obtained or verified, and which parts of the output are affected. Fabricating, estimating, or interpolating a required number to complete the deliverable is never sanctioned. A stated gap is a complete answer.


Reference files

GitHub リポジトリ

rampstackco/claude-skills
パス: dist/codex/.agents/skills/seo-audit-orchestration
0
agent-skillsai-agentsanthropicclaudeclaude-aiclaude-code
FAQ

よくある質問

seo-audit-orchestration Skillとは何ですか?

seo-audit-orchestration はrampstackco が作成した Claude Skillです。Skillは、Claudeが必要に応じて読み込む指示とリソースをまとめ、追加の指示なしで seo-audit-orchestration に関連するタスクを実行できるようにします。

seo-audit-orchestration をインストールするには?

このページのインストールコマンドを使用してください。seo-audit-orchestration をプラグインとして Claude Code に追加するか、リポジトリを skills ディレクトリにクローンし、Claudeを再起動してSkillを読み込みます。

seo-audit-orchestration はどのカテゴリに属しますか?

seo-audit-orchestration は メタ カテゴリに属します。

seo-audit-orchestration は無料で利用できますか?

はい。seo-audit-orchestration は AIMCP に掲載されており、無料でインストールできます。

関連スキル

content-collections
メタ

このスキルは、Content Collections(Markdown/MDXファイルを型安全なデータコレクションに変換するTypeScriptファーストのツール)の本番環境でテストされた設定を提供します。Zodバリデーションによる型安全性を実現し、ブログ、ドキュメントサイト、コンテンツ重視のVite + Reactアプリケーション構築時にご利用ください。Viteプラグインの設定、MDXコンパイルから、デプロイ最適化、スキーマバリデーションまで、すべてを網羅しています。

スキルを見る
polymarket
メタ

このスキルは、開発者がPolymarket予測市場プラットフォームを活用したアプリケーション構築を可能にします。API統合による取引や市場データの取得に加え、WebSocketを介したリアルタイムデータストリーミングにより、ライブ取引や市場活動を監視できます。取引戦略の実装や、ライブ市場更新を処理するツールの作成にご利用ください。

スキルを見る
creating-opencode-plugins
メタ

このスキルは、開発者がコマンド、ファイル、LSP操作など25種類以上のイベントタイプにフックするOpenCodeプラグインを作成することを支援します。JavaScript/TypeScriptモジュール向けに、プラグイン構造、イベントAPI仕様、および実装パターンを提供します。カスタムイベント駆動ロジックでOpenCode AIアシスタントのライフサイクルをインターセプト、監視、または拡張する必要がある場合にご利用ください。

スキルを見る
sglang
メタ

SGLangは、高性能なLLMサービングフレームワークであり、RadixAttentionプレフィックスキャッシュを活用したJSON、正規表現、エージェントワークフロー向けの高速で構造化された生成を特長とします。特にプレフィックスが繰り返されるタスクにおいて、大幅に高速な推論を実現し、複雑な構造化出力やマルチターン対話に最適です。制約付きデコードが必要な場合や、広範なプレフィックス共有を伴うアプリケーションを構築する場合は、vLLMなどの代替案ではなくSGLangを選択してください。

スキルを見る