について
このスキルは、ウェブサイトのコンテンツライブラリを監査し、各コンテンツを「保持/更新/統合/リダイレクト/削除」のフレームワークで評価・分類します。コンテンツの劣化やキーワードカニバリゼーションといったSEO課題の解決を支援し、コンテンツの整理・更新要請やサイト全体のトラフィック低下を契機に発動します。このツールはスタックに依存せず、ブログ、マーケティングサイト、ナレッジベースなど、あらゆるプラットフォームで動作します。
クイックインストール
Claude Code
推奨npx skills add rampstackco/claude-skills -a claude-code/plugin add https://github.com/rampstackco/claude-skillsgit clone https://github.com/rampstackco/claude-skills.git ~/.claude/skills/seo-content-audit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
Content Audit
Inventory existing content, score it, and decide for each piece: keep, update, merge, redirect, or delete. Stack-agnostic. Works on blogs, marketing sites, knowledge bases, and product content.
When to use
- Inheriting a content library you did not create
- Diagnosing site-wide traffic decline
- Resolving cannibalization (two pages competing for the same query)
- Pre-migration cleanup
- Annual or semi-annual content health check
- Pruning before a redesign or replatform
When NOT to use
- Optimizing a single page (use
seo-onpage) - Planning new content (use
seo-keyword) - Comparing your content to competitors (use
seo-competitor) - Site-level technical issues (use
seo-technical)
Required inputs
- The site URL and access to crawl it (or a complete URL list)
- Search console access (or a 12-month export)
- Analytics access (sessions, conversions, engagement)
- A backlink tool (to identify pages with referring domains worth preserving)
The framework: 5 actions
For every content piece, the audit produces one of five decisions.
1. Keep
The page performs well, has clear intent, and needs no changes.
Signals:
- Top 10 ranking for its primary query
- Consistent traffic with no decay
- Healthy engagement (above-site-average time on page or interaction rate)
- Up-to-date information
2. Update
The page has potential but is underperforming due to fixable issues.
Signals:
- Page 2 ranking for high-value queries (rank 11 to 30)
- Traffic decay over the last 6 to 12 months
- Information gone stale
- Title or meta need rewriting for CTR
- Thin content that could expand to match competitor depth
- Missing schema or other technical hygiene
3. Merge
Two or more pages target overlapping queries and should consolidate.
Signals:
- Cannibalization (multiple pages ranking for the same query, none ranking well)
- Significant content overlap between pages
- Combined, they would outperform either alone
- Both have backlinks worth preserving
4. Redirect
The page has no future but has assets (links, equity) worth preserving.
Signals:
- No traffic, no rankings
- Holds backlinks (especially editorial ones)
- A relevant target page exists that would benefit from the equity
- Topic is still relevant but this specific page is not
5. Delete (and let return 404 or 410)
The page has no future and no assets worth preserving.
Signals:
- No traffic, no rankings, no backlinks
- Content is outdated and not worth updating
- Topic is no longer relevant
- Even thin or spam content from a previous era
Note: In most cases, return 410 (gone) for intentionally deleted content. 410 is processed faster than 404 and signals the deletion was deliberate.
Scoring inputs
Pull these for every URL before deciding:
| Metric | Source | Threshold for "low" |
|---|---|---|
| Sessions (last 90 days) | Analytics | <10/month |
| Organic traffic (last 90 days) | Search console or analytics | <5/month |
| Average position for top query | Search console | >30 |
| Impressions (last 90 days) | Search console | <100/month |
| Click-through rate | Search console | <1% (when impressions exist) |
| Referring domains | Backlink tool | 0 |
| Engagement (avg time on page) | Analytics | <30 seconds |
| Last meaningful update | Manual / git | >24 months |
| Word count | Crawler | <300 (for articles) |
| Internal links in | Crawler | 0 |
A page can survive low scores on a few metrics. A page that fails on most is a delete or redirect candidate.
Decision matrix
A simplified decision tree:
Has traffic? ─── Yes ──── Recent decay? ─── Yes ── UPDATE
│ │
│ └── No ─── KEEP
│
└── No ──── Has backlinks? ─── Yes ── Has relevant target? ─── Yes ── REDIRECT
│ │
│ └── No ─── UPDATE (rebuild)
│
└── No ──── Cannibalizing another page? ─── Yes ── MERGE
│
└── No ─── DELETE (410)
For overlapping pages, "merge" usually wins over "delete" because it preserves both link equity and any topical authority.
Workflow
- Inventory. Pull a complete URL list from the crawl, sitemap, and search console (some indexed pages may not be in the sitemap).
- Pull the metrics. Sessions, organic, search console rank/CTR, backlinks, last-modified date, word count.
- Score each URL. Use the framework. Mark a decision: Keep / Update / Merge / Redirect / Delete.
- Identify cannibalization clusters. Group URLs targeting the same query. Decide which becomes the canonical, what to merge, what to redirect.
- Sequence the work. Do redirects and deletes in batches. Plan updates by priority (highest-traffic-recovery potential first).
- Implement. With change tracking. Re-crawl after each batch to confirm no broken redirect chains.
- Measure. Track aggregate organic traffic 30, 60, 90 days post-audit.
Failure patterns
- Deleting pages with backlinks. Always check referring domains before deleting. A redirect preserves equity at near-zero cost.
- Updating pages that should be merged. Two thin pages updated to medium pages still cannibalize. Merge first.
- Merging without preserving the better URL. Pick the merge target by which URL has stronger signals (older URL, more backlinks, better URL slug, currently better ranking), not which one has more content.
- Mass-deleting low-traffic pages. Some have value: fresh pages still ramping, niche pages serving a specific audience, evergreen pages with seasonal traffic. Do not bulk-delete by sessions alone.
- Over-aggressive pruning of "old" content. Date alone is not a delete signal. Topic relevance and intent quality are.
- No post-audit measurement. Without measurement, you cannot tell if the audit worked.
Output format
Default output: a spreadsheet with one row per URL, plus a summary markdown report.
Spreadsheet columns:
- URL
- Page type (article, product, category, etc.)
- Sessions (90d), organic clicks (90d), impressions (90d), avg position
- Referring domains
- Word count
- Last modified
- Decision (keep / update / merge / redirect / delete)
- Merge target / redirect target (if applicable)
- Priority (1-5)
- Notes
Summary report:
- Inventory totals (URLs by decision)
- Cannibalization clusters identified
- Top 20 update priorities
- Redirect map (CSV)
- Delete list
- Implementation roadmap (sequenced by priority)
- Measurement plan
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
references/audit-template.md- Spreadsheet column definitions and report template.references/cannibalization-resolution.md- Detailed methodology for resolving cannibalization clusters.
GitHub リポジトリ
よくある質問
seo-content-audit Skillとは何ですか?
seo-content-audit 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-content-audit に関連するタスクを実行できるようにします。
seo-content-audit 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-content-audit 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-content-audit はどのカテゴリに属しますか?
seo-content-audit は メタ カテゴリに属します。
seo-content-audit は無料で利用できますか?
はい。seo-content-audit 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
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。
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。
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。
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。
