agentleFS
JakeLabateJakeLabate/Claude-SEO-Skills/skills/keyword-cannibalization-audit/SKILL.md

keyword-cannibalization-audit

Skill3 starsChanged 5 months agoMITView on GitHub

Audit a website for keyword cannibalization (multiple pages competing for the same search query). Crawls pages and compares titles, H1s, and body keywords to find pages with duplicate title targets, clusters of pages whose keyword signatures overlap, and pages sharing the same primary keyword phrase. Use when the user asks to audit, check, or fix keyword cannibalization, pages competing for the same keyword, overlapping/competing content, keyword overlap, or which page should rank for a query on a website.

  • Installs packages

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user asks to:

    line 14
  2. Very specific:

    Write a report following references/report-template.md: summary, duplicate title targets first, then overlapping clusters (largest first) …

    line 65
  3. Very specific:

    If the user wants the report as a .docx (for example, to share with stakeholders or attach to a ticket), save the Markdown report to a file …

    line 86
  4. Very specific:

    If the user wants the raw findings as a spreadsheet (for filtering, sorting, or triage in Sheets or Excel), convert the audit's …

    line 96

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Keyword Cannibalization Audit

Audit a website for pages that compete with each other for the same query, and produce an actionable report. Findings are candidates to confirm: some overlap is legitimate; this skill surfaces the clusters and recommends a hierarchy.

When to use this skill

Use this skill when the user asks to:

  • Audit or fix keyword cannibalization
  • Find pages competing for the same keyword / query
  • Decide which page should rank for a topic and what to do with the rest
  • Review overlapping or competing content

Inputs to collect

  1. Site URL or URL list: a live site root to crawl (auto-seeds from /sitemap.xml), or a text file with --url-list.
  2. Scope: pages to crawl (default 500, --max-pages).
  3. Brand suffix: e.g. "| Acme Co" so brand words don't inflate title similarity (--brand-suffix).
  4. Overlap threshold: Jaccard similarity to flag competing pages (default 0.6, --overlap).

Workflow

Step 1: Crawl and capture target signals

Use scripts/extract_targets.py:

python3 scripts/extract_targets.py https://example.com --max-pages 500 --output target_inventory.json
# already crawled once (e.g. in a full SEO audit)? skip the crawl and reuse the shared cache:
# python3 scripts/fetch_pages.py https://example.com --output page_cache.json
# python3 scripts/extract_targets.py --from-cache page_cache.json --output target_inventory.json

For each page it records title, H1, meta description, noindex, word count, and the top body keywords by frequency.

Step 2: Run the audit checks

python3 scripts/audit_cannibalization.py target_inventory.json --brand-suffix "| Acme Co" --overlap 0.6 --output audit_report.json

Step 3: Evaluate the audit checks

Evaluate each check in references/audit-checks.md. Core checks:

CheckSeverity
Duplicate title targetHigh
Overlapping target cluster (keyword signatures)Medium
Shared primary keyword (title bigram)Low

Step 4: Produce the report

Write a report following references/report-template.md: summary, duplicate title targets first, then overlapping clusters (largest first) each with a recommended hierarchy, and a prioritized action list.

Step 5: Recommend fixes

  • For each cluster, name one primary page and a role for every other page: differentiate to a distinct sub-query, merge, or 301/canonicalize into the primary.
  • Frame as hierarchy, not deletion: supporting pages that target distinct intents and link up to the primary are healthy.
  • Always recommend confirming with Search Console query data before consolidating: this audit infers competition from on-page signals.
  • Related angles: meta-data-audit (duplicate titles) and content-quality-audit (duplicate bodies).
  • Base every grouping on observed signatures; never invent rankings.

Optional: export the report

As a Word document (.docx)

If the user wants the report as a .docx (for example, to share with stakeholders or attach to a ticket), save the Markdown report to a file and convert it:

python3 scripts/md_to_docx.py report.md --output report.docx

scripts/md_to_docx.py uses only the Python standard library (no pip install) and renders headings, tables, lists, links, bold/italic, and code blocks. Offer this whenever a user asks for a Word doc, a .docx, or a shareable/downloadable report.

As a CSV of findings (.csv)

If the user wants the raw findings as a spreadsheet (for filtering, sorting, or triage in Sheets or Excel), convert the audit's audit_report.json directly:

python3 scripts/findings_to_csv.py audit_report.json --output findings.csv

scripts/findings_to_csv.py is also standard-library only. It writes one row per finding, with check and severity columns prepended and list fields (e.g. the pages sharing a duplicate value) joined with ; . Unlike the .docx, which reformats the written report, the CSV is a direct dump of the structured findings: offer it whenever a user wants the data itself, a spreadsheet, or to slice findings by check or severity.

Resources

  • scripts/md_to_docx.py: convert the Markdown report into a Word (.docx) document (standard library only)
  • scripts/findings_to_csv.py: flatten the audit findings JSON into a CSV, one row per finding (standard library only)
  • references/audit-checks.md: full definitions, thresholds, and rationale
  • references/report-template.md: report output structure
  • scripts/extract_targets.py: crawl and capture keyword-target signals
  • scripts/audit_cannibalization.py: run cannibalization audit checks

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.