content-quality-audit
Skill3 starsChanged 5 months agoMITView on GitHub
Audit a website's content quality for SEO. Crawls pages and measures visible word count, text-to-HTML ratio, and content fingerprints to find thin content, exact duplicate body text across pages, near-duplicate (templated/boilerplate) pages, pages that are mostly markup with little text, and pages missing an H1. Use when the user asks to audit, check, or fix thin content, duplicate or near-duplicate content, low-value pages, content depth, doorway pages, or text-to-HTML ratio on a website.
- Installs packages
In this repository19 other files it gives its agents.
- canonical-tag-auditSkill
- core-web-vitals-auditSkill
- external-link-auditSkill
- full-seo-auditSkill
- heading-structure-auditSkill
- image-seo-auditSkill
- internal-link-auditSkill
- keyword-cannibalization-auditSkill
- llms-txt-auditSkill
- meta-data-auditSkill
- mixed-content-auditSkill
- open-graph-auditSkill
- pagination-auditSkill
- redirect-auditSkill
- robots-txt-auditSkill
- schema-markup-auditSkill
- site-architecture-auditSkill
- sitemap-auditSkill
- soft-404-auditSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Use this skill when the user asks to:
- Distinctive: line 18
Check content depth or text-to-HTML ratio
- Very specific: line 66
Write a report following references/report-template.md: summary with the median word count for calibration, thin and duplicate content …
- Very specific: line 77
Missing H1: add one descriptive H1 (see heading-structure-audit).
- Very specific: line 86
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 …
- Very specific: line 96
If the user wants the raw findings as a spreadsheet (for filtering, sorting, or triage in Sheets or Excel), convert the audit's …
≈ “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.
Files
Content Quality Audit
Audit a website's content for thinness and duplication, and produce an actionable report. These checks surface pages unlikely to rank or add value; they are signals for human review, calibrated to the site.
When to use this skill
Use this skill when the user asks to:
- Audit or fix thin / low-value content
- Find duplicate or near-duplicate pages (templated/boilerplate content)
- Check content depth or text-to-HTML ratio
- Identify doorway-style pages
Inputs to collect
- Site URL or URL list: a live site root to crawl (auto-seeds from
/sitemap.xml), or a text file with--url-list. - Scope: pages to crawl (default 500,
--max-pages). - Thresholds:
--thin-words(default 300) and--similarity(default 0.85). Calibrate to the content type before running.
Workflow
Step 1: Crawl and measure content
Use scripts/extract_content.py:
python3 scripts/extract_content.py https://example.com --max-pages 500 --output content_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_content.py --from-cache page_cache.json --output content_inventory.jsonFor each page it records visible word count, text-to-HTML ratio, title, H1, noindex, an exact content hash, and a 32-value MinHash signature for fast near-duplicate detection.
Step 2: Run the audit checks
python3 scripts/audit_content.py content_inventory.json --thin-words 300 --similarity 0.85 --output audit_report.jsonStep 3: Evaluate the audit checks
Evaluate each check in references/audit-checks.md. Core checks:
| Check | Severity |
| Thin content (below word threshold) | High |
| Duplicate content (identical body) | High |
| Near-duplicate content (high MinHash similarity) | Medium |
| Low text-to-HTML ratio | Medium |
| Missing H1 | Low |
Step 4: Produce the report
Write a report following references/report-template.md: summary with the median
word count for calibration, thin and duplicate content first, near-duplicate
clusters grouped as patterns, and a prioritized action list.
Step 5: Recommend fixes
- Thin content: expand with useful content, consolidate several thin pages, or
noindexpages that exist for non-search reasons. - Duplicate/near-duplicate: canonicalize to one URL, consolidate, or add
substantial unique content (cross-check
canonical-tag-audit). - Low ratio: increase real content or trim boilerplate markup.
- Missing H1: add one descriptive H1 (see
heading-structure-audit). - Always caveat JavaScript-rendered pages: this crawler doesn't run JS, so verify a flagged page isn't simply rendered client-side.
- Base every recommendation on the measured signals; never invent content.
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.docxscripts/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.csvscripts/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 rationalereferences/report-template.md: report output structurescripts/extract_content.py: crawl and measure content signalsscripts/audit_content.py: run content-quality audit checks
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
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.

