Download brain/.raw/sources/claude-blog-skill/skills/blog-audit/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
Where does blog-audit live?
The publisher keeps it at https://github.com/AgriciDaniel/claude-blog.
Which agents can use blog-audit?
Claude, Cursor, and Codex can read a SKILL.md you add from the publisher's repository.
>
name: blog-audit
description: >
Full-site blog health assessment scanning all blog files for quality scores,
orphan pages, topic cannibalization, stale content, and AI citation readiness.
Runs canonical batch analysis before site-wide checks. Produces per-post scores
and a prioritized action queue. Use when user says "audit blog", "blog audit",
"site audit", "blog health", "audit all posts", "check all blogs".
user-invokable: true
argument-hint: "[directory]"
license: MIT
Blog Audit: Full-Site Health Assessment
Performs a comprehensive blog health assessment across all posts in the project.
Scans for quality scores, orphan pages, topic cannibalization, stale content,
and AI citation readiness. Uses the canonical analyzer JSON as the score source
and produces a prioritized action queue.
Audit Process
Step 1: Discover Blog Files
Scan the project for all blog content files:
Recursively glob for .md, .mdx, .html, .astro, .svelte, .vue,
.tsx, and .jsx in common blog directories and CMS export folders
Common paths to check:
content/
posts/
blog/
src/content/
_posts/
pages/blog/
articles/
content/blog/**
CMS export folders explicitly provided by the user
If no blog files are found in standard locations, ask for an allow-listed root
or only search user-approved content directories. Do not scan the entire project
root by default.
Step 2: Canonical Batch Analysis
Run canonical analyzer output first and use it as the source of per-post scores:
Process files in chunks, cap parallel follow-up work to a small fixed number,
respect context limits, and aggregate deterministic JSON with file, score,
categories, issues, and metadata. Layer the site-wide checks below on top
of analyzer JSON, not separate scoring rubrics.
Content Quality Layer
Score each post on the 30-point content quality scale
Check paragraph length (target 40-80 words, hard limit 150)
Check sentence length (target 15-20 words)
Evaluate heading structure and question-format headings
Assess readability using persona and content type: consumer content favors
easier bands, professional content can be moderate, and technical content may
be denser when clarity remains high
SEO Optimization Layer
Check on-page SEO elements per post:
Title tag length (40-60 acceptable, 50-60 ideal, preview warning only)
Meta description is concise and page-specific. Statistics are optional and
must be visible and sourced
H1 presence and uniqueness
Image alt text coverage
Internal and external link counts
URL slug quality
Schema Validation Layer
Detect structured data across all posts
Validate Article/BlogPosting, Person, Organization, and BreadcrumbList schema completeness
If FAQPage exists, validate it as optional entity markup only, not a Google rich result
Normalize dateModified, lastUpdated, updated, and lastmod, including
timezone-normalized generated schema, then require freshness parity
Add site-wide technical checks before final recommendations:
Validate sitemap coverage, robots.txt, noindex directives, canonical tags,
redirects, HTTP status codes, hreflang, and internal canonical consistency
Use blog-google when available for Core Web Vitals, GSC queries, URL
Inspection, indexing status, and GA4 context
Report skipped optional checks with reasons such as
SKIPPED: credentials unavailable
Step 3: Topic Cannibalization Detection
Analyze across all posts for keyword competition:
Extract primary keyword/topic from each post:
Title text
H1 heading
Meta description
First paragraph
Normalize keywords with stopword handling, lemmatization, locale awareness,
and intent modifiers
Cluster by intent using analyzer data, embeddings or explicit confidence,
GSC query-to-URL data when available, and SERP overlap where available
Flag competing posts with one of these recommendations:
Merge: Combine two weak posts into one strong post
Redirect: 301 redirect the weaker post to the stronger one after
preserving backlinks, validating a redirect map, and updating internal
links
Differentiate: Adjust focus so posts target distinct intents
Step 4: Orphan Page Detection
Build and analyze the internal link graph:
Normalize URLs against site config and sitemap, including relative links,
same-domain absolutes, trailing slashes, generated routes, anchors, and slug
mappings
Build an adjacency map: { page -> [pages it links to] }
Build a reverse map: { page -> [pages linking to it] }
Identify orphan pages: posts with zero inbound internal links
Identify dead-end pages: posts with zero outbound internal links
For each orphan, recommend 2-3 existing posts that should link to it
based on topic relevance
### Stale Content
| Post | Last Updated | Days Stale | Priority | Refresh Effort |
|------|-------------|------------|----------|----------------|
| [file] | [date] | [N] | High/Med/Low | Light/Moderate/Heavy |
Step 7: Save Report
Save timestamped Markdown and JSON exports under reports/, for example
reports/blog-audit-YYYY-MM-DD.md and reports/blog-audit-YYYY-MM-DD.json.
Do not overwrite a previous audit report.
After saving, inform the user:
Report locations: [project-root]/reports/blog-audit-YYYY-MM-DD.md and
[project-root]/reports/blog-audit-YYYY-MM-DD.json
Summary of findings (total posts, average score, critical issues count)
Suggest running /blog analyze <file> on the lowest-scoring post first
Suggest running /blog flow optimize for AI-citation SEO checks on key posts
Cross-reference
For evidence-led audit prompts beyond this site-wide health pass, see /blog flow optimize (visibility, CTR, schema, extraction audits) and /blog flow win (dual-surface scorecard, conversion audit).
How do I install blog-audit?
Download brain/.raw/sources/claude-blog-skill/skills/blog-audit/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
Where does blog-audit live?
The publisher keeps it at https://github.com/AgriciDaniel/claude-blog.
Which agents can use blog-audit?
Claude, Cursor, and Codex can read a SKILL.md you add from the publisher's repository.