blog-taxonomy
Extract, suggest, and sync tags and categories for blog posts across all major CMS platforms. Supports WordPress REST API, Shopify GraphQL, Ghost Content API, Strapi REST/GraphQL, and Sanity GROQ. Generates tag suggestions from content analysis (keyword frequency, heading extraction, semantic groupi
By agricidaniel · 2,004 installs
npx skills add agricidaniel/claude-blog --skill blog-taxonomy
Source repository · Upstream listing
Blog Taxonomy
Manage tags, categories, and topic clusters across CMS platforms.
Commands
Command Purpose
/blog taxonomy suggest <file Extract candidate tags and categories from content
/blog taxonomy sync <cms Push taxonomy to CMS via authenticated API
/blog taxonomy audit [directory] Check for thin tags, orphan tags, taxonomy bloat
Tag Suggestion Workflow
Step 1: Parse Content Structure
Read the target file and extract:
All H2 and H3 headings (primary topic signals)
Bold and italic phrases (emphasis signals)
Existing frontmatter tags/categories if present
Step 2: Frequency Analysis
Scan the body text for high frequency phrases:
1 word terms: minimum 4 occurrences (excluding stop words)
2 word phrases: minimum 3 occurrences
3 word phrases: minimum 2 occurrences
Exclude common non tag words: articles, prepositions, conjunctions, pronouns.
Step 3: Semantic Grouping
Group related candidates into clusters:
Merge singular/plural variants (keep the more common form)
Merge hyphenated and non hyphenated forms
Group synonyms under the highest frequency term
Step 4: Deduplicate and Rank
Fuzzy match on slugified names (Levenshtein distance <= 2)
Do not auto merge short slugs under 5 characters using Levenshtein alone; require token overlap or manual review
Score each candidate: (frequency 2) + (heading presence 5) + (emphasis 1)
Return top 5 10 ranked suggestions
Output Format
CMS Adapters
Adapter Overview
CMS API Type Auth Method Tags Model
WordPress REST Application Passwords (base64) First class entities with IDs
Shopify GraphQL (Admin API) Admin API access token String array on Article
Ghost REST (Admin API) API key with JWT signing First class entities
Strapi REST or GraphQL API token (Bearer) User defined content type
Sanity GROQ / Mutations Project token (Bearer) Document type
WordPress Adapter
List tags :
Create tag :
List categories (hierarchical, supports parent field):
Create category :
Assign tags to post :
Pagination: follow X WP TotalPages header for full listing.
Shopify Adapter
Tags on Shopify are string arrays on the Article object, not first class entities.
Update article tags (GraphQL Admin API):
List all tags in use (GraphQL):
Auth header: X Shopify Access Token: {token}
Pagination: loop while pageInfo.hasNextPage is true, passing endCursor as
the next $cursor .
Note: REST API marked legacy Oct 2024. GraphQL required for new apps since Apr 2025.
Ghost Adapter
List tags :
Create tag :
JWT generation: sign with admin API key (id:secret format), iat = now, exp = 5 min,
audience = /admin/ .
Strapi Adapter
Endpoint auto generated from content types. Typical setup:
Pagination: increment pagination[page] until all pages are exhausted.
Strapi v4 responses use the data wrapper with attributes ; Strapi v5 uses
a flatter response shape. Detect the version or normalize both shapes before
deduplication. Check your content type schema for field names.
Sanity Adapter
Query tags (GROQ):
Create tag (Mutations API):
Default SANITY API VERSION to a current tested API date supplied by the
project environment; do not hard code it in generated requests.
Taxonomy Audit Workflow
Step 1: Inventory
Scan all posts in the target directory (or fetch from CMS). Build a map:
tag name [list of post files/IDs using this tag]
category name [list of post files/IDs]
Step 2: Health Checks
Check Threshold Action
Thin tag archives < 5 posts per tag Review for merge or noindex after traffic, intent, and link checks
Orphan tags 0 posts Recommend deletion
Tag bloat More than max(50, post count 0.25) total tags, adjusted for taxonomy purpose Recommend consolidation
Category depth 3 levels Recommend flattening
Uncategorized posts No category assigned Assign to appropriate category
Duplicate slugs Same slug, different name Merge into canonical version
Step 3: Recommendations
Group findings by priority:
Critical : orphan tags creating empty archive pages (crawl waste)
High : thin tags with < 5 posts after traffic, intent, and link checks
Medium : tag bloat above the scaled threshold (diluted taxonomy, harder to navigate)
Low : naming inconsistencies (mixed case, hyphen vs space)
Output Format
Site Wide Guidelines
Aim for 5 10 main categories per site (broad topics)
Tags should have at least 5 posts before creating an archive page
Use consistent slug format: lowercase, hyphen separated
Every post needs exactly 1 primary category
Tags per post: 3 8 recommended, never exceed 15
Environment Variables
Variable Purpose Example
CMS TYPE Platform identifier wordpress, shopify, ghost, strapi, sanity
CMS URL HTTPS base URL of the CMS https://example.com
CMS ALLOWED HOSTS Optional comma separated allowlist for CMS hosts example.com,admin.example.com
CMS USERNAME WordPress username when using Application Passwords editor@example.com
CMS API KEY Authentication credential WordPress app password, API token, or key
SANITY API VERSION Sanity API date for mutations v2026 07 01
These must be set in the shell environment. Never store credentials in files or
commit them to version control. The skill reads them via $CMS TYPE , $CMS URL ,
$CMS USERNAME , $CMS API KEY , and optional platform specific variables at runtime.
Security rule for CMS calls: require HTTPS, allow only http and https
parsing paths but send authenticated requests over HTTPS only, resolve DNS and
block loopback/private/link local/reserved IPs, validate redirects with the same
checks or disable redirects, cap timeouts at 10 seconds, and enforce
CMS ALLOWED HOSTS when set.
Error Handling
Missing environment variables : If CMS TYPE, CMS URL, or CMS API KEY is unset, or if WordPress lacks CMS USERNAME, report which variable is missing and provide the expected format
Invalid credentials : If the CMS API returns 401/403, report "Authentication failed check CMS USERNAME/CMS API KEY" and do not retry
Connection timeouts : If the CMS endpoint is unreachable after 10 seconds, report the timeout and suggest checking CMS URL
Duplicate tag slugs : If a tag already exists on the CMS, skip creation and note "Tag already exists: [name]"
Rate limits : If the CMS API returns 429, honor Retry After when present; otherwise use exponential backoff and retry once. Report if the limit persists
Unsupported CMS : If CMS TYPE is not one of the 5 supported platforms, list the valid options and exit