Semantic topic cluster planning and automated execution engine for claude-blog. Performs SERP-based keyword research, groups keywords by search intent and SERP overlap, builds a hub-and-spoke cluster architecture, generates an interactive SVG cluster map, and executes the full cluster by orchestrating blog-write calls with shared cluster context and automatic internal-link injection. Fills the strategy-to-execution gap: blog-strategy plans the blueprint, blog-cluster builds the house. Use when user says "blog cluster", "topic cluster", "content cluster", "cluster plan", "cluster execute", "pillar content", "hub and spoke", "content ecosystem", "cluster map".
Semantic topic cluster planning and automated execution engine for claude-blog. Performs SERP-based keyword research, groups keywords by search intent and SERP overlap, builds a hub-and-spoke cluster architecture, generates an interactive SVG cluster map, and executes the full cluster by orchestrating blog-write calls with shared cluster context and automatic internal-link injection. Fills the strategy-to-execution gap: blog-strategy plans the blueprint, blog-cluster builds the house. Use when user says "blog cluster", "topic cluster", "content cluster", "cluster plan", "cluster execute", "pillar content", "hub and spoke", "content ecosystem", "cluster map".
license
MIT
compatibility
Requires Claude Code and claude-blog (provides blog-write, blog-chart, blog-image)
Plans and executes entire interlinked content ecosystems from a single seed
keyword. Three layers: Semantic Clustering (the brain), Cluster Architecture
(the structure), and Execution Engine (the machine).
Adapted from the semantic-cluster-engine submission by Lutfiya Miller
(winner, AI Marketing Hub Pro Challenge, March 2026, 95/100 Exemplary).
Original repository: https://github.com/Drfiya/semantic-cluster-engine
This port keeps the Plan + Execute architecture and the cluster context
innovation, removes brand-specific (ScienceExperts.ai) styling and image
prompts, and routes through claude-blog's existing sub-skills.
Commands
Command
What it does
/blog cluster
Interactive. Asks whether to plan or execute.
/blog cluster plan <seed-keyword>
SERP-based semantic analysis. Outputs cluster plan + map.
/blog cluster plan --from strategy [path]
Imports existing blog-strategy cluster build plan and validates against SERP data.
/blog cluster execute [path-to-plan]
Sequential blog-write calls with cluster context and auto-interlinks.
Group the expanded keywords using the priority rules in references/semantic-clustering.md:
SERP Overlap Analysis is the primary signal. Two keywords with 4 or more shared top-10 results usually target the same intent and should be considered for one post.
Intent Classification assigns each keyword to informational, commercial, transactional, or navigational.
Entity Mapping identifies the people, products, frameworks, and organizations Google associates with the topic.
Grouping combines keywords that share intent and topical proximity. Each group becomes one branch of the hub and spoke.
Step 3. Cluster architecture design
Reference: references/cluster-architecture.md
Build the hub and spoke:
Pillar (hub): targets the broadest keyword. Word count 2,500 to 4,000. Template pillar-page. Links down to every spoke.
Spokes: each targets a long-tail cluster. Word count 1,200 to 1,800. Template auto-selected by intent. Links up to the pillar and across to siblings.
Cluster formation rules:
Normal mode: 2 to 5 clusters per pillar, 2 to 4 spokes per cluster, total 1 pillar plus 5 to 15 spokes.
Small-cluster mode: for narrow seeds, allow 1 pillar plus 2 to 4 spokes only after warning the user and asking for confirmation.
Every spoke targets a unique primary keyword (zero cannibalization).
Step 4. Internal link matrix
For each spoke S:
S to Pillar (always; anchor text uses the pillar's primary keyword).
Pillar to S (always; anchor text uses S's primary keyword).
S to other spokes in the same cluster (2 to 3 links each, contextual anchors).
S to spokes in adjacent clusters (0 to 1 links, only when semantically relevant).
Verify every spoke has at least 2 incoming links. Count total planned interlinks.
Step 5. Generate output files
All plan and execute artifacts go into a single subdirectory of the current working directory. Canonicalize the output directory, refuse symlinks, and reject writes outside the cluster directory. Slugs must match lowercase letters, numbers, and hyphens only; reject absolute paths, .., path separators inside slugs, and hidden control characters.
{"seed_keyword":"<seed>","generated_at":"YYYY-MM-DDTHH:MM:SSZ","pillar":{"id":"P","title":"Title of the pillar","primary_keyword":"broadest keyword","secondary_keywords":["..."],"search_volume_estimate":"high|medium|low","template":"pillar-page","word_count_target":3000,"cluster":"pillar"},"clusters":[{"name":"Cluster A: Theme","intent":"informational|commercial|transactional","color":"#2563eb","posts":[{"id":"A1","title":"Post title","primary_keyword":"long-tail keyword","secondary_keywords":["..."],"search_volume_estimate":"high|medium|low","template":"how-to-guide","word_count_target":1500,"links_to":["P","A2"],"links_from":["P","A2"]}]}],"total_posts":9,"total_interlinks":23,"estimated_total_words":18000}
Note: volume estimates are relative indicators (high, medium, low) derived from SERP signals, not absolute search volumes. For precise data, the user should consult Ahrefs, SEMrush, or DataForSEO (claude-blog provides the seo-dataforseo companion sibling).
cluster-map.html (XSS-safe)
A static, self-contained HTML file with an embedded SVG visualization. Hard rules for the writer:
No inline <script> blocks. No onclick, onmouseover, or any on* event attributes anywhere in the document.
No external script <src> references.
Every text label drawn into the SVG (titles, keywords, cluster names) must be escaped: replace & with &, < with <, > with >, " with ", and ' with ' before insertion.
Hover effects use CSS :hover only. No JavaScript.
Use <title> child elements inside SVG nodes for accessible tooltips (browser native, no script).
The map shows: a central pillar node, color-coded cluster groups radiating outward, spoke nodes within each cluster, and link lines connecting related nodes.
Step 6. Present plan to user
Show a summary table of clusters and posts, total interlinks, estimated words, and the file paths. Ask for confirmation before proceeding to execution. Wait for explicit user approval. Do not auto-execute.
Strategy Import: /blog cluster plan --from strategy [path]
Bridges blog-strategy output into a cluster plan.
Locate strategy output. Scan the current directory (or the user-specified path) for a file containing a Cluster Build Plan table with the columns # | Spoke Topic | Template | Target Keyword | Word Count | Internal Links (the format produced by /blog strategy).
Parse the table. Extract the pillar row (marked P), the spoke rows, template assignments, target keywords, word counts, and link relationships.
Validate and enrich. Run SERP overlap validation (Plan Phase Step 2) on each keyword. Add volume estimates and verify cluster groupings semantically.
If SERP data contradicts the strategy table, flag the conflict; do not silently override the user's strategic intent.
Generate cluster-plan.json and cluster-map.html using the same outputs as the standard Plan Phase.
Present the converted plan with any SERP-based adjustments highlighted, and wait for user confirmation.
Read cluster-plan.json from the user-specified path or the most recent cluster-*/cluster-plan.json in the working directory. Validate JSON structure. If no plan exists, return: "No cluster plan found. Run /blog cluster plan <seed-keyword> first."
Before reading a user-supplied plan path, canonicalize it relative to the current working directory. Reject absolute paths, .., symlinks, non-cluster-plan.json filenames, and any path outside the selected cluster directory. Constrain all generated post, image, map, and scorecard outputs to that cluster directory.
Step 2. Determine execution order
Pillar page first (so spokes can link to a known filename).
Then spokes, ordered by (cluster priority, search_volume_estimate desc, post id alphabetical). Cluster priority is the sum of estimated volumes within the cluster (highest first).
Alternating between clusters when more than 2 clusters exist diversifies the early content spread.
Step 3. For each post: build cluster context and call blog-write
Construct the cluster context block (full schema in references/execution-workflow.md) and prepend it to the topic prompt passed to the Task tool invoking blog-write. The context tells blog-write the cluster name, the post's role (pillar or spoke), the primary and secondary keywords, the chosen template, the word count target, the list of already-written posts (link to these), the list of upcoming posts (use [INTERNAL-LINK] placeholders), and the linking requirements for this post.
Evidence provenance propagation. The cluster context includes this directive
for every spoke and the pillar: "Keep material claims traceable to sources that
support them. Record dates, publisher/title details, retrieval notes,
methodology, and limitations when they help identify or interpret the source.
Use the publication's citation style. Drop unverifiable statistics and replace
contradicted ones."
This cascade preserves evidence discipline across batch execution without
turning a fixed source-record format into a score or gate. See
skills/blog/references/flow-alignment.md.
The context also instructs blog-write to run autonomously: skip topic clarification, skip outline approval, do not auto-detect template, do not pause.
Output format: standard markdown (.md) by default, matching blog-write's default. If the user explicitly requests HTML, set the platform target accordingly. Do not impose any brand-specific CSS or wordmark; that is the user's responsibility downstream.
Step 4. Per-post optional hero image
If blog-image is available, call /blog image generate via the Task tool to produce a 16:9 hero image for the post and place it in cluster-<slug>/images/<post-slug>-hero.png. Delegate provider selection to blog-image, prefer current Gemini image models when available, and record the model ID in the scorecard. If image generation is unavailable or fails, log a warning and continue without images. Image generation is non-blocking.
Step 5. Backward link injection
After each post is written:
Scan all previously written posts in the cluster directory for [INTERNAL-LINK: keyword -> filename.md] markers that reference the just-written post.
Replace each match with a real markdown link: [keyword](filename.md).
Add a cluster metadata block to the post's frontmatter on first pass (cluster:, cluster_role:, cluster_group:).
Step 6. Failure handling
If blog-write returns a quality-gate failure for any post, stop the batch immediately. Save progress, mark the failed post and all remaining posts as skipped, and tell the user to inspect or retry the failed post manually before continuing. Do not keep generating 5 to 15 posts after a quality failure, because that can create scaled-content-abuse risk.
If blog-write fails before content is generated because of a timeout or runtime error, log the failure in the scorecard and stop unless the user explicitly resumes after checking the cause.
If the user cancels mid-execution, save progress and note completed posts. On the next /blog cluster execute, detect already-written files and resume from the next unwritten post.
Step 7. Generate cluster-scorecard.md
After all attempted posts complete, produce a markdown scorecard covering:
Per-post status (written, failed, skipped) with file path and word count.
Per-post quality score (call /blog analyze on each in parallel via Task) and the cluster average.
Cluster cohesion score: a 0 to 100 composite of link reciprocity, intent diversity, template diversity, and keyword coverage (formula in references/execution-workflow.md).
Internal-link audit: outgoing and incoming counts per post, orphan flags, unresolved [INTERNAL-LINK] markers.
Cannibalization check: any two posts sharing primary keyword, or any pair with greater than 70% keyword overlap. Recommend running /blog cannibalization for a deeper pass.
Image generation summary: hero images generated vs. skipped.
Recommended next actions: schema generation (/blog schema), per-post SEO validation (/blog seo-check), repurposing (/blog repurpose).
Step 8. Final report
Return a concise summary to the user with totals, the scorecard path, and the next-action commands.
Output Artifacts (summary)
File
Phase
Format
cluster-plan.json
Plan
JSON
cluster-map.html
Plan
Static HTML + inline SVG, no JavaScript
pillar-<slug>.md
Execute
Markdown (or platform-detected format)
<spoke-slug>.md
Execute
Markdown (or platform-detected format)
images/<post-slug>-hero.png
Execute (optional)
PNG via blog-image
cluster-scorecard.md
Execute
Markdown
Quality Gates
Gate
Check
Action on fail
Cluster minimum
At least 2 clusters with at least 2 posts each
Warn during plan; suggest expansion
Cannibalization
No two posts share primary keyword
Block execution; require plan adjustment
Link completeness
Every post has 2 or more incoming internal links
Warn in scorecard
Length estimate
Pillars often need more depth than spokes
Pass to blog-write as optional planning context; never enforce a raw word minimum
Intent diversity
At least 2 distinct intents across clusters
Warn in scorecard
Template diversity
At least 3 distinct templates across the cluster
Warn in scorecard
Error Handling
Scenario
Action
Seed keyword too broad (more than 50 keyword variants)
Suggest narrowing the focus before clustering.
Seed keyword too narrow (fewer than 5 keyword variants)
Offer a smaller cluster (pillar plus 2 to 3 spokes) or suggest broadening.
WebSearch unavailable
Produce a draft plan only and require user confirmation, imported keyword data, or SERP data before execution.
blog-write fails a quality gate or content generation
Stop the batch, save progress, mark remaining posts as skipped, and require manual inspection or explicit resume.
blog-write not installed
Return: "blog-cluster requires claude-blog. Install it before running this skill."
cluster-plan.json malformed
Validate JSON and report parse errors with line numbers.
User cancels execution
Save progress; resume on next invocation with already-written posts auto-detected.
Optional image generation unavailable or failed
Skip hero image generation; warn once at start of execute, not per post.
Differentiation from related claude-blog skills
Skill
Role
What blog-cluster adds
blog-strategy
Plans 3 to 5 content pillars and draws hub-and-spoke diagrams as a strategic exercise
Performs SERP-based semantic clustering, then executes the plan into real, interlinked posts.
blog-calendar
Schedules publication dates around topic clusters
Does not build clusters or write posts; this skill does both.
blog-cannibalization
Detects keyword overlap in existing content
Diagnostic only. blog-cluster prevents cannibalization at the planning stage.
blog-write
Writes one post at a time
blog-cluster orchestrates many blog-write calls with shared cluster context and bidirectional linking.
blog-outline
Generates a single SERP-informed outline
blog-cluster generates an outline-equivalent across an entire cluster, then writes the posts.
blog-cluster is the general contractor: it analyzes the topic, draws the data-driven plan, and builds the entire structure from a single seed keyword.
