blog-cluster
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", "pil
npx skills add AgriciDaniel/claude-blog --skill blog-cluster --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Plans and executes entire interlinked content ecosystems from a single seed keyword, covering semantic clustering, cluster architecture design, and an execution engine that runs blog-write calls with shared cluster context and automatic internal-link injection. It supports interactive planning and subsequent automated execution of a generated cluster plan.
How it works
- Commands include interactive /blog cluster to choose plan or execute, /blog cluster plan <seed-keyword> to generate a cluster plan with a map, and /blog cluster execute <path-to-plan> to run sequential blog-write calls with cluster context.
- Step-by-step Plan Phase: expands the seed keyword into a keyword universe via SERP-based methods; performs semantic clustering using SERP overlap, intent classification, and entity mapping; designs hub-and-spoke architecture with pillar (hub) and spokes (long-tail clusters); builds an internal link matrix ensuring proper linking between pillar and spokes and among spokes; generates output files cluster-plan.json, cluster-map.html and post files for execution; then presents a summary and waits for user confirmation.
- Step 3 Execute Phase: loads the plan, determines order (pillar first, spokes by cluster priority and volume, alternating across clusters), constructs a cluster context for each post, and calls blog-write with the context. Optionally generates hero images via blog-image and injects internal links post-writing. Handles failures by stopping and reporting.
- After execution, produces cluster-scorecard.md with per-post status, quality, coherence, link metrics, cannibalization checks, and action recommendations.
When to use it
Use when the user requests blog clustering, topic or content cluster planning, or cluster execution (e.g., phrases like "blog cluster", "topic cluster", "cluster plan", "cluster execute").
What it can touch
- Tools: claude-code and claude-blog (provides blog-write, blog-chart, blog-image)
- It routes to /blog strategy and /blog write as needed during execution. It can generate images via blog-image when available.
Caveats
- Outputs are scoped to a single cluster directory (cluster-<seed-keyword-slug>/) and enforce path validation. If external data sources or image generation fail, execution continues with warnings.
- Requires prior plan via /blog cluster plan or /blog cluster plan --from strategy. No auto-execution without explicit user confirmation.
# Blog Cluster (Semantic Topic Cluster Engine) 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. | ## Key references (load
- Commands
- Key references (load on demand)
- Cross-references to existing claude-blog skills
- Command Routing
- Plan Phase: /blog cluster plan <seed-keyword>
- Step 1. Seed keyword expansion
- Step 2. Semantic clustering
- Step 3. Cluster architecture design
- Step 4. Internal link matrix
- Step 5. Generate output files
- Step 6. Present plan to user
- Strategy Import: /blog cluster plan --from strategy [path]
- Execute Phase: /blog cluster execute [path-to-plan]
- Step 1. Load plan
What does the blog-cluster skill do?
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", "pil
How do I install it?
Run `npx skills add AgriciDaniel/claude-blog --skill blog-cluster --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From AgriciDaniel/claude-blog, a repository with 1,566 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.