agentsclimarketplace

Seo cluster

Skill fusengine/agents/plugins/seo/skills/seo-cluster

Redefining development through cognitive automation and collaborative agent systems.

Install
npx -y skills add fusengine/agents --skill seo-cluster

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 22 stars22 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when building semantic keyword clusters from SERP overlap. Covers seed keyword expansion, Jaccard SERP overlap, intent grouping, pillar/cluster content architecture.

SKILL.md

2.9 KB, as published. Nobody here has run it

Semantic Clustering

Method

  1. Take seed keyword (e.g. "claude code")
  2. Fetch SERP for seed via WebFetch/fuse-browser (top 10 results)
  3. For each related keyword (autocomplete + "People Also Ask"):
    • Fetch its SERP
    • Compute overlap with seed's SERP (Jaccard index)
  4. Group keywords where SERP overlap ≥ 30% → same cluster
  5. Cluster center = highest-volume keyword

Output

# Cluster: "claude code"

## Pillar: claude code (vol: 12K, KD: 45)
- Intent: informational
- Featured: AI Overview, video

## Cluster pages
1. claude code installation (vol: 2.4K)
2. claude code vs cursor (vol: 1.8K)
3. claude code mcp servers (vol: 900)
4. claude code hooks (vol: 720)

Cluster by Buyer State (2026)

SERP overlap is the mechanical signal; the strategic axis is buyer state + intent, not surface similarity. Map each cluster keyword to a layer, then group by layer:

LayerStateIntent signal
L1Awareness"what is", "why", problem framing
L2Comparison"vs", "alternatives", "best for"
L3Evaluation"pricing", "reviews", "worth it"
L4Decision"buy", "near me", "demo", "signup"

Two keywords with high SERP overlap but different buyer states belong to different pages. Never merge clusters on lexical similarity alone.

Citation eligibility

AI Overviews capture ~30-60% of informational (L1/L2) CTR. For those layers, prioritize pages that produce verbatim-extractable answers per section over raw ranking — the goal is the LLM citation, not only the blue link.

Local vs Global Intent (2026)

AxisLOCAL intentGLOBAL intent
TypeProximity transactional/navigational ("near me", "[service] [city]")Informational / comparative
SERP featureTriggers the Map PackAI Overviews-heavy
AI Overviews exposureResists (local results stay link-driven)CTR eroded -40% to -58% on informational keywords
Target pageLocal page / city hubGlobal pillar

One intent = one URL. Split a local page from the global/pillar page when local volume and content justify it. Do not split if local volume is below ~30 searches/month, or if you cannot write 1200+ words genuinely distinct from the pillar.

Anti-Cannibalization Check

Before creating cluster pages, verify no existing page targets the same buyer state + intent. Use seo-content skill. The primary keyword is exclusive per page — pillar = [service] (no city), local = [service] [city]. See seo-internal-linking for the pillar/local/region URL architecture and link mesh.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.