seo-cluster

Name: seo-cluster
Author: AgriciDaniel

12kstars1.8kforks

How to install seo-cluster?

agricidaniel/claude-seo/seo-cluster

$curl -o .claude/agents/seo-cluster.md https://raw.githubusercontent.com/AgriciDaniel/claude-seo/HEAD/agents/seo-cluster.md

Installs into the current project.

Summary

Semantic topic clustering analysis using SERP overlap methodology. Expands seed keywords, performs pairwise SERP comparison, classifies intent, designs hub-and-spoke content architecture, and generates internal link matrices.

Files · 1

View on GitHub

agents/seo-cluster.md

1	# Semantic Topic Clustering
2
3	SERP-overlap-driven keyword clustering for content architecture. Groups keywords
4	by how Google actually ranks them (shared top-10 results), not by text similarity.
5	Designs hub-and-spoke content clusters with internal link matrices and generates
6	interactive cluster map visualizations.
7
8	Scripts: Located at the plugin root `scripts/` directory.
9
10	---
11
12	## Quick Reference
13
14	\| Command \| What it does \|
15	\|---------\|-------------\|
16	\| `/seo cluster plan <seed-keyword>` \| Full planning workflow: expand, cluster, architect, visualize \|
17	\| `/seo cluster plan --from strategy` \| Import from existing `/seo plan` output \|
18	\| `/seo cluster execute` \| Execute plan: create content via claude-blog or output briefs \|
19	\| `/seo cluster map` \| Regenerate the interactive cluster visualization \|
20
21	---
22
23	## Planning Workflow
24
25	### Step 1: Seed Keyword Expansion
26
27	Expand the seed keyword into 30-50 variants using WebSearch:
28
29	1. Related searches: Search the seed, extract "related searches" and "people also search for"
30	2. People Also Ask (PAA): Extract all PAA questions from SERP results
31	3. Long-tail modifiers: Append common modifiers: "best", "how to", "vs", "for beginners", "tools", "examples", "guide", "template", "mistakes", "checklist"
32	4. Question mining: Generate who/what/when/where/why/how variants
33	5. Intent modifiers: Add commercial modifiers: "pricing", "review", "alternative", "comparison", "free", "top"
34
35	Deduplication: Normalize variants (lowercase, strip articles), remove exact duplicates.
36	Target: 30-50 unique keyword variants. If under 30, run a second expansion pass
37	with the top PAA questions as seeds.
38
39	### Step 2: SERP Overlap Clustering
40
41	This is the core differentiator. Load `references/serp-overlap-methodology.md` for
42	the full algorithm.
43
44	Process:
45	1. Group keywords by initial intent guess (reduces pairwise comparisons)
46	2. For each candidate pair within a group, WebSearch both keywords
47	3. Count shared URLs in the top 10 organic results (ignore ads, featured snippets, PAA)
48	4. Apply thresholds:
49
50	\| Shared Results \| Relationship \| Action \|
51	\|---------------\|-------------\|--------\|
52	\| 7-10 \| Same post \| Merge into single target page \|
53	\| 4-6 \| Same cluster \| Group under same spoke cluster \|
54	\| 2-3 \| Interlink \| Place in adjacent clusters, add cross-links \|
55	\| 0-1 \| Separate \| Assign to different clusters or exclude \|
56
57	Optimization: With 40 keywords, full pairwise = 780 comparisons. Instead:
58	- Pre-group by intent (4 groups of ~10 = 4 x 45 = 180 comparisons)
59	- Only cross-check group boundary keywords
60	- Skip pairs where both are long-tail variants of the same head term (assume same cluster)
61
62	DataForSEO integration: If DataForSEO MCP is available, use `serp_organic_live_advanced`
63	instead of WebSearch for SERP data. Run `claude-seo run dataforseo_costs.py check serp_organic_live_advanced --count N`
64	before each batch. If `"status": "needs_approval"`, show cost estimate and ask user.
65	If `"status": "blocked"`, fall back to WebSearch.
66
67	### Step 3: Intent Classification
68
69	Classify each keyword into one of four intent categories:
70
71	\| Intent \| Signals \| Include in Clusters? \|
72	\|--------\|---------\|---------------------\|
73	\| Informational \| how, what, why, guide, tutorial, learn \| Yes \|
74	\| Commercial \| best, top, review, comparison, vs, alternative \| Yes \|
75	\| Transactional \| buy, price, discount, coupon, order, sign up \| Yes \|
76	\| Navigational \| brand names, specific product names, login \| No (exclude) \|
77
78	Remove navigational keywords from clustering. Flag borderline cases for
79	manual review. Keywords can have mixed intent (e.g., "best CRM software" is
80	both commercial and informational) -- classify by dominant intent.
81
82	### Step 4: Hub-and-Spoke Architecture
83
84	Load `references/hub-spoke-architecture.md` for full specifications.
85
86	Design the cluster structure:
87
88	1. Select the pillar keyword: Highest volume, broadest intent, most SERP overlap with other keywords
89	2. Group spokes into clusters: Each cluster is a subtopic area (2-5 clusters per pillar)
90	3. Assign posts to clusters: Each cluster gets 2-4 spoke posts
91	4. Select templates per post: Based on intent classification:
92
93	\| Intent Pattern \| Template Options \|
94	\|---------------\|-----------------\|
95	\| In

People who liked this also viewed

6 picks

Type

seo-cluster

12kstars1.8kforks

View on GitHub

How to install seo-cluster?

agricidaniel/claude-seo/seo-cluster

$curl -o .claude/agents/seo-cluster.md https://raw.githubusercontent.com/AgriciDaniel/claude-seo/HEAD/agents/seo-cluster.md

Installs into the current project.

Summary

Files · 1

View on GitHub

agents/seo-cluster.md

1	# Semantic Topic Clustering
2
3	SERP-overlap-driven keyword clustering for content architecture. Groups keywords
4	by how Google actually ranks them (shared top-10 results), not by text similarity.
5	Designs hub-and-spoke content clusters with internal link matrices and generates
6	interactive cluster map visualizations.
7
8	Scripts: Located at the plugin root `scripts/` directory.
9
10	---
11
12	## Quick Reference
13
14	\| Command \| What it does \|
15	\|---------\|-------------\|
16	\| `/seo cluster plan <seed-keyword>` \| Full planning workflow: expand, cluster, architect, visualize \|
17	\| `/seo cluster plan --from strategy` \| Import from existing `/seo plan` output \|
18	\| `/seo cluster execute` \| Execute plan: create content via claude-blog or output briefs \|
19	\| `/seo cluster map` \| Regenerate the interactive cluster visualization \|
20
21	---
22
23	## Planning Workflow
24
25	### Step 1: Seed Keyword Expansion
26
27	Expand the seed keyword into 30-50 variants using WebSearch:
28
29	1. Related searches: Search the seed, extract "related searches" and "people also search for"
30	2. People Also Ask (PAA): Extract all PAA questions from SERP results
31	3. Long-tail modifiers: Append common modifiers: "best", "how to", "vs", "for beginners", "tools", "examples", "guide", "template", "mistakes", "checklist"
32	4. Question mining: Generate who/what/when/where/why/how variants
33	5. Intent modifiers: Add commercial modifiers: "pricing", "review", "alternative", "comparison", "free", "top"
34
35	Deduplication: Normalize variants (lowercase, strip articles), remove exact duplicates.
36	Target: 30-50 unique keyword variants. If under 30, run a second expansion pass
37	with the top PAA questions as seeds.
38
39	### Step 2: SERP Overlap Clustering
40
41	This is the core differentiator. Load `references/serp-overlap-methodology.md` for
42	the full algorithm.
43
44	Process:
45	1. Group keywords by initial intent guess (reduces pairwise comparisons)
46	2. For each candidate pair within a group, WebSearch both keywords
47	3. Count shared URLs in the top 10 organic results (ignore ads, featured snippets, PAA)
48	4. Apply thresholds:
49
50	\| Shared Results \| Relationship \| Action \|
51	\|---------------\|-------------\|--------\|
52	\| 7-10 \| Same post \| Merge into single target page \|
53	\| 4-6 \| Same cluster \| Group under same spoke cluster \|
54	\| 2-3 \| Interlink \| Place in adjacent clusters, add cross-links \|
55	\| 0-1 \| Separate \| Assign to different clusters or exclude \|
56
57	Optimization: With 40 keywords, full pairwise = 780 comparisons. Instead:
58	- Pre-group by intent (4 groups of ~10 = 4 x 45 = 180 comparisons)
59	- Only cross-check group boundary keywords
60	- Skip pairs where both are long-tail variants of the same head term (assume same cluster)
61
62	DataForSEO integration: If DataForSEO MCP is available, use `serp_organic_live_advanced`
63	instead of WebSearch for SERP data. Run `claude-seo run dataforseo_costs.py check serp_organic_live_advanced --count N`
64	before each batch. If `"status": "needs_approval"`, show cost estimate and ask user.
65	If `"status": "blocked"`, fall back to WebSearch.
66
67	### Step 3: Intent Classification
68
69	Classify each keyword into one of four intent categories:
70
71	\| Intent \| Signals \| Include in Clusters? \|
72	\|--------\|---------\|---------------------\|
73	\| Informational \| how, what, why, guide, tutorial, learn \| Yes \|
74	\| Commercial \| best, top, review, comparison, vs, alternative \| Yes \|
75	\| Transactional \| buy, price, discount, coupon, order, sign up \| Yes \|
76	\| Navigational \| brand names, specific product names, login \| No (exclude) \|
77
78	Remove navigational keywords from clustering. Flag borderline cases for
79	manual review. Keywords can have mixed intent (e.g., "best CRM software" is
80	both commercial and informational) -- classify by dominant intent.
81
82	### Step 4: Hub-and-Spoke Architecture
83
84	Load `references/hub-spoke-architecture.md` for full specifications.
85
86	Design the cluster structure:
87
88	1. Select the pillar keyword: Highest volume, broadest intent, most SERP overlap with other keywords
89	2. Group spokes into clusters: Each cluster is a subtopic area (2-5 clusters per pillar)
90	3. Assign posts to clusters: Each cluster gets 2-4 spoke posts
91	4. Select templates per post: Based on intent classification:
92
93	\| Intent Pattern \| Template Options \|
94	\|---------------\|-----------------\|
95	\| In

People who liked this also viewed

6 picks

Type