blog-cannibalization

Name: blog-cannibalization
Author: AgriciDaniel

1.3kinstalls251forks

How to install blog-cannibalization?

agricidaniel/claude-blog/blog-cannibalization

$npx -y skills add AgriciDaniel/claude-blog --skill blog-cannibalization

Installs into the current project.

Summary

Detect keyword cannibalization across blog posts by extracting primary keywords from titles and headings, clustering semantically similar targets, and flagging posts competing for the same search intent. Supports local-only mode (grep-based) and DataForSEO API mode (Page Intersec

Files · 1

View on GitHub

SKILL.md

1	# Blog Cannibalization - Keyword Overlap Detection
2
3	Detect when multiple blog posts compete for the same search keywords. Two modes:
4	local-only analysis (default) and DataForSEO API mode for SERP-level data.
5
6	## Two Modes
7
8	\| Mode \| Flag \| Cost \| Data Source \|
9	\|------\|------\|------\|-------------\|
10	\| Local \| (default) \| Free \| File content analysis via Grep/Read \|
11	\| API \| `--api` \| ~$0.01/call \| DataForSEO Page Intersection + Ranked Keywords \|
12
13	Local mode works without any API keys. API mode requires DataForSEO credentials
14	set as environment variables: `DATAFORSEO_LOGIN` and `DATAFORSEO_PASSWORD`.
15
16	## Local Mode Workflow
17
18	### Step 1: Scan Blog Files
19
20	Use Glob to find all content files in the target directory:
21	- Patterns: `*/.md`, `*/.mdx`, `*/.html`
22	- Skip files in `node_modules/`, `.git/`, `drafts/`
23
24	### Step 2: Extract Primary Keywords
25
26	For each file, read and extract keyword signals from:
27	- Title tag or H1 heading (highest weight)
28	- H2 headings (medium weight)
29	- First paragraph (supporting signal)
30	- Meta description if present in frontmatter
31
32	Primary keyword extraction method:
33	1. Tokenize title and H1 into 1-gram, 2-gram, and 3-gram phrases
34	2. Score each phrase by frequency across title + H2s + first paragraph
35	3. Select the top-scoring 2-3 word phrase as the primary keyword
36	4. Record secondary keywords from H2 headings
37
38	### Step 3: Cluster by Similarity
39
40	Group posts into clusters using these matching rules (in priority order):
41
42	1. Exact match - identical primary keyword across 2+ posts
43	2. Stem match - same root word (e.g., "optimize" vs "optimization")
44	3. Semantic overlap - Claude determines that two keywords target the same
45	search intent (e.g., "best CRM software" vs "top CRM tools 2026")
46	4. Subset match - one keyword contains another (e.g., "email marketing"
47	vs "email marketing for startups")
48
49	### Step 4: Score and Flag
50
51	For each cluster with 2+ posts, assess severity and generate a recommendation.
52
53	### Step 5: Output Report
54
55	Display the results table and per-cluster recommendations.
56
57	## API Mode Workflow (DataForSEO)
58
59	Requires the `--api` flag. Uses WebFetch to call DataForSEO endpoints.
60
61	### Endpoints Used
62
63	Page Intersection - find keywords where multiple URLs rank:
64	```
65	POST https://api.dataforseo.com/v3/dataforseo_labs/google/page_intersection/live
66	Authorization: Basic <base64(login:password)>
67
68	{
69	"pages": {
70	"1": "https://example.com/post-a",
71	"2": "https://example.com/post-b"
72	},
73	"language_code": "en",
74	"location_code": 2840
75	}
76	```
77	Cost: ~$0.01 per call. Returns overlapping keywords with position, volume, CPC.
78
79	Ranked Keywords - get all keywords a single URL ranks for:
80	```
81	POST https://api.dataforseo.com/v3/dataforseo_labs/google/ranked_keywords/live
82
83	{
84	"target": "https://example.com/post-a",
85	"language_code": "en",
86	"location_code": 2840
87	}
88	```
89
90	### API Analysis Steps
91
92	1. Collect all published URLs from the user (or sitemap)
93	2. Run Ranked Keywords for each URL to build keyword profiles
94	3. Run Page Intersection for URL pairs that share keyword clusters
95	4. Calculate severity using the formula below
96	5. Output enriched report with search volume and position data
97
98	## Severity Scoring
99
100	Four severity levels based on overlap signals:
101
102	\| Level \| Criteria \| Action Urgency \|
103	\|-------\|----------\|----------------\|
104	\| Critical \| Same exact keyword, both pages in top 20 \| Immediate \|
105	\| High \| Same keyword cluster, one page outranks the other \| This week \|
106	\| Medium \| Related keywords with partial SERP overlap \| This month \|
107	\| Low \| Semantic similarity but different confirmed intents \| Monitor \|
108
109	### Severity Formula (API Mode)
110
111	```
112	severity_score = overlap_count x avg_search_volume x (1 / position_gap)
113	```
114
115	Where:
116	- `overlap_count` = number of shared ranking keywords
117	- `avg_search_volume` = mean monthly volume of shared keywords
118	- `position_gap` = absolute difference in average ranking position (min 1)
119
120	Higher score = more urgent cannibalization problem.
121
122	### Severity Heuristic (Local Mode)
123
124	Without SERP data, use a simplified scoring:
125	- Critical: Exact primary keyword match between posts
126	- High: Stem match on primary keyword, or 3+ shared H2 keywords
127	- Medium: Semantic overlap on primary keyword
128	- Low: Subset match only, or shared secondary keywords
129
130	## Output Format
131
132	### Summary Table
133
134	```
135	\| Post A \| Post B \| S

People who liked this also viewed

6 picks

Type

blog-cannibalization

1.3kinstalls251forks

View on GitHub

How to install blog-cannibalization?

agricidaniel/claude-blog/blog-cannibalization

$npx -y skills add AgriciDaniel/claude-blog --skill blog-cannibalization

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Blog Cannibalization - Keyword Overlap Detection
2
3	Detect when multiple blog posts compete for the same search keywords. Two modes:
4	local-only analysis (default) and DataForSEO API mode for SERP-level data.
5
6	## Two Modes
7
8	\| Mode \| Flag \| Cost \| Data Source \|
9	\|------\|------\|------\|-------------\|
10	\| Local \| (default) \| Free \| File content analysis via Grep/Read \|
11	\| API \| `--api` \| ~$0.01/call \| DataForSEO Page Intersection + Ranked Keywords \|
12
13	Local mode works without any API keys. API mode requires DataForSEO credentials
14	set as environment variables: `DATAFORSEO_LOGIN` and `DATAFORSEO_PASSWORD`.
15
16	## Local Mode Workflow
17
18	### Step 1: Scan Blog Files
19
20	Use Glob to find all content files in the target directory:
21	- Patterns: `*/.md`, `*/.mdx`, `*/.html`
22	- Skip files in `node_modules/`, `.git/`, `drafts/`
23
24	### Step 2: Extract Primary Keywords
25
26	For each file, read and extract keyword signals from:
27	- Title tag or H1 heading (highest weight)
28	- H2 headings (medium weight)
29	- First paragraph (supporting signal)
30	- Meta description if present in frontmatter
31
32	Primary keyword extraction method:
33	1. Tokenize title and H1 into 1-gram, 2-gram, and 3-gram phrases
34	2. Score each phrase by frequency across title + H2s + first paragraph
35	3. Select the top-scoring 2-3 word phrase as the primary keyword
36	4. Record secondary keywords from H2 headings
37
38	### Step 3: Cluster by Similarity
39
40	Group posts into clusters using these matching rules (in priority order):
41
42	1. Exact match - identical primary keyword across 2+ posts
43	2. Stem match - same root word (e.g., "optimize" vs "optimization")
44	3. Semantic overlap - Claude determines that two keywords target the same
45	search intent (e.g., "best CRM software" vs "top CRM tools 2026")
46	4. Subset match - one keyword contains another (e.g., "email marketing"
47	vs "email marketing for startups")
48
49	### Step 4: Score and Flag
50
51	For each cluster with 2+ posts, assess severity and generate a recommendation.
52
53	### Step 5: Output Report
54
55	Display the results table and per-cluster recommendations.
56
57	## API Mode Workflow (DataForSEO)
58
59	Requires the `--api` flag. Uses WebFetch to call DataForSEO endpoints.
60
61	### Endpoints Used
62
63	Page Intersection - find keywords where multiple URLs rank:
64	```
65	POST https://api.dataforseo.com/v3/dataforseo_labs/google/page_intersection/live
66	Authorization: Basic <base64(login:password)>
67
68	{
69	"pages": {
70	"1": "https://example.com/post-a",
71	"2": "https://example.com/post-b"
72	},
73	"language_code": "en",
74	"location_code": 2840
75	}
76	```
77	Cost: ~$0.01 per call. Returns overlapping keywords with position, volume, CPC.
78
79	Ranked Keywords - get all keywords a single URL ranks for:
80	```
81	POST https://api.dataforseo.com/v3/dataforseo_labs/google/ranked_keywords/live
82
83	{
84	"target": "https://example.com/post-a",
85	"language_code": "en",
86	"location_code": 2840
87	}
88	```
89
90	### API Analysis Steps
91
92	1. Collect all published URLs from the user (or sitemap)
93	2. Run Ranked Keywords for each URL to build keyword profiles
94	3. Run Page Intersection for URL pairs that share keyword clusters
95	4. Calculate severity using the formula below
96	5. Output enriched report with search volume and position data
97
98	## Severity Scoring
99
100	Four severity levels based on overlap signals:
101
102	\| Level \| Criteria \| Action Urgency \|
103	\|-------\|----------\|----------------\|
104	\| Critical \| Same exact keyword, both pages in top 20 \| Immediate \|
105	\| High \| Same keyword cluster, one page outranks the other \| This week \|
106	\| Medium \| Related keywords with partial SERP overlap \| This month \|
107	\| Low \| Semantic similarity but different confirmed intents \| Monitor \|
108
109	### Severity Formula (API Mode)
110
111	```
112	severity_score = overlap_count x avg_search_volume x (1 / position_gap)
113	```
114
115	Where:
116	- `overlap_count` = number of shared ranking keywords
117	- `avg_search_volume` = mean monthly volume of shared keywords
118	- `position_gap` = absolute difference in average ranking position (min 1)
119
120	Higher score = more urgent cannibalization problem.
121
122	### Severity Heuristic (Local Mode)
123
124	Without SERP data, use a simplified scoring:
125	- Critical: Exact primary keyword match between posts
126	- High: Stem match on primary keyword, or 3+ shared H2 keywords
127	- Medium: Semantic overlap on primary keyword
128	- Low: Subset match only, or shared secondary keywords
129
130	## Output Format
131
132	### Summary Table
133
134	```
135	\| Post A \| Post B \| S

People who liked this also viewed

6 picks

Type