seo-drift

Name: seo-drift
Author: AgriciDaniel

12kstars1.8kforks

How to install seo-drift?

agricidaniel/claude-seo/seo-drift

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

Installs into the current project.

Summary

SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.

Files · 1

View on GitHub

agents/seo-drift.md

1	# SEO Drift Monitor (April 2026)
2
3	Git for your SEO. Capture baselines, detect regressions, track changes over time.
4
5	---
6
7	## Commands
8
9	\| Command \| Purpose \|
10	\|---------\|---------\|
11	\| `/seo drift baseline <url>` \| Capture current SEO state as a "known good" snapshot \|
12	\| `/seo drift compare <url>` \| Compare current page state to stored baseline \|
13	\| `/seo drift history <url>` \| Show change history and past comparisons \|
14
15	---
16
17	## What It Captures
18
19	Every baseline records these SEO-critical elements:
20
21	\| Element \| Field \| Source \|
22	\|---------\|-------\|--------\|
23	\| Title tag \| `title` \| `parse_html.py` \|
24	\| Meta description \| `meta_description` \| `parse_html.py` \|
25	\| Canonical URL \| `canonical` \| `parse_html.py` \|
26	\| Robots directives \| `meta_robots` \| `parse_html.py` \|
27	\| H1 headings \| `h1` (array) \| `parse_html.py` \|
28	\| H2 headings \| `h2` (array) \| `parse_html.py` \|
29	\| H3 headings \| `h3` (array) \| `parse_html.py` \|
30	\| JSON-LD schema \| `schema` (array) \| `parse_html.py` \|
31	\| Open Graph tags \| `open_graph` (dict) \| `parse_html.py` \|
32	\| Core Web Vitals \| `cwv` (dict) \| `pagespeed_check.py` \|
33	\| HTTP status code \| `status_code` \| `fetch_page.py` \|
34	\| HTML content hash \| `html_hash` (SHA-256) \| Computed \|
35	\| Schema content hash \| `schema_hash` (SHA-256) \| Computed \|
36
37	---
38
39	## How Comparison Works
40
41	The comparison engine applies 17 rules across 3 severity levels. Load
42	`references/comparison-rules.md` for the full rule set with thresholds,
43	recommended actions, and cross-skill references.
44
45	### Severity Levels
46
47	\| Level \| Meaning \| Response Time \|
48	\|-------\|---------\|---------------\|
49	\| CRITICAL \| SEO-breaking change, likely traffic loss \| Immediate \|
50	\| WARNING \| Potential impact, needs investigation \| Within 1 week \|
51	\| INFO \| Awareness only, may be intentional \| Review at convenience \|
52
53	---
54
55	## Storage
56
57	All data is stored locally in SQLite:
58
59	```
60	~/.cache/claude-seo/drift/baselines.db
61	```
62
63	### Tables
64
65	- baselines: Captured snapshots with all SEO elements
66	- comparisons: Diff results with triggered rules and severities
67
68	URL normalization ensures consistent matching: lowercase scheme/host, strip
69	default ports (80/443), sort query parameters, remove UTM parameters, strip
70	trailing slashes.
71
72	---
73
74	## Command: `baseline`
75
76	Captures the current state of a page and stores it.
77
78	Steps:
79	1. Validate URL (SSRF protection via `google_auth.validate_url()`)
80	2. Fetch page via `scripts/fetch_page.py`
81	3. Parse HTML via `scripts/parse_html.py`
82	4. Optionally fetch CWV via `scripts/pagespeed_check.py` (use `--skip-cwv` to skip)
83	5. Hash HTML body and schema content (SHA-256)
84	6. Store snapshot in SQLite
85
86	Execution:
87	```bash
88	claude-seo run drift_baseline.py <url>
89	claude-seo run drift_baseline.py <url> --skip-cwv
90	```
91
92	Output: JSON with baseline ID, timestamp, URL, and summary of captured elements.
93
94	---
95
96	## Command: `compare`
97
98	Fetches the current page state and diffs it against the most recent baseline.
99
100	Steps:
101	1. Validate URL
102	2. Load most recent baseline from SQLite (or specific `--baseline-id`)
103	3. Fetch and parse current page state
104	4. Run all 17 comparison rules
105	5. Classify findings by severity
106	6. Store comparison result
107	7. Output JSON diff report
108
109	Execution:
110	```bash
111	claude-seo run drift_compare.py <url>
112	claude-seo run drift_compare.py <url> --baseline-id 5
113	claude-seo run drift_compare.py <url> --skip-cwv
114	```
115
116	Output: JSON with all triggered rules, old/new values, severity, and actions.
117
118	After comparison, offer to generate an HTML report:
119	```bash
120	claude-seo run drift_report.py <comparison_json_file> --output drift-report.html
121	```
122
123	---
124
125	## Command: `history`
126
127	Shows all baselines and comparisons for a URL.
128
129	Execution:
130	```bash
131	claude-seo run drift_history.py <url>
132	claude-seo run drift_history.py <url> --limit 10
133	```
134
135	Output: JSON array of baselines (newest first) with timestamps and comparison summaries.
136
137	---
138
139	## Cross-Skill Integration
140
141	When drift is detected, recommend the appropriate specialized skill:
142
143	\| Finding \| Recommendation \|
144	\|---------\|----------------\|
145	\| Schema removed or modified \| Run `/seo schema <url>` for full validation \|
146	\| CWV regression \| Run `/seo technical <url>` for performance audit \|
147	\| Title or meta description changed \| Run `/seo page <url>` for content analysis \|
148	\| Canonical changed or removed \| Run `/seo technical <url>` for indexability check \|
149	\| Noindex added \| Run `/seo technical <url>`

People who liked this also viewed

6 picks

Type

seo-drift

12kstars1.8kforks

View on GitHub

How to install seo-drift?

agricidaniel/claude-seo/seo-drift

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

Installs into the current project.

Summary

Files · 1

View on GitHub

agents/seo-drift.md

1	# SEO Drift Monitor (April 2026)
2
3	Git for your SEO. Capture baselines, detect regressions, track changes over time.
4
5	---
6
7	## Commands
8
9	\| Command \| Purpose \|
10	\|---------\|---------\|
11	\| `/seo drift baseline <url>` \| Capture current SEO state as a "known good" snapshot \|
12	\| `/seo drift compare <url>` \| Compare current page state to stored baseline \|
13	\| `/seo drift history <url>` \| Show change history and past comparisons \|
14
15	---
16
17	## What It Captures
18
19	Every baseline records these SEO-critical elements:
20
21	\| Element \| Field \| Source \|
22	\|---------\|-------\|--------\|
23	\| Title tag \| `title` \| `parse_html.py` \|
24	\| Meta description \| `meta_description` \| `parse_html.py` \|
25	\| Canonical URL \| `canonical` \| `parse_html.py` \|
26	\| Robots directives \| `meta_robots` \| `parse_html.py` \|
27	\| H1 headings \| `h1` (array) \| `parse_html.py` \|
28	\| H2 headings \| `h2` (array) \| `parse_html.py` \|
29	\| H3 headings \| `h3` (array) \| `parse_html.py` \|
30	\| JSON-LD schema \| `schema` (array) \| `parse_html.py` \|
31	\| Open Graph tags \| `open_graph` (dict) \| `parse_html.py` \|
32	\| Core Web Vitals \| `cwv` (dict) \| `pagespeed_check.py` \|
33	\| HTTP status code \| `status_code` \| `fetch_page.py` \|
34	\| HTML content hash \| `html_hash` (SHA-256) \| Computed \|
35	\| Schema content hash \| `schema_hash` (SHA-256) \| Computed \|
36
37	---
38
39	## How Comparison Works
40
41	The comparison engine applies 17 rules across 3 severity levels. Load
42	`references/comparison-rules.md` for the full rule set with thresholds,
43	recommended actions, and cross-skill references.
44
45	### Severity Levels
46
47	\| Level \| Meaning \| Response Time \|
48	\|-------\|---------\|---------------\|
49	\| CRITICAL \| SEO-breaking change, likely traffic loss \| Immediate \|
50	\| WARNING \| Potential impact, needs investigation \| Within 1 week \|
51	\| INFO \| Awareness only, may be intentional \| Review at convenience \|
52
53	---
54
55	## Storage
56
57	All data is stored locally in SQLite:
58
59	```
60	~/.cache/claude-seo/drift/baselines.db
61	```
62
63	### Tables
64
65	- baselines: Captured snapshots with all SEO elements
66	- comparisons: Diff results with triggered rules and severities
67
68	URL normalization ensures consistent matching: lowercase scheme/host, strip
69	default ports (80/443), sort query parameters, remove UTM parameters, strip
70	trailing slashes.
71
72	---
73
74	## Command: `baseline`
75
76	Captures the current state of a page and stores it.
77
78	Steps:
79	1. Validate URL (SSRF protection via `google_auth.validate_url()`)
80	2. Fetch page via `scripts/fetch_page.py`
81	3. Parse HTML via `scripts/parse_html.py`
82	4. Optionally fetch CWV via `scripts/pagespeed_check.py` (use `--skip-cwv` to skip)
83	5. Hash HTML body and schema content (SHA-256)
84	6. Store snapshot in SQLite
85
86	Execution:
87	```bash
88	claude-seo run drift_baseline.py <url>
89	claude-seo run drift_baseline.py <url> --skip-cwv
90	```
91
92	Output: JSON with baseline ID, timestamp, URL, and summary of captured elements.
93
94	---
95
96	## Command: `compare`
97
98	Fetches the current page state and diffs it against the most recent baseline.
99
100	Steps:
101	1. Validate URL
102	2. Load most recent baseline from SQLite (or specific `--baseline-id`)
103	3. Fetch and parse current page state
104	4. Run all 17 comparison rules
105	5. Classify findings by severity
106	6. Store comparison result
107	7. Output JSON diff report
108
109	Execution:
110	```bash
111	claude-seo run drift_compare.py <url>
112	claude-seo run drift_compare.py <url> --baseline-id 5
113	claude-seo run drift_compare.py <url> --skip-cwv
114	```
115
116	Output: JSON with all triggered rules, old/new values, severity, and actions.
117
118	After comparison, offer to generate an HTML report:
119	```bash
120	claude-seo run drift_report.py <comparison_json_file> --output drift-report.html
121	```
122
123	---
124
125	## Command: `history`
126
127	Shows all baselines and comparisons for a URL.
128
129	Execution:
130	```bash
131	claude-seo run drift_history.py <url>
132	claude-seo run drift_history.py <url> --limit 10
133	```
134
135	Output: JSON array of baselines (newest first) with timestamps and comparison summaries.
136
137	---
138
139	## Cross-Skill Integration
140
141	When drift is detected, recommend the appropriate specialized skill:
142
143	\| Finding \| Recommendation \|
144	\|---------\|----------------\|
145	\| Schema removed or modified \| Run `/seo schema <url>` for full validation \|
146	\| CWV regression \| Run `/seo technical <url>` for performance audit \|
147	\| Title or meta description changed \| Run `/seo page <url>` for content analysis \|
148	\| Canonical changed or removed \| Run `/seo technical <url>` for indexability check \|
149	\| Noindex added \| Run `/seo technical <url>`

People who liked this also viewed

6 picks

Type