Blog Quality Checklist

Blog quality scoring checklist

by AgriciDaniel · MIT license · ★ 2,219 on GitHub · updated Sep 18

Score each blog post against this checklist. Used by /blog analyze.

# Blog Quality Scoring Checklist

Score each blog post against this checklist. Used by `/blog analyze`.

## Content Quality (30 points)

| Check | Points | Pass Criteria |
|-------|--------|---------------|
| Depth/comprehensiveness | 7 | Covers topic thoroughly, no major gaps |
| Readability | 7 | Match the audience; default Flesch 60-70, 55-75 acceptable; technical/YMYL topics may justify denser prose |
| Originality/unique value markers | 5 | Original data, case studies, first-hand experience |
| Sentence & paragraph structure | 4 | Avg sentence 15-20 words, ≤25% over 20; paragraphs 40-80 words; H2 every 200-300 words |
| Engagement elements | 4 | Summary box near the top, callouts, varied content blocks |
| Grammar/anti-pattern | 3 | Passive voice ≤10%, AI trigger words ≤5/1K, transition words 20-30%, clean prose |

## SEO Optimization (25 points)

| Check | Points | Pass Criteria |

Overview

Score each blog post against this checklist. Used by /blog analyze.

Manual install (npx, ZIP)

Claude Codenpx skills add AgriciDaniel/claude-blog --skill blog-quality-scoring-checklist -g -a claude-code

Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

quality-scoring.md7.9 KB

Read quality-scoring.md here

AgriciDaniel/main1 file

quality-scoring.md7.9 KB

quality-scoring.md

Show the full text165 lines

Blog Quality Scoring Checklist

Score each blog post against this checklist. Used by /blog analyze.

Content Quality (30 points)

Check	Points	Pass Criteria
Depth/comprehensiveness	7	Covers topic thoroughly, no major gaps
Readability	7	Match the audience; default Flesch 60-70, 55-75 acceptable; technical/YMYL topics may justify denser prose
Originality/unique value markers	5	Original data, case studies, first-hand experience
Sentence & paragraph structure	4	Avg sentence 15-20 words, ≤25% over 20; paragraphs 40-80 words; H2 every 200-300 words
Engagement elements	4	Summary box near the top, callouts, varied content blocks
Grammar/anti-pattern	3	Passive voice ≤10%, AI trigger words ≤5/1K, transition words 20-30%, clean prose

SEO Optimization (25 points)

Check	Points	Pass Criteria
Heading hierarchy with keywords	5	H1 → H2 → H3, no skips, keyword in 2-3 headings, H2 every 200-300 words
Title tag (40-60 chars, keyword, power word)	4	Front-loaded keyword, positive sentiment, brackets if applicable
Keyword placement/density	4	Natural integration (0.5-2%), no stuffing, present in first 100 words
Internal linking (3-10 contextual)	4	Descriptive anchor text, bidirectional, related content
URL structure	3	Short, keyword-rich, no stop words, lowercase
Meta description (150-160 chars)	3	Fact-dense, clear value prop; include a sourced statistic only when central to the page
External linking (tier 1-3)	2	3-8 outbound links to authoritative sources

E-E-A-T Signals (15 points)

Check	Points	Pass Criteria
Author attribution (accountable, with bio)	4	Named author/editor preferred; organization attribution acceptable with clear editorial ownership
Source citations (tier 1-3, inline format)	4	`([Source](url), year)` format, 8+ unique stats, zero fabricated
Trust indicators (contact, about, transparency)	4	Site has contact page, about page, editorial policy
Experience signals (first-person markers)	3	"When we tested...", "In our experience...", original photos/data

Source citations gating rule: Sources must follow the FLOW evidence triple: year anchor in prose, inline citation with publisher and title, AND URL with retrieval date in compact retrieval notes, footnotes, or a bibliography. Sources without retrieval dates do not pass this criterion. Reference: flow-alignment.md.

Technical Elements (15 points)

Check	Points	Pass Criteria
Schema markup priority baseline	4	Article/BlogPosting + Person + Organization + BreadcrumbList; FAQPage optional only for visible Q&A entity support; dateModified current
Image optimization (alt text, format, lazy load)	3	AVIF/WebP, descriptive alt text, lazy except LCP
Structured data elements	2	Tables, lists, comparison blocks for AI extraction
Page speed signals (no render-blocking)	2	LCP < 2.5s, no render-blocking JS, fetchpriority on hero
Mobile-friendliness	2	Responsive, tap targets 48px+, no horizontal scroll, paragraphs ≤100 words
OG/social meta tags	2	og:title, og:description, og:image (1200x630), twitter:card

AI Citation Readiness (15 points)

Check	Points	Pass Criteria
Passage-level citability (120-180 word passages)	4	About 50-word direct-answer sentence followed by self-contained passage with stat + source
Q&A formatted sections	3	60-70% of H2s as questions, visible FAQ section when template calls for it
Entity clarity	3	Unambiguous topic entity, consistent terminology
Content structure for extraction	3	Answer-first, tables with `<thead>`, comparison formats
AI crawler accessibility	2	SSR/SSG, no JS-gated content, robots.txt allows AI bots

Total: 100 points

Scoring Bands

Score	Rating	Action
90-100	Exceptional	Publish as-is, flagship content
80-89	Strong	Minor polish, ready for publication
70-79	Acceptable	Targeted improvements needed before publish
60-69	Below Standard	Significant rework required
< 60	Rewrite	Fundamental issues, start from outline

Priority Classification

When reporting issues, classify by priority:

Critical (Must Fix Before Publishing)

Fabricated statistics (zero tolerance)
Broken heading hierarchy (H1 → H3 skip)
Paragraphs > 200 words (Yoast red)
No source attribution on claims
Missing author attribution
Content behind JavaScript (invisible to AI crawlers)
Missing summary box near the top

High Priority

Missing answer-first formatting on H2 sections
Missing Article/Person/Organization/BreadcrumbList schema baseline
Missing visible Q&A section when the selected template calls for FAQ
Fewer than 8 sourced statistics
Missing meta description or lastUpdated
Title tag outside 40-60 character range
No internal links
Flesch score outside 55-75 range
No OG/social meta tags
Paragraphs > 150 words
Passive voice > 15%
AI trigger words > 8 per 1,000

Medium Priority

Fewer than 2 charts
Fewer than 3 images
Tier 4-5 sources present
Self-promotion > 1 mention
Sections exceeding 300 words between headings
Missing experience signals (no first-person markers)
Images not in AVIF/WebP format
loading="lazy" on LCP image
Average sentence length > 22 words
Transition words < 15% or > 35%

Low Priority

Paragraph length slightly above 80 words (but under 150)
Question-format H2 ratio outside 60-70%
Missing chart type diversity
Images without alt text
Missing external links to tier 1-3 sources
Entity terminology inconsistency

Quick Automated Checks

These can be detected programmatically:

Content Quality

Word count per paragraph (split on double newlines, flag > 150, critical > 200)
Sentence count per paragraph (flag > 3 sentences)
Flesch-Kincaid score (default target 60-70, acceptable 55-75; adjust for audience)
Heading frequency (flag gaps > 300 words between H2s)
Summary box presence in first 500 characters (accept "TL;DR", "Key Takeaways", "Summary", or "Quick Answer")
Average sentence length (target 15-20, flag > 22)
Sentences over 20 words (flag if > 25% of total)
Passive voice percentage (flag > 10%, high priority > 15%)
AI trigger word density (flag > 5 per 1,000 words)
Transition word percentage (target 20-30%, flag < 15% or > 35%)

SEO Optimization

Title tag length (frontmatter, target 40-60 chars)
Heading hierarchy (regex for ^#{1,6} , no skipped levels)
Meta description length (frontmatter, target 150-160 chars)
Internal link count (regex for relative URLs or same-domain links)
External link count and tier classification
URL structure check (lowercase, no stop words)

E-E-A-T Signals

Author attribution presence (frontmatter author field)
Citation format (regex for \([^)]+\(http)
Unsourced statistics (numbers without attribution nearby)
Self-promotion patterns (brand name frequency, max 1)
First-person markers ("we tested", "in our experience")

Technical Elements

Image count (regex for !\[ or <img)
Image alt text presence (images without alt attribute)
Chart count (regex for <svg or <figure)
Schema presence (search for structured data markers)
OG meta tags (frontmatter ogImage, coverImage)
loading="lazy" on first image (flag as LCP issue)
lastUpdated presence (frontmatter check)

AI Citation Readiness

Opening citable passage after each H2 (target 120-180 words after about 50-word answer sentence)
Question-format heading ratio (target 60-70% of H2s)
Visible Q&A presence when template calls for FAQ
Table presence with <thead> (for AI extraction)
robots.txt AI bot allowance (site-level check)

1	# Blog Quality Scoring Checklist
2
3	Score each blog post against this checklist. Used by `/blog analyze`.
4
5	## Content Quality (30 points)
6
7	\| Check \| Points \| Pass Criteria \|
8	\|-------\|--------\|---------------\|
9	\| Depth/comprehensiveness \| 7 \| Covers topic thoroughly, no major gaps \|
10	\| Readability \| 7 \| Match the audience; default Flesch 60-70, 55-75 acceptable; technical/YMYL topics may justify denser prose \|
11	\| Originality/unique value markers \| 5 \| Original data, case studies, first-hand experience \|
12	\| Sentence & paragraph structure \| 4 \| Avg sentence 15-20 words, ≤25% over 20; paragraphs 40-80 words; H2 every 200-300 words \|
13	\| Engagement elements \| 4 \| Summary box near the top, callouts, varied content blocks \|
14	\| Grammar/anti-pattern \| 3 \| Passive voice ≤10%, AI trigger words ≤5/1K, transition words 20-30%, clean prose \|
15
16	## SEO Optimization (25 points)
17
18	\| Check \| Points \| Pass Criteria \|
19	\|-------\|--------\|---------------\|
20	\| Heading hierarchy with keywords \| 5 \| H1 → H2 → H3, no skips, keyword in 2-3 headings, H2 every 200-300 words \|
21	\| Title tag (40-60 chars, keyword, power word) \| 4 \| Front-loaded keyword, positive sentiment, brackets if applicable \|
22	\| Keyword placement/density \| 4 \| Natural integration (0.5-2%), no stuffing, present in first 100 words \|
23	\| Internal linking (3-10 contextual) \| 4 \| Descriptive anchor text, bidirectional, related content \|
24	\| URL structure \| 3 \| Short, keyword-rich, no stop words, lowercase \|
25	\| Meta description (150-160 chars) \| 3 \| Fact-dense, clear value prop; include a sourced statistic only when central to the page \|
26	\| External linking (tier 1-3) \| 2 \| 3-8 outbound links to authoritative sources \|
27
28	## E-E-A-T Signals (15 points)
29
30	\| Check \| Points \| Pass Criteria \|
31	\|-------\|--------\|---------------\|
32	\| Author attribution (accountable, with bio) \| 4 \| Named author/editor preferred; organization attribution acceptable with clear editorial ownership \|
33	\| Source citations (tier 1-3, inline format) \| 4 \| `([Source](url), year)` format, 8+ unique stats, zero fabricated \|
34	\| Trust indicators (contact, about, transparency) \| 4 \| Site has contact page, about page, editorial policy \|
35	\| Experience signals (first-person markers) \| 3 \| "When we tested...", "In our experience...", original photos/data \|
36
37	Source citations gating rule: Sources must follow the FLOW evidence triple: year anchor in prose, inline citation with publisher and title, AND URL with retrieval date in compact retrieval notes, footnotes, or a bibliography. Sources without retrieval dates do not pass this criterion. Reference: `flow-alignment.md`.
38
39	## Technical Elements (15 points)
40
41	\| Check \| Points \| Pass Criteria \|
42	\|-------\|--------\|---------------\|
43	\| Schema markup priority baseline \| 4 \| Article/BlogPosting + Person + Organization + BreadcrumbList; FAQPage optional only for visible Q&A entity support; dateModified current \|
44	\| Image optimization (alt text, format, lazy load) \| 3 \| AVIF/WebP, descriptive alt text, lazy except LCP \|
45	\| Structured data elements \| 2 \| Tables, lists, comparison blocks for AI extraction \|
46	\| Page speed signals (no render-blocking) \| 2 \| LCP < 2.5s, no render-blocking JS, fetchpriority on hero \|
47	\| Mobile-friendliness \| 2 \| Responsive, tap targets 48px+, no horizontal scroll, paragraphs ≤100 words \|
48	\| OG/social meta tags \| 2 \| og:title, og:description, og:image (1200x630), twitter:card \|
49
50	## AI Citation Readiness (15 points)
51
52	\| Check \| Points \| Pass Criteria \|
53	\|-------\|--------\|---------------\|
54	\| Passage-level citability (120-180 word passages) \| 4 \| About 50-word direct-answer sentence followed by self-contained passage with stat + source \|
55	\| Q&A formatted sections \| 3 \| 60-70% of H2s as questions, visible FAQ section when template calls for it \|
56	\| Entity clarity \| 3 \| Unambiguous topic entity, consistent terminology \|
57	\| Content structure for extraction \| 3 \| Answer-first, tables with `<thead>`, comparison formats \|
58	\| AI crawler accessibility \| 2 \| SSR/SSG, no JS-gated content, robots.txt allows AI bots \|
59
60	## Total: 100 points
61
62	### Scoring Bands
63
64	\| Score \| Rating \| Action \|
65	\|-------\|--------\|--------\|
66	\| 90-100 \| Exceptional \| Publish as-is, flagship content \|
67	\| 80-89 \| Strong \| Minor polish, ready for publication \|
68	\| 70-79 \| Acceptable \| Targeted improvements needed before publish \|
69	\| 60-69 \| Below Standard \| Significant rework required \|
70	\| < 60 \| Rewrite \| Fundamental issues, start from outline \|
71
72	## Priority Classification
73
74	When reporting issues, classify by priority:
75
76	### Critical (Must Fix Before Publishing)
77	- Fabricated statistics (zero tolerance)
78	- Broken heading hierarchy (H1 → H3 skip)
79	- Paragraphs > 200 words (Yoast red)
80	- No source attribution on claims
81	- Missing author attribution
82	- Content behind JavaScript (invisible to AI crawlers)
83	- Missing summary box near the top
84
85	### High Priority
86	- Missing answer-first formatting on H2 sections
87	- Missing Article/Person/Organization/BreadcrumbList schema baseline
88	- Missing visible Q&A section when the selected template calls for FAQ
89	- Fewer than 8 sourced statistics
90	- Missing meta description or lastUpdated
91	- Title tag outside 40-60 character range
92	- No internal links
93	- Flesch score outside 55-75 range
94	- No OG/social meta tags
95	- Paragraphs > 150 words
96	- Passive voice > 15%
97	- AI trigger words > 8 per 1,000
98
99	### Medium Priority
100	- Fewer than 2 charts
101	- Fewer than 3 images
102	- Tier 4-5 sources present
103	- Self-promotion > 1 mention
104	- Sections exceeding 300 words between headings
105	- Missing experience signals (no first-person markers)
106	- Images not in AVIF/WebP format
107	- `loading="lazy"` on LCP image
108	- Average sentence length > 22 words
109	- Transition words < 15% or > 35%
110
111	### Low Priority
112	- Paragraph length slightly above 80 words (but under 150)
113	- Question-format H2 ratio outside 60-70%
114	- Missing chart type diversity
115	- Images without alt text
116	- Missing external links to tier 1-3 sources
117	- Entity terminology inconsistency
118
119	## Quick Automated Checks
120
121	These can be detected programmatically:
122
123	### Content Quality
124	1. Word count per paragraph (split on double newlines, flag > 150, critical > 200)
125	2. Sentence count per paragraph (flag > 3 sentences)
126	3. Flesch-Kincaid score (default target 60-70, acceptable 55-75; adjust for audience)
127	4. Heading frequency (flag gaps > 300 words between H2s)
128	5. Summary box presence in first 500 characters (accept "TL;DR", "Key Takeaways", "Summary", or "Quick Answer")
129	6. Average sentence length (target 15-20, flag > 22)
130	7. Sentences over 20 words (flag if > 25% of total)
131	8. Passive voice percentage (flag > 10%, high priority > 15%)
132	9. AI trigger word density (flag > 5 per 1,000 words)
133	10. Transition word percentage (target 20-30%, flag < 15% or > 35%)
134
135	### SEO Optimization
136	11. Title tag length (frontmatter, target 40-60 chars)
137	12. Heading hierarchy (regex for `^#{1,6} `, no skipped levels)
138	13. Meta description length (frontmatter, target 150-160 chars)
139	14. Internal link count (regex for relative URLs or same-domain links)
140	15. External link count and tier classification
141	16. URL structure check (lowercase, no stop words)
142
143	### E-E-A-T Signals
144	17. Author attribution presence (frontmatter `author` field)
145	18. Citation format (regex for `\([^)]+\(http`)
146	19. Unsourced statistics (numbers without attribution nearby)
147	20. Self-promotion patterns (brand name frequency, max 1)
148	21. First-person markers ("we tested", "in our experience")
149
150	### Technical Elements
151	22. Image count (regex for `!\[` or `<img`)
152	23. Image alt text presence (images without alt attribute)
153	24. Chart count (regex for `<svg` or `<figure`)
154	25. Schema presence (search for structured data markers)
155	26. OG meta tags (frontmatter `ogImage`, `coverImage`)
156	27. `loading="lazy"` on first image (flag as LCP issue)
157	28. lastUpdated presence (frontmatter check)
158
159	### AI Citation Readiness
160	29. Opening citable passage after each H2 (target 120-180 words after about 50-word answer sentence)
161	30. Question-format heading ratio (target 60-70% of H2s)
162	31. Visible Q&A presence when template calls for FAQ
163	32. Table presence with `<thead>` (for AI extraction)
164	33. robots.txt AI bot allowance (site-level check)
165