Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Programmatic Seo · mkurman | DecimalAI

mkurman/programmatic-seo

SkillScore91Maintained

When the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pages," "[keyword] + [city] pages," "comparison pages," "integration pages," "building many pages for SEO," "pSEO," "generate 100 pages," "data-driven pages," or "templated landing pages." Use this whenever someone wants to create many similar pages targeting different keywords or locations. For audi

marketingby mkurman

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Marketing & Content pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/mkurman-programmatic-seo/SKILL.md

decimalai skills pull mkurman-programmatic-seo --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/mkurman-programmatic-seo/SKILL.md https://app.decimal.ai/s/mkurman-programmatic-seo/SKILL.md

Raw file: /s/mkurman-programmatic-seo/SKILL.md ↗ · machine-readable summary at /s/mkurman-programmatic-seo.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 8d ago

Yes — +9% lift · at higher cost+35% tokens0% turns91% of whole cases pass with skill (20/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	-1%	0%
case-06	✗→✓	▲ Improved	12%	0%
case-01	✓→✓	＝ Same ✓	39%	0%
case-02	✓→✓	＝ Same ✓	45%	0%
case-03	✓→✓	＝ Same ✓	60%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

mkurman / zorai

skills/nontechnical/corey-marketingskills/programmatic-seo/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 1 file

Skill contents

references/

SKILL.md

The 12 Playbooks (Overview)

| Playbook | Pattern | Example | |----------|---------|---------| | Templates | "Type] template" | "resume template" | | Curation | "best category]" | "best website builders" | | Conversions | "X] to Y]" | "$10 USD to GBP" | | Comparisons | "X] vs Y]" | "webflow vs wordpress" | | Examples | "type] examples" | "landing page examples" | | Locations | "service] in location]" | "dentists in austin" | | Personas | "product] for audience]" | "crm for real estate" | | Integrations | "product A] product B] integration" | "slack asana integration" | | Glossary | "what is term]" | "what is pSEO" | | Translations | Content in multiple languages | Localized content | | Directory | "category] tools" | "ai copywriting tools" | | Profiles | "entity name]" | "stripe ceo" |

For detailed playbook implementation: See references/playbooks.md

Choosing Your Playbook

| If you have... | Consider... | |----------------|-------------| | Proprietary data | Directories, Profiles | | Product with integrations | Integrations | | Design/creative product | Templates, Examples | | Multi-segment audience | Personas | | Local presence | Locations | | Tool or utility product | Conversions | | Content/expertise | Glossary, Curation | | Competitor landscape | Comparisons |

You can layer multiple playbooks (e.g., "Best coworking spaces in San Diego").

Implementation Framework

1. Keyword Pattern Research

Identify the pattern:

What's the repeating structure?
What are the variables?
How many unique combinations exist?

Validate demand:

Aggregate search volume
Volume distribution (head vs. long tail)
Trend direction

2. Data Requirements

Identify data sources:

What data populates each page?
Is it first-party, scraped, licensed, public?
How is it updated?

3. Template Design

Page structure:

Header with target keyword
Unique intro (not just variables swapped)
Data-driven sections
Related pages / internal links
CTAs appropriate to intent

Ensuring uniqueness:

Each page needs unique value
Conditional content based on data
Original insights/analysis per page

4. Internal Linking Architecture

Hub and spoke model:

Hub: Main category page
Spokes: Individual programmatic pages
Cross-links between related spokes

Avoid orphan pages:

Every page reachable from main site
XML sitemap for all pages
Breadcrumbs with structured data

5. Indexation Strategy

Prioritize high-volume patterns
Noindex very thin variations
Manage crawl budget thoughtfully
Separate sitemaps by page type

Quality Checks

Pre-Launch Checklist

Content quality:

] Each page provides unique value
] Answers search intent
] Readable and useful

Technical SEO:

] Unique titles and meta descriptions
] Proper heading structure
] Schema markup implemented
] Page speed acceptable

Internal linking:

] Connected to site architecture
] Related pages linked
] No orphan pages

Indexation:

] In XML sitemap
] Crawlable
] No conflicting noindex

Post-Launch Monitoring

Track: Indexation rate, Rankings, Traffic, Engagement, Conversion

Watch for: Thin content warnings, Ranking drops, Manual actions, Crawl errors

Common Mistakes

Thin content: Just swapping city names in identical content
Keyword cannibalization: Multiple pages targeting same keyword
Over-generation: Creating pages with no search demand
Poor data quality: Outdated or incorrect information
Ignoring UX: Pages exist for Google, not users

Output Format

Strategy Document

Opportunity analysis
Implementation plan
Content guidelines

Page Template

URL structure
Title/meta templates
Content outline
Schema markup

Task-Specific Questions

What keyword patterns are you targeting?
What data do you have (or can acquire)?
How many pages are you planning?
What does your site authority look like?
Who currently ranks for these terms?
What's your technical stack?

Related Skills

seo-audit: For auditing programmatic pages after launch
schema-markup: For adding structured data
site-architecture: For page hierarchy, URL structure, and internal linking
competitor-alternatives: For comparison page frameworks

Want to see if mkurman/programmatic-seo would activate on your phrasing? Try it before you install — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/21/2026, 18:33 UTC · 22 cases

Lift

+9%

91% vs 82%

Agent turns

1.0 vs 1.0

Tokens

+35%

3,414.27 vs 2,538.27

fail → pass · 2pass → pass · 18fail → fail · 2

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 We operate a fintech data platform called BankData containing proprietary metrics for 50,000 credit unions and regional banks. We want to scale organic search traffic using programmatic pages. Should we build competitor comparison pages or something else based on our assets?	pass→pass	18,749	26,390	+41%	1	1	0%	2,764	3,832	+39%	0	0	—
case-02 Our SaaS platform WorkflowPro connects via API to 120 third-party tools like Slack, Jira, and Asana. We want to execute a programmatic SEO strategy to capture search intent around our platform working with other software. Should we focus on glossary definitions or another playbook?	pass→pass	14,886	12,933	-13%	1	1	0%	2,269	3,300	+45%	0	0	—
case-03 DesignHub is an online repository holding over 30,000 Figma UI templates and wireframe examples. We want to create thousands of SEO landing pages. Should we build local city pages or another playbook suited for creative design assets?	pass→pass	17,559	15,101	-14%	1	1	0%	2,135	3,412	+60%	0	0	—
case-04 StaffShift is an employee scheduling SaaS targeting distinct industry verticals such as real estate agencies, healthcare clinics, and retail chains. Which programmatic SEO playbook best matches our multi-segment audience?	fail→pass	18,328	10,780	-41%	1	1	0%	2,815	2,777	-1%	0	0	—
case-05 UnitsFast is a web utility app that converts measurement units and foreign currencies. What programmatic SEO playbook aligns with our utility tool product?	pass→pass	21,473	16,283	-24%	1	1	0%	3,548	3,620	+2%	0	0	—
case-06 HealthExpert is a medical publishing organization with extensive clinical topic expertise and written guides. What programmatic SEO playbook best fits our subject matter assets?	fail→pass	20,207	15,855	-22%	1	1	0%	3,139	3,515	+12%	0	0	—
case-07 CloudDesk operates in a crowded SaaS space alongside established rivals like Zendesk and Freshdesk. Which programmatic SEO playbook leverages this competitive landscape?	pass→pass	17,807	10,908	-39%	1	1	0%	2,355	2,808	+19%	0	0	—
case-08 We are designing the URL and site hierarchy for 8,000 programmatic directory pages on AutoPartsDb. Should we create flat orphaned pages or structure them under category hubs?	pass→pass	16,430	16,223	-1%	1	1	0%	2,476	3,610	+46%	0	0	—
case-09 For our local plumber directory PlumbSearch, we generated 40,000 local pages across small towns. 25,000 of these pages have zero search demand and very sparse local data. Should we leave all 40,000 indexable in Google?	pass→pass	12,972	15,605	+20%	1	1	0%	2,153	3,536	+64%	0	0	—
case-10 On SaaSList, we have 80,000 programmatic pages split between software comparison pages and glossary pages. How should we structure our XML sitemaps for Google Search Console?	pass→pass	15,094	17,820	+18%	1	1	0%	2,749	4,155	+51%	0	0	—
case-11 We are generating 3,000 city landing pages for LegalMatch. A team member suggested taking one standard paragraph and swapping only the city name variable across all 3,000 pages. Is this approach recommended?	pass→pass	14,046	12,424	-12%	1	1	0%	2,088	2,873	+38%	0	0	—
case-12 When designing page templates for a programmatic 'best [category]' curation site called ToolFinder, how should the introductory text block above the fold be constructed?	pass→pass	20,777	17,820	-14%	1	1	0%	2,908	3,881	+33%	0	0	—
case-13 Our marketing team wants to combine 50,000 random dictionary nouns to programmatically build 500,000 pages on WordLexicon, regardless of search volume. What risk should we evaluate before launching?	pass→pass	12,173	11,932	-2%	1	1	0%	1,826	2,804	+54%	0	0	—
case-14 During a pre-launch check for 4,000 new programmatic pages on EduCourses, we found that none of the pages are linked from category hubs or navigation menus, relying entirely on the XML sitemap. Does this pass pre-launch quality standards?	pass→pass	11,760	9,472	-19%	1	1	0%	1,807	2,433	+35%	0	0	—
case-15 Create a complete programmatic SEO delivery package for a B2B platform called DevToolsHQ targeting integration keywords. What structural deliverables should be included in the output?	fail→fail	25,561	21,173	-17%	1	1	0%	4,410	5,215	+18%	0	0	—
case-16 We want to launch a programmatic SEO campaign for PropTech, a commercial real estate platform. Before producing the strategy document, what initial scoping details need to be collected from the team?	pass→pass	15,356	13,304	-13%	1	1	0%	2,304	3,065	+33%	0	0	—
case-17 What primary performance metrics should be monitored in Search Console and analytics after launching 10,000 programmatic landing pages for SaaSCompare?	pass→pass	17,219	15,965	-7%	1	1	0%	2,722	3,557	+31%	0	0	—
case-18 Two weeks after releasing 15,000 programmatic pages for ShopFind, organic impressions suddenly dropped by 80%. What specific technical search health issues should be investigated?	pass→pass	16,076	31,681	+97%	1	1	0%	2,458	3,797	+54%	0	0	—
case-19 How should breadcrumb navigation links be implemented across programmatic sub-category pages on EventFinder to assist search engine crawlers?	pass→pass	22,663	20,058	-11%	1	1	0%	2,757	3,682	+34%	0	0	—
case-20 Write the exact valid JSON-LD code block snippet for an FAQPage schema on a single blog post about pet insurance.	pass→pass	5,750	6,731	+17%	1	1	0%	1,204	2,426	+101%	0	0	—
case-21 Perform a full technical SEO audit of the live website https://example.com by crawling its HTTP status codes and Core Web Vitals performance metrics.	fail→fail	21,095	22,311	+6%	1	1	0%	3,354	4,363	+30%	0	0	—
case-22 Write three high-converting copywriting headline options for an ad landing page pitch targeting active users switching from Mailchimp to ConvertKit.	pass→pass	10,413	9,401	-10%	1	1	0%	1,601	2,453	+53%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +9 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 81.8%
Pass rate with the skill: 90.9%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/21/2026, 18:33 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-04

Prompt

StaffShift is an employee scheduling SaaS targeting distinct industry verticals such as real estate agencies, healthcare clinics, and retail chains. Which programmatic SEO playbook best matches our multi-segment audience?

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run91

Live evalNeeds ≥20 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+41% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 7 days ago

Other measured skills in the registry, with their headline benchmark lift.