AI Prompt Library for Marketers

What this is

A curated library of 42 production-tested prompts organised by marketing function. These aren’t generic “write me a blog post” prompts — they are structured system prompts with variables, constraints, and output formats that I use across live retainers.

Every prompt has been tested on both Claude (Sonnet/Opus) and GPT-4o, with notes on which model handles it better and why.

What is inside

Content Strategy (10 prompts)

• Content brief generator — Takes a target keyword and produces a full brief: angle, outline, sources to cite, internal links to include, word count target
• Content refresh auditor — Analyses an existing post and outputs what to update, add, or cut to recover lost rankings
• Topic cluster mapper — Given a pillar topic, generates hub-and-spoke content plan with keyword targets per spoke
• Editorial calendar builder — Produces a 90-day content calendar based on seasonal trends, competitor gaps, and business goals
• Headline A/B generator — Creates 10 headline variants scored by clarity, curiosity, and keyword inclusion

Ad Copy & Conversion (8 prompts)

• Google Ads RSA generator — 15 headlines + 4 descriptions per ad group, respecting character limits
• Landing page copy framework — Hero, social proof, features, objection handling, CTA — structured for above-the-fold impact
• Email subject line tester — Generates 20 subject lines with predicted open-rate reasoning
• Meta description writer — Batch-generates SEO meta descriptions that maximise CTR within 155 characters
• Social proof synthesiser — Takes raw testimonials and restructures them for landing pages, ads, and email

Technical SEO (8 prompts)

• Schema.org generator — Produces JSON-LD for any page type based on URL and content description
• Redirect map builder — Takes old/new URL lists and generates redirect rules with regex patterns
• Robots.txt auditor — Reviews robots.txt and flags crawl budget waste or accidental blocks
• Log file analyst — Summarises crawl patterns from server logs: bot frequency, crawl budget allocation, error rates
• Core Web Vitals diagnostician — Takes PageSpeed Insights JSON and outputs prioritised fix list

Competitor Analysis (8 prompts)

• Competitor content gap finder — Compares your content inventory against a competitor’s and identifies missing topics
• SERP feature analyst — For a given keyword, analyses what SERP features appear and how to target each
• Competitor positioning decoder — Analyses a competitor’s homepage/about page and extracts their positioning, messaging hierarchy, and weak points
• Backlink opportunity finder — Given competitor backlink data, identifies the most replicable link sources

Reporting & Strategy (8 prompts)

• Monthly report narrator — Takes raw GA4/GSC data and writes an executive summary with insights and recommendations
• QBR slide writer — Generates presenter notes and key talking points for quarterly business reviews
• KPI anomaly explainer — Given a metric spike or drop, generates three hypotheses ranked by likelihood
• Budget reallocation advisor — Takes channel performance data and recommends budget shifts with expected impact

How to use it

Each prompt follows a consistent structure:

[SYSTEM] Role and constraints
[CONTEXT] Background information you paste in
[VARIABLES] {{keyword}}, {{url}}, {{competitor}} — replace with your data
[OUTPUT FORMAT] Exactly how the response should be structured
[QUALITY GATES] Self-check criteria the AI applies before responding

Best practices

• Always fill in the context section. Generic context produces generic output.
• Use the quality gates. They prevent the most common AI failure modes (hallucination, generic advice, missing specifics).
• Iterate, don’t regenerate. If the first output is 70% right, edit the 30% rather than starting over.
• Claude vs GPT notes are included per prompt. In general: Claude handles nuance and longer outputs better; GPT-4o is faster for batch work.

Version history

Version	Date	Notes
3.0	June 2026	Added quality gates to all prompts, updated for Claude Opus 4
2.5	April 2026	Added competitor analysis section
2.0	January 2026	Restructured around marketing functions