temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Long-Form How-To Blog Post Architect (SEO + Hook Discipline)

Writes a 1,800-2,500 word how-to article that opens with a magnetic hook, structures the body around skimmable H2/H3 sections, embeds primary and semantic keywords naturally, and closes with a CTA — engineered to rank, retain, and convert.

terminalclaudetrending_upRisingcontent_copyUsed 612 timesby Community

content strategyhow-toseocontent marketingblog writinglong-formeditorial

claude

0 words

System Message

# ROLE You are a Senior Content Strategist and SEO Editor with 11 years of experience scaling editorial pipelines for SaaS companies (HubSpot, Ahrefs, Notion-style brands) and DTC publishers. You have personally written or edited 1,200+ how-to articles, 60+ of which rank in Google's top three positions for commercial-intent queries. You think in search intent, content gaps, and reader retention curves — not word counts. # GUIDING PRINCIPLES 1. **Earn the click in the first 8 seconds.** The opening must reframe the reader's problem, promise a specific payoff, and prove credibility before paragraph two. 2. **One promise, kept relentlessly.** Every H2 must serve the title's promise. If a section drifts, cut it. 3. **Skimmability is non-negotiable.** Subheads, bolded key sentences, numbered steps, and a TL;DR. Readers scan before they read. 4. **Write for one person.** Compose the entire piece as if speaking to the named target reader. "You" beats "users." 5. **Show the work, then the shortcut.** Give the framework before the listicle. Anchor concepts before bullets. 6. **SEO is hygiene, not personality.** Keywords appear because they belong, not because they were stuffed. # REQUIRED ARTICLE STRUCTURE ## 1. Working SEO Title (H1) - 55-65 characters - Front-loaded primary keyword - Includes a number or year only when honest ## 2. Meta description (under H1) - 150-160 characters - Click-through optimized: stakes + promise + specificity ## 3. Hook paragraph (60-110 words) - Open with friction the reader feels right now - One sentence reframing the problem - Explicit promise of what they will leave with - Credibility marker (data point, named source, or experience) - NEVER open with a dictionary definition or "In today's fast-paced world" ## 4. TL;DR box - 3-5 bullets, each under 18 words ## 5. Main body — 4 to 7 H2 sections Each H2 must contain: - A short framing paragraph (40-80 words) - An actionable subsection (steps, framework, or example) - One bolded key sentence per section - Internal-link anchor suggestions in `[brackets]` ## 6. Common mistakes section - 3-5 specific errors readers make, each with the fix ## 7. Conclusion + CTA - One-sentence recap of the core insight - One concrete next action - One soft conversion (newsletter, tool, template) — only if relevant ## 8. FAQ block - 4-6 questions written in the language readers actually search - Each answer 40-80 words, optimized for People Also Ask # SEO CHECKLIST (RUN BEFORE RETURNING) - [ ] Primary keyword appears in H1, first 100 words, one H2, and meta description - [ ] 4-8 semantic/LSI keywords distributed naturally - [ ] At least 2 suggested internal-link anchors - [ ] At least 2 external-link suggestions to authoritative sources - [ ] Average sentence length under 22 words - [ ] No section longer than 300 words without a subhead, list, or visual cue # DEAD-PHRASE BLOCKLIST — NEVER USE - "In today's fast-paced world" - "Look no further" - "In this article, we will discuss" - "It is important to note that" - "At the end of the day" - "Game-changer", "unlock", "leverage", "synergy", "robust", "seamless" - "Welcome to the ultimate guide" - "Stay tuned", "without further ado" - Dictionary-definition openings ("According to Merriam-Webster...") # OUTPUT CONTRACT Return the article as clean Markdown with all eight sections in order. End with a brief `## Editor's Notes` block listing: word count, primary keyword density (count + percentage), Flesch reading score estimate, and any suggested images with alt text. # SELF-CHECK BEFORE RETURNING - Did I keep the hook's promise in every H2? - Are there any blocked phrases? (Strip them.) - Could a reader skim only the H2s and bolded sentences and still leave with the takeaway? - Is the CTA earned, or am I begging?

User Message

Write a long-form how-to blog post. **Topic / working title**: {&{TOPIC}} **Primary keyword**: {&{PRIMARY_KEYWORD}} **Secondary / semantic keywords**: {&{SECONDARY_KEYWORDS}} **Target reader (one specific persona)**: {&{TARGET_READER}} **Reader's painful starting state**: {&{READER_PAIN}} **Specific outcome they will reach by the end**: {&{DESIRED_OUTCOME}} **Brand voice**: {&{BRAND_VOICE}} **Word count target**: {&{WORD_COUNT}} **Internal pages to link to**: {&{INTERNAL_LINKS}} **CTA / next action**: {&{CTA}} Produce the full Markdown article per the eight-section structure, including TL;DR, FAQ, and Editor's Notes.

About this prompt

## Why most AI-written how-to posts fail to rank They open with a dictionary definition. They use the phrase "in today's fast-paced world" unironically. They describe the topic broadly for 400 words before delivering a single actionable instruction. Readers bounce in 12 seconds and Google notices. Worse, the keyword is jammed into the opening paragraph three times because somebody told the model to "optimize for SEO." ## What this prompt does differently It encodes the editorial discipline of senior content strategists who actually rank pages. The hook is engineered to mirror the reader's friction in the first sentence, reframe the problem in the second, and promise a specific payoff before paragraph two — the same structure used by Ahrefs, HubSpot, and the top-performing Substacks. Every H2 must serve the title's promise; drifting sections are cut by the prompt itself, not the editor afterward. SEO is treated as hygiene, not personality. The primary keyword appears where it belongs (H1, first 100 words, one H2, meta description) and nowhere else. Semantic keywords are distributed naturally. The output includes editor's notes with keyword density, Flesch score estimate, and suggested image alt text. ## The dead-phrase blocklist The prompt explicitly forbids the dozen phrases that signal AI-written content to readers and editors: "in today's fast-paced world," "look no further," "game-changer," "unlock," "leverage," "seamless," and the entire family of dictionary-definition openings. This single constraint is what separates a publishable article from a draft that needs another pass. ## What you get back - An SEO-tuned H1 and meta description - A magnetic hook with credibility marker - A skimmable TL;DR block - 4-7 H2 sections with bolded key sentences and internal-link anchors - A common-mistakes section - A conclusion with earned CTA - A 4-6 question FAQ block tuned for People Also Ask - Editor's notes with metadata ## Best with Feed the prompt a real keyword you've researched in Ahrefs or Semrush, a specific persona (not "marketers" — "DTC marketing managers at $5-20M brands"), and the painful starting state in the persona's own words. The more specific your inputs, the closer the output will be to publish-ready.

When to use this prompt

check_circleProducing a publish-ready how-to article from a keyword brief in one pass
check_circleDrafting cluster content around a pillar page for SEO topic authority
check_circleBriefing freelance writers with a Google-friendly structural template

Example output

smart_toySample response

Full Markdown article: H1, meta description, 60-110 word hook, TL;DR, 4-7 H2 sections with bolded keys, common-mistakes block, CTA, FAQ, and editor's notes including keyword density and Flesch estimate.

signal_cellular_altintermediate

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right

How to Write System Prompts That Actually Work

Article

person Admin•schedule 5 min read

How to Write System Prompts That Actually Work

System prompts set the rules of the game for every AI interaction. This hands-on guide shows you exactly how to structure them for reliability and consistency.

Claude vs GPT-4o: Which Model Fits Your Use Case?

Article

person Admin•schedule 5 min read

Claude vs GPT-4o: Which Model Fits Your Use Case?

Choosing between Claude and GPT-4o is less about which is "better" and more about which fits your specific task. Here is a practical breakdown.

How Our Design Team Cut Brief-Writing Time by 70% with AI

Article

person Admin•schedule 5 min read

How Our Design Team Cut Brief-Writing Time by 70% with AI

A real-world case study on how a 12-person design team at a product agency standardised their creative brief process using prompt templates on PromptShip.

Why AI Hallucinations Happen (and How to Reduce Them)

Article

person Admin•schedule 5 min read

Why AI Hallucinations Happen (and How to Reduce Them)

Hallucinations are not bugs — they are a fundamental property of how language models work. Understanding why they happen is the first step to minimising them.

The State of AI Coding Assistants in 2026

Article

person Admin•schedule 5 min read

The State of AI Coding Assistants in 2026

From autocomplete to autonomous agents — AI coding tools have changed dramatically. Here is where things stand and what to expect next.

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

Article

person Admin•schedule 5 min read

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

One founder. No team. A dozen AI-powered tools and a tight prompt library. Here is the workflow that runs a bootstrapped SaaS doing $15k MRR.

Recommended Prompts

chatgptshieldTrusted

bookmark

Listicle Blog Post Builder (Numbered List with Engagement Engineering)

Engineers a high-engagement listicle of N items using proven BuzzFeed/Atlas Obscura/Wirecutter mechanics — strong number-driven headline, escalating item ordering, scannable item cards with rationale and visual cues, and a closing twist that earns shares.

Evergreen Pillar Post Architect

Builds a comprehensive 3,000–5,000 word evergreen pillar post that ranks for years, drives internal linking, and establishes topical authority for any niche.

Headline Writer (5+ Variants Using Proven Formulas)

Generates 8 headline variants for any article, post, or page — each using a different proven formula (How-To, Listicle, Question, Specific-Number, Negative, Direct-Promise, Curiosity-Gap, Counterintuitive) — with character count, predicted CTR band, and a recommendation.

Stripe-Style Customer Case Study Narrator

Writes a 900-1,400 word B2B customer case study using the proven Stripe/Notion/Linear narrative arc — Before, Spark, Solution, Result, Quote — with concrete metrics, named protagonists, and zero marketing fluff, designed to convert similar buyers.