Write meta descriptions for a batch of page titles
Writing meta descriptions one at a time across a large site migration or content sprint is tedious and leads to inconsistent tone. This prompt processes a list of titles in a single pass and enforces both character limits and brand voice.
You are an SEO copywriter. Write a meta description for each page title in the list below. Follow these steps exactly.
1. READ the brand voice note: {{BRAND_VOICE_NOTE}}. Identify two or three concrete language rules you will apply (e.g., active verbs, no exclamation marks, second-person).
2. FOR EACH title in the list:
a. Write one meta description between 140-155 characters (count carefully).
b. Include the primary topic keyword naturally.
c. End with a soft call-to-action relevant to the page intent (informational, transactional, or navigational — infer from the title).
d. Do not start two descriptions with the same verb.
3. OUTPUT a table with three columns: Title | Meta Description | Character Count.
4. FLAG any title that is too vague to infer page intent. Write [NEEDS CLARIFICATION] instead of guessing.
Page titles:
{{TITLE_LIST}}
Edge case: This prompt works best when titles are specific. Generic titles like 'Home' or 'About Us' will produce weak descriptions without more context — provide the actual page purpose for those. {{BRAND_VOICE_NOTE}}{{TITLE_LIST}}
How to use this prompt
- Copy the prompt above (Copy button on the top-right).
- Replace each
{{VAR}}with your own value. Variables:{{BRAND_VOICE_NOTE}}{{TITLE_LIST}}. - Paste it into one of the recommended tools below.
- Iterate: tighten constraints in the prompt if the output is generic.
Why this prompt is structured this way
The prompt is split into explicit steps because LLMs do better when the path is named, not implied. Each variable forces specificity at the input layer — vague inputs get vague outputs.
Pair this prompt with a tool
Surfer SEO
$89/moReal-time SEO scoring while you write.
Surfer scores your draft against the top-ranking competitors in real time. Indispensable for anyone publishing programmatic SEO content at scale.
Frase
$15/moSERP-driven brief generation + writer in one tool.
Frase started as a brief generator and added a writer. The brief side is still the strongest part — it ingests SERPs and outputs structured outlines faster than anything else.
Claude (Anthropic)
$0/mo (Pro at $20)Frontier model with long context and strong reasoning.
Claude (Opus / Sonnet / Haiku tiers) is the assistant favored by writers and engineers who care about reasoning quality and tone. 1M token context on Opus.
ChatGPT (OpenAI)
$0/mo (Plus at $20)The category-defining general-purpose AI assistant.
ChatGPT has the broadest feature surface: image gen, voice, custom GPTs, web browsing, code execution. Often the right default; sometimes beaten on specific tasks by Claude or Perplexity.
The PlaybookPrompts weekly
One short email per week. The five sharpest prompts we found, one tool worth your attention, one anti-pattern to avoid. Unsubscribe in one click.
Newsletter signup is not configured. Set PUBLIC_NEWSLETTER_USERNAME in the build env.