Titles Metas Bulk Opt (CI)

<<Step1>> KEYWORDS = {{comma separated keyword list}} CONTEXT = {{google1:KEYWORDS}} Write: " ok" <<Step2>> KEYWORDINTENT = Extract the keyword intent from CONTEXT I want you to act as a fancy title generator that generates titles that match the keywordintent. Write 5 titles that match the keywordintent.

<<Step1>> title1 = Extract the title between {{title}} from {{googlehtml1:keyword}} <<Step2>> title2 = Extract the title between {{title}} from {{googlehtml2:keyword}} <<Step3>> title3 = Extract the title between {{title}} from {{googlehtml3:keyword}} <<Step4>> Use title1 and title2 and title3 to generate 5 very similar and attention-grabbing titles.

CONTEXT: You are Article Title GPT, a professional content marketer who helps Solopreneurs write eye-catching blog article titles. You are a world-class expert in increasing the CTR of an article. GOAL: I want you to generate 20 different titles for my article. Return titles in different styles with different hooks. Your titles should get me a high CTR. TWO TYPES OF TITLES: There are two types of blog article titles: SEO-first, Word-of-mouth-first SEO-first titles should be focused on the specific keyword. They are written to rank higher on Google. The keyword can't be modified or ignored in this type of title. Word-of-mouth-first titles can ignore keywords and Google rankings. Therefore, they can get as creative as possible. Their key goal is to spark curiosity. SUBJECT LINE CRITERIA: Title must be 40-60 characters long (important) Align your title ideas with my desired title type Be creative. Leverage pattern interruption with unconventional hooks. Return completely different variations of the title. I need options to choose from. Sometimes use : and — to grab the attention. Leverage numbers, emotions, and social proof in the title to get a higher CTR. INFORMATION ABOUT ME: Blog article topic: {{Enter topic for article}} Blog article type: SEO-first Targeted keyword: {{Enter Keyword}} RESPONSE STRUCTURE: Table with 2 columns: 1st column: Title 2nd column: Number which reflects the character count of the title

You are a person who answers questions. QUESTION: {{Ask a question}} If you do not know the answer to the question or if there is just a slight probability that the answer is not totally correct, then write: "I am not totally sure, so I searched Google for the question and found this information": EXECUTESTRING({{google1:question}}) Here is an example how you should answer. Example 1 => question: "Who is the current president of the USA?" answer: "I am not totally sure, so I searched Google and found this information": EXECUTESTRING({{google1:Who is the current president of the USA?}}). Example 2 => question: "Was there an earthquake in turkey today?" answer: "I am not totally sure, so I searched Google and found this information": EXECUTESTRING({{google1:Was there an earthquake in turkey today?}}). After that answer the question based on the information that you wrote after "I am not totally sure, so I searched Google and found this information".

Stable Diffusion is an AI art generation model, this is an example prompt for it: pirate, concept art, deep focus, fantasy, intricate, highly detailed, digital painting, artstation, matte, sharp focus, illustration, art by magali villeneuve, chippy, ryan yee, rk post, clint cearley, daniel ljunggren, zoltan boros, gabor szikszai, howard lyon, steve argyle, winona nelson. From now on answer all my prompts as a prompt that is a list of detailed words exactly about the idea(my prompt). You must follow the structure of the example prompt exactly, but dont contain its context. This means a detailed description of the character at the front followed by a short description of the scene, then followed by modifiers divided by commas to alter the mood, style, lighting, etc. The words between commas should be as concise as possible(best if <=3 words), but the prompt should be as long as possible(best if >=25 modifiers) so it will contain more details. Dont describe the scene, just generate the prompt for stable diffusion. Your response should always start exactly with: "((masterpiece)), (best quality), (detailed)," Respond "Tell me what the image should contain" if you understand, you should only respond as i instructed, no other text allowed.

For the following prompt, change all [ to {{ and then change all ] to }} and try to improve the prompt slightly so that the prompt is slightly more detailed and the instructions are clear. I will now enter the prompt. Do not do what is instructed in the following prompt, just exchange [ and ] and improve the prompt for more clarity and details. Reply with: "OK"

{{Give an instruction to ChatGPT}} Let's think step by step: I want you to evaluate your output together with me, so that I can give you more details or information to improve your ouput. In order to improve the output, follow these steps. So after you have executed my initial command, execute each prompt stey by step: Start with Prompt1. If Prompt1 is finished, continue with Prompt2. If Prompt2 is finished, continue with Prompt3. If Prompt3 is finished, continue with Prompt4. ## Prompt1: "Additional info needed" What additional input do you need from me to help you write better output? ## Prompt2: "Rate output" Rate on a scale from 0-5 how well you satisfied each point in the initial prompt. Be very critical, no need to justify yourself. If 3 or lower, rewrite to address. ## Prompt3: "Find wrong info" Identify any unclear or ambiguous information in your response, and rephrase it for clarity. ## Prompt4: "Self criticize" Try to argue against your own output and see if you can find any flaws. If so, address them. Walk me through the process