YouTube Audio Samples Extractor - Confirm & Copy Final Agent Code

Describe

Describe your task

Refine

Refine the plan

SubAgents

Review all agents

Deploy

Deploy your agent

Review Final Agent Copy

Expand

Here is the updated combined JSON array with the requested changes:

[
  {
    "taskID": 169,
    "semanticTitleOfTask": "Create Dalle Image (Rectangle)",
    "taskDescription": "This skill creates a 1792x1024 square image with DalleE, based on a given text prompt. Dalle3 is a great AI image creator, especially for \"non photo realistic\" images. Once the image is created it is saved to the server as a .png file.",
    "inputDescription": "10-300 character text prompt",
    "inputRequired": [
      "VARIABLE1"
    ],
    "outputDescription": "internal and external link to the image",
    "outputName": "dallee_rectangle_image",
    "promptInstruction": "Generate a 1792x1024 rectangular image using Dall-E based on this text prompt: [VARIABLE1]. Return the image URL."
  },
  {
    "taskID": 170,
    "semanticTitleOfTask": "Create Leonardo Image (Rectangle)",
    "taskDescription": "This skill creates a 1536x864 square image with LeonardoAI, based on a given text prompt. LeonardoAI is a great AI image creator, especially for photo-realistic images.",
    "inputDescription": "10-300 character text prompt",
    "inputRequired": [
      "VARIABLE1"  
    ],
    "outputDescription": "internal and external link to the image",
    "outputName": "leonardo_rectangle_image",
    "promptInstruction": "Generate a 1536x864 rectangular image using Leonardo AI based on this text prompt: [VARIABLE1]. Return the image URL."
  },
  {
    "taskID": 171,
    "semanticTitleOfTask": "Create Dalle Image (Transparent Square)",
    "taskDescription": "This skill creates a 1024x1024, square, transparent PNG file, based on a given text prompt. The image created should be of a singular object/scene with a clearly defined edge (so the background remover works particularly well). This skill is especially great at creating icons, vectors, cartoons, physical objects, etc. Once the image is created it is saved to the server as a .png file.",
    "inputDescription": "10-300 character text prompt",
    "inputRequired": [
      "VARIABLE1"
    ],
    "outputDescription": "internal and external link to the image",
    "outputName": "dallee_transparent_square_image",
    "promptInstruction": "Generate a 1024x1024 square transparent PNG image using Dall-E based on this text prompt: [VARIABLE1]. The image should be of a singular object or scene with a clearly defined edge. Return the image URL."
  },
  {
    "taskID": 172,
    "semanticTitleOfTask": "Make Logos & eCover Marketing Assets",
    "taskDescription": "This skill takes the name of a product and generates a white logo, black logo, and two software \"mockups\", all transparent PNGs.",
    "inputDescription": "Product name and description of product.",
    "inputRequired": [
      "VARIABLE1",
      "VARIABLE2" 
    ],
    "outputDescription": "Internal and external links to the generated assets",
    "outputName": "logo_and_asset_urls",
    "promptInstruction": "Create a white logo, black logo, and two software mockups as transparent PNGs for a product with the name [VARIABLE1] and description [VARIABLE2]. Return the URLs for each asset."
  },
  {
    "taskID": 173,
    "semanticTitleOfTask": "Copy & Download External Folder",
    "taskDescription": "This skill copies the entirety of a folder on an external website (eg. externaldomain.com/images is copied to ourserver/project-images). This is useful if user has an entire folder of images, templates or some other group of assets which is required for the task.",
    "inputDescription": "URL of folder root path",
    "inputRequired": [
      "logo_and_asset_urls"
    ],
    "outputDescription": "Explanation of new folder URL, both internal and external.",
    "outputName": "new_folder_urls",
    "promptInstruction": "Copy the entire folder from the external URL [logo_and_asset_urls] to our internal server. Provide the new internal and external URLs for the copied folder."
  },
  {
    "taskID": 174,
    "semanticTitleOfTask": "Copy & Download External File",
    "taskDescription": "This skill copies an individual file (eg externaldomain.com/filename.txt) to our internal server. Having files on our own servers allows us to run more tasks (few of the skills work with files hosted on external servers).",
    "inputDescription": "URL of a file",
    "inputRequired": [
      "dallee_rectangle_image"
    ],
    "outputDescription": "Explanation of new file URL, both internal and external",
    "outputName": "new_dallee_rectangle_image_url",
    "promptInstruction": "Copy the file from the external URL [dallee_rectangle_image] to our internal server. Provide the new internal and external URLs for the copied file."
  },
  {
    "taskID": 175,
    "semanticTitleOfTask": "Zip Internal URLs",
    "taskDescription": "Input between 1 and 100 file URLs that you want to zip up. The output is the URL of the zip file.",
    "inputDescription": "2 or more internal URLs",
    "inputRequired": [
      "new_dallee_rectangle_image_url", 
      "leonardo_rectangle_image"
    ],
    "outputDescription": "We just zipped up some files, now here's explanation of location, both internal and external",
    "outputName": "zip_file_urls",
    "promptInstruction": "Create a zip file containing the following internal file URLs: [new_dallee_rectangle_image_url], [leonardo_rectangle_image]. Provide the internal and external URLs for the generated zip file."
  },
  {
    "taskID": 177,
    "semanticTitleOfTask": "Write Text (Or Copy) From Researched Text",
    "taskDescription": "This skill takes a piece of researched text and uses a LLM (typically GPT4) to return text based on this research. This is very useful for a whole range of tasks, such as writing copy about a researched product, writing articles about a research topic, etc.",
    "inputDescription": "Some text input of some kind",
    "inputRequired": [
      "researchSummary"  
    ],
    "outputDescription": "Generated text based on the research",
    "outputName": "generated_text",
    "promptInstruction": "Based on the researched text provided, generate new text using GPT-4: [researchSummary]"
  },
  {
    "taskID": 178,
    "semanticTitleOfTask": "Rewrite Text Based On Instructions",
    "taskDescription": "This skill uses a LLM (typically GPT4) to return some type of text, based on prompt instructions. This is a fundamental and important skill.",
    "inputDescription": "Text to rewrite and rewrite instructions",
    "inputRequired": [
      "generated_text",
      "VARIABLE3"
    ],
    "outputDescription": "Rewritten text based on the instructions",
    "outputName": "rewritten_text", 
    "promptInstruction": "Rewrite the following text based on these instructions: [VARIABLE3]\n\nText to rewrite: [generated_text]"
  },
  {
    "taskID": 179,
    "semanticTitleOfTask": "Rewrite HTML Based On Instructions",
    "taskDescription": "This skill inputs some HTML (such as a template that has been pre-created) and uses a LLM (typically GPT4) to edit it, based on prompt instructions given. The HTML is then edited, as per the instructions, and returned.",
    "inputDescription": "HTML code, elements to add, and rewrite instructions",
    "inputRequired": [
      "htmlCode",
      "rewritten_text",
      "VARIABLE3"  
    ],
    "outputDescription": "Rewritten HTML code",
    "outputName": "rewritten_html",
    "promptInstruction": "Rewrite the following HTML code based on these instructions: [VARIABLE3]\n\nElements to add: [rewritten_text]\n\nHTML code: [htmlCode]"
  },
  {
    "taskID": 180,
    "semanticTitleOfTask": "Rewrite JSON (or other code) Based On Instructions", 
    "taskDescription": "This skill inputs a JSON code (such as a template that can then be used to trigger an API call) and uses a LLM (typically GPT4) to edit it, based on prompt instructions given. The JSON code is then edited, as per the instructions, and returned. Note that this skill can also be used for other types of code (such as CSS, JS, etc), except for HTML (for HTML rewriting, the dedicated skill for that should be used).",
    "inputDescription": "JSON code, elements to add, and rewrite instructions",
    "inputRequired": [
      "jsonCode",
      "rewritten_text",
      "VARIABLE3"
    ],
    "outputDescription": "Rewritten JSON code",
    "outputName": "rewritten_json",
    "promptInstruction": "Rewrite the following JSON code based on these instructions: [VARIABLE3]\n\nElements to add: [rewritten_text]\n\nJSON code: [jsonCode]"
  },
  {
    "taskID": 181,
    "semanticTitleOfTask": "Research Topic (Or Keyword) Deeply",
    "taskDescription": "This skill will research a given topic or keyword deeply. This skill will run a number of searches on various search engines, visit several websites, and collate a large amount of research information, then use a LLM to summarize the research provided, based on the information that has been requested.",
    "inputDescription": "Keywords and/or topic to research",
    "inputRequired": [
      "VARIABLE1"
    ],
    "outputDescription": "1000 character research summary",
    "outputName": "research_summary",
    "promptInstruction": "Conduct deep research on the following topic or keyword: [VARIABLE1]. Run searches on various search engines, visit relevant websites, and collate the information. Summarize the research in approximately 1000 characters."
  },
  {
    "taskID": 183,
    "semanticTitleOfTask": "Find Most Relevant YouTube Video For Keyword (Or Topic)",
    "taskDescription": "This skill inputs a keyword or topic and returns a list of the most relevant YouTube videos for that given task.",
    "inputDescription": "A single keyword",
    "inputRequired": [
      "VARIABLE1" 
    ],
    "outputDescription": "List of relevant YouTube videos with summaries",
    "outputName": "relevant_youtube_videos",
    "promptInstruction": "Find the most relevant YouTube videos for the keyword or topic: [VARIABLE1]. Return a list of the videos ranked in order of relevance, along with a brief summary of each video."
  },
  {
    "taskID": 184,
    "semanticTitleOfTask": "Brainstorm Related Keywords",
    "taskDescription": "This skill inputs a single keyword (or topic, product description, or any piece of text really) and will then run multiple searches (using keyword tools like SEMRush along with Google related suggestions, etc), and then return a list of the 4 most related keywords in order of relevancy, along with additional commentary on each (as written by a LLM).",
    "inputDescription": "A single keyword, topic, product description, or any text",
    "inputRequired": [
      "VARIABLE1"
    ],
    "outputDescription": "List of 4 related keywords with commentary",
    "outputName": "related_keywords",
    "promptInstruction": "Brainstorm related keywords for the following input: [VARIABLE1]. Use keyword tools like SEMRush and Google related suggestions to find the 4 most relevant keywords. Return the list of keywords in order of relevance, along with commentary on each keyword generated by GPT-4."
  },
  {
    "taskID": 185,
    "semanticTitleOfTask": "Brainstorm Most Relevant Domains/Websites",
    "taskDescription": "This skill inputs a single keyword (or topic, product description, or any piece of text really) and will then run multiple searches (using keyword tools like SEMRush along with Google related suggestions, etc), and then return a list of the 4 most related domains/website URLs in order of relevancy, along with additional commentary on each (as written by a LLM).",
    "inputDescription": "A single keyword, topic, product description, or any text", 
    "inputRequired": [
      "VARIABLE1"
    ],
    "outputDescription": "List of 4 relevant domains with commentary",
    "outputName": "relevant_domains",
    "promptInstruction": "Brainstorm the most relevant domains or websites for the following input: [VARIABLE1]. Use keyword tools like SEMRush and Google related suggestions to find the 4 most relevant domains. Return the list of domain URLs in order of relevance, along with commentary on each domain generated by GPT-4."
  },
  {
    "taskID": 186,
    "semanticTitleOfTask": "Select Most Relevant Images From External Server",
    "taskDescription": "This skill inputs a root URL of a folder (eg. site.com/images-we-uploaded) and searches them to find the the filenames in this folder which are most related to a specific query the user wants. This is especially useful when the user has a collection of templates or files, and they want to select from them, depending on an input that may vary each time they want to run the agent.",
    "inputDescription": "Folder URL to search and keyword/topic/product description to match relevance",
    "inputRequired": [
      "new_folder_urls",
      "VARIABLE1"  
    ],
    "outputDescription": "List of 4 related image files with internal and external URLs",
    "outputName": "relevant_images",
    "promptInstruction": "Search the images in the folder [new_folder_urls] and find the 4 most relevant filenames based on the keyword/topic/product description: [VARIABLE1]. Return the list of related image files with their internal and external URLs."
  }
]

Happy? Now Copy-Paste To Proceed...

BACK TO SUBAGENTS

COPY TO CLIPBOARD