Converted number to base 2, 8, and 16 - 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 JSON array with the suggested 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": "dalle_image_link",
    "promptInstruction": "Create a 1792x1024 image based on the following prompt: [VARIABLE1]"
  },
  {
    "taskID": 217,
    "semanticTitleOfTask": "Select Most Relevant Template To Use In Next Prompt(s)",
    "taskDescription": "This skill will input a series of templates, and select the most relevant one based on a given description of the required task.",
    "inputDescription": "Description of the task",
    "inputRequired": ["VARIABLE2", "templates"],
    "outputDescription": "Template (text, code.. some non-binary text template output of some kind)",
    "outputName": "selected_template",
    "promptInstruction": "Given the following task description: [VARIABLE2], select the most relevant template from the provided options: [templates]"
  },
  {
    "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 input and rewrite instructions",
    "inputRequired": ["selected_template", "rewrite_instructions"],
    "outputDescription": "Rewritten text based on instructions",
    "outputName": "rewritten_text",
    "promptInstruction": "Rewrite the following text: [selected_template] based on these instructions: [rewrite_instructions]"
  },
  {
    "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 realistic images.",
    "inputDescription": "10-300 character text prompt",
    "inputRequired": ["rewritten_text"],
    "outputDescription": "Internal and external link to the image",
    "outputName": "leonardo_image_link",
    "promptInstruction": "Create a 1536x864 image based on the following prompt: [rewritten_text]"
  },
  {
    "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": "Single keyword (or topic, product description, or any piece of text)",
    "inputRequired": ["rewritten_text"],
    "outputDescription": "List of 4 related keywords, listed in order, with comments",
    "outputName": "related_keywords",
    "promptInstruction": "Brainstorm 4 keywords related to the following input: [rewritten_text]. Provide a brief commentary on each keyword."
  },
  {
    "taskID": 208,
    "semanticTitleOfTask": "Create 1 Banner Ad For Any URL/Product",
    "taskDescription": "This skill inputs information about a given product (or topic) and creates a promotional banner ad (300x300 image).",
    "inputDescription": "Info about product/topic to write about",
    "inputRequired": ["related_keywords"],
    "outputDescription": "Link to banner with description",
    "outputName": "banner_ad",
    "promptInstruction": "Create a 300x300 banner ad for a product with the following information: [related_keywords]"
  },
  {
    "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 + the keyword/topic/product description that it needs to be relevant to",
    "inputRequired": ["folder_url", "related_keywords"],
    "outputDescription": "List of 4 related files, listed in order, with both internal and external URL and how to use them",
    "outputName": "relevant_images",
    "promptInstruction": "Search the folder at [folder_url] and find the 4 images most relevant to: [related_keywords]. Provide both internal and external URLs for each image, along with a brief description of how they can be used."
  },
  {
    "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 AND the elements to be added into it AND instructions",
    "inputRequired": ["html_code", "relevant_images", "rewrite_instructions"],
    "outputDescription": "Rewritten HTML code",
    "outputName": "rewritten_html",
    "promptInstruction": "Rewrite the following HTML code: [html_code] by adding these elements: [relevant_images] based on these instructions: [rewrite_instructions]"
  },
  {
    "taskID": 193,
    "semanticTitleOfTask": "Create 2-10 Short MicroCopy Text",
    "taskDescription": "This skill uses an LLM to write several pieces of \"micro-copy\" (ie small copywriting or creative texts, to be used within a banner or some other asset). The skill will output a list of the requested copy.",
    "inputDescription": "Info about product/topic to write about",
    "inputRequired": ["related_keywords"],
    "outputDescription": "List of micro-copy elements",
    "outputName": "microcopy_text",
    "promptInstruction": "Write 2-10 pieces of short micro-copy for a product with the following information: [related_keywords]"
  },
  {
    "taskID": 167,
    "semanticTitleOfTask": "Select Most Relevant HTML Template Based On Product/Task Description",
    "taskDescription": "Inputs a folder of HTML files and a description of a product, then analyzes the HTML templates and returns the one that is most suitable for building a piece of software or a website about the given product.",
    "inputDescription": "Folder of HTML files + a product/task description",
    "inputRequired": ["folder_url", "rewritten_text"],
    "outputDescription": "Most relevant HTML file for the given product/task",
    "outputName": "selected_html_template",
    "promptInstruction": "Analyze the HTML files in the folder [folder_url] and select the one most relevant for building a website or software about a product described as: [rewritten_text]"
  },
  {
    "taskID": 218,
    "semanticTitleOfTask": "Add Images & Videos On Top Of Existing MP4",
    "taskDescription": "This skill will input a collection of images and/or videos (up to 18 in total) and layer them on top of an existing MP4 URL. It will intelligently review the new media and decide where to insert it. For added control, it is recommended that a description of the images/videos, and transcription of the video is provided.",
    "inputDescription": "List of images/videos, ideally with descriptions, and transcription of video",
    "inputRequired": ["relevant_images", "video_transcription", "base_video_url"],
    "outputDescription": "URL of MP4 video with added media",
    "outputName": "edited_video_url",
    "promptInstruction": "Add the following images and videos: [relevant_images] to the base video at [base_video_url]. Use the video transcription [video_transcription] and media descriptions to intelligently place the new media. Return the URL of the edited video."
  },
  {
    "taskID": 227,
    "semanticTitleOfTask": "Format Up To 4000 Characters Of Text Into Pretty HTML",
    "taskDescription": "Skill which is useful for finishing articles or ebooks. Input up to 4000 characters of plain text or unformatted HTML, and this skill will convert it to finished formatted, pretty HTML.",
    "inputDescription": "Text and perhaps images and videos with description of what they are, grouped",
    "inputRequired": ["rewritten_text", "relevant_images"],
    "outputDescription": "Pretty formatted HTML",
    "outputName": "pretty_html",
    "promptInstruction": "Format the following text: [rewritten_text] into pretty HTML. If available, also include the images and videos from [relevant_images] in appropriate locations."
  },
  {
    "taskID": 205,
    "semanticTitleOfTask": "Build Software Tool For Any Niche/Topic",
    "taskDescription": "This skill inputs a keyword/topic/product description and generates a GPT powered software tool which the user can sell/launch/etc.",
    "inputDescription": "Keyword/topic/product description to build all variables from",
    "inputRequired": ["rewritten_text"],
    "outputDescription": "URL with software link and description of what it does",
    "outputName": "software_tool_url",
    "promptInstruction": "Build a GPT-powered software tool for the following topic: [rewritten_text]. Provide the URL to access the tool along with a description of its functionality."
  },
  {
    "taskID": 222,
    "semanticTitleOfTask": "Create Database Software From CSV File",
    "taskDescription": "Inputs a CSV file and create a \"database software\" which is basically a software tool which makes the CSV file searchable and filterable.",
    "inputDescription": "CSV file, email of customer, description of software and title",
    "inputRequired": ["csv_url", "customer_email", "software_description", "software_title"],
    "outputDescription": "Summary of software URL and how to login",
    "outputName": "database_software_summary",
    "promptInstruction": "Create a database software tool using the CSV file at [csv_url]. The software should allow searching and filtering the data. It is being created for customer with email [customer_email]. The software title is [software_title] and it is described as [software_description]. Provide a summary of the created software, including the URL to access it and login instructions."
  },
  {
    "taskID": 216,
    "semanticTitleOfTask": "Return final HTML Selector File",
    "taskDescription": "This skill inputs a collection of embeddable file URLs (either text, code, images, videos, audio). The skill will generate a \"selector\" HTML page which embeds these elements for quick and easy selection and review (if the files are either very large or cumbersome, it might be best to use the \"summarize\" skill instead).",
    "inputDescription": "List of files or text to return along with a description of them", 
    "inputRequired": ["pretty_html", "file_descriptions"],
    "outputDescription": "URL of selector HTML file",
    "outputName": "selector_file_url",
    "promptInstruction": "Create an HTML \"selector\" file that embeds the following files: [pretty_html]. Include the descriptions for each file: [file_descriptions]. The selector should allow for easy review and selection of the embedded elements. Provide the URL to the generated HTML file."
  },
  {
    "taskID": 215,
    "semanticTitleOfTask": "Summarise and Return All Final Output Files",
    "taskDescription": "This skill returns a summary of various previous skills that have completed, and is particularly useful when appearing at the end of an entire Agent task, silo or sequence of skills.",
    "inputDescription": "At least one output (perhaps other supplementary ones that may be helpful)",
    "inputRequired": ["selector_file_url", "software_tool_url"],
    "outputDescription": "Nice text summary containing 1 or more outputs",
    "outputName": "task_summary",
    "promptInstruction": "Provide a summary of the completed task, focusing on the primary outputs: [selector_file_url] and [software_tool_url]. If relevant, also mention any supplementary outputs."
  }
]

Happy? Now Copy-Paste To Proceed...

BACK TO SUBAGENTS

COPY TO CLIPBOARD