Menu
NEW AGENT
MY AGENTS
ASSISTANTS
Ebook from Title and Keywords
- Step 4
Summary - 14th Jan
Summary - 13th Jan
Summary - 12th Jan
Summary - 10th Jan
Summary - 7th Jan
Summary - 7th Jan
Summary - 4th Jan
Summary - 3rd Jan
Summary - 2nd Jan
SETTINGS
LOGOUT
Ebook from Title and Keywords - Confirm & Copy Final Agent Code
1
Describe
Describe your task
2
Refine
Refine the plan
3
SubAgents
Review all agents
4
Deploy
Deploy your agent
Review Final Agent Copy
Expand
Here is the updated combined JSON array with the requested changes: ```json [ { "taskID": 169, "semanticTitleOfTask": "Create a 1792x1024 image with Dalle based on text prompt", "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": "A 10-300 character text prompt describing the desired image", "inputRequired": [ "VARIABLE1" ], "outputDescription": "This skill returns both an internal server link and an external link to the generated image", "outputName": "generatedImage", "promptInstruction": "Create a 1792x1024 pixel image with the following text description: {{VARIABLE1}}" }, { "taskID": 211, "semanticTitleOfTask": "Search the web for information about a product", "taskDescription": "The skill takes the name of a product and runs various detailed web-searches, browses and scrapes to return detailed information about the product (such as price, features, and other data and information).", "inputDescription": "The name of the product to research", "inputRequired": [ "VARIABLE2" ], "outputDescription": "This skill returns various details about the researched product, including price, features, specs, reviews, etc.", "outputName": "productInformation", "promptInstruction": "Conduct a deep web search to find as much relevant information as possible about the following product: {{VARIABLE2}}. Return details on pricing, features, specifications, customer reviews and any other useful data. Summarize the key findings." }, { "taskID": 184, "semanticTitleOfTask": "Brainstorm related keywords for a given keyword", "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, phrase, topic or product description to brainstorm related keywords for", "inputRequired": [ "productInformation" ], "outputDescription": "This skill returns a list of the top 4 most relevant keywords related to the input, ranked in order of relevance. Additional commentary is provided on each keyword.", "outputName": "relatedKeywords", "promptInstruction": "Brainstorm the top 4 most relevant keywords related to: {{productInformation}}. Use keyword research tools to find semantically related terms and phrases. Rank the keywords in order of relevance and provide a brief explanation on why each is related. Focus on finding highly relevant long-tail keywords." }, { "taskID": 217, "semanticTitleOfTask": "Select Most Relevant Template To Use", "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": "A description of the task that needs to be accomplished, along with a list of potential templates that could be used.", "inputRequired": [ "productInformation", "relatedKeywords" ], "outputDescription": "The skill returns the template text or code that is deemed most suitable for the described task.", "outputName": "selectedTemplate", "promptInstruction": "Given the following product information: {{productInformation}}, and related keywords: {{relatedKeywords}}, analyze the list of template options and select the one that is best suited to create promotional content for the product. Return the full text or code of the selected template." }, { "taskID": 180, "semanticTitleOfTask": "Edit JSON 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": "The JSON code to be edited, the elements to be added or changed within the code, and instructions on what to modify.", "inputRequired": [ "selectedTemplate", "productInformation", "relatedKeywords" ], "outputDescription": "This skill returns the modified JSON code after making the requested edits as per the instructions.", "outputName": "editedJsonCode", "promptInstruction": "Take the following JSON template: {{selectedTemplate}} and customize it using this product information: {{productInformation}} and related keywords: {{relatedKeywords}}. Update the relevant elements in the JSON to create promotional content specific to the researched product." }, { "taskID": 177, "semanticTitleOfTask": "Write Text Based on 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 researched text input about a topic, product, etc.", "inputRequired": [ "editedJsonCode" ], "outputDescription": "This skill returns a generated text based on the research input. The output is raw text.", "outputName": "promotionalText", "promptInstruction": "Based on the following edited JSON template with researched product information, generate promotional text content for the product: {{editedJsonCode}}" }, { "taskID": 187, "semanticTitleOfTask": "Convert Script to Voice-Over MP3", "taskDescription": "This skill accepts a text script for a video and converts it to an MP3 voice-over file. This skill works best with scripts of less than 4000 characters (approx max 5 minutes of video), and so if a script is expected to be much longer than this, the script should be divided up (and then concatenated back together again later, using another skill which does this).", "inputDescription": "The text script that needs to be converted into a voice-over MP3 file", "inputRequired": [ "promotionalText" ], "outputDescription": "This skill returns an MP3 file of the script being read out loud in a natural voice. It provides both an internal server URL and external URL to access the MP3 file.", "outputName": "voiceOverMP3", "promptInstruction": "Please convert the following promotional text into an audio MP3 file with a natural sounding voice-over: {{promotionalText}}" }, { "taskID": 218, "semanticTitleOfTask": "Layer Additional Media on Top of Existing Video", "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": "An MP4 video URL to use as the base, a list of up to 18 image/video URLs to layer on top, and optionally a description of each media element and a transcription of the base video.", "inputRequired": [ "generatedImage", "voiceOverMP3" ], "outputDescription": "This skill returns a new MP4 video URL which has the additional media elements intelligently layered on top of the original base video.", "outputName": "enhancedVideoURL", "promptInstruction": "Take the base voice-over MP3 at {{voiceOverMP3}} and layer the generated product image {{generatedImage}} on top of it to create a promotional video. Determine the optimal placement and timing of the image overlay. Generate a new MP4 video file with the enhancements." }, { "taskID": 215, "semanticTitleOfTask": "Summarize and Return Final Outputs", "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 from a previous skill should be provided, but other supplementary skill outputs can also be included to make the summary more comprehensive.", "inputRequired": [ "generatedImage", "productInformation", "promotionalText", "enhancedVideoURL" ], "outputDescription": "This skill generates a nicely formatted text summary highlighting the key outputs and results from the previous skills that were executed.", "outputName": "finalOutputSummary", "promptInstruction": "Please summarize the following outputs from the previously completed skills: Generated Product Image: {{generatedImage}}, Researched Product Information: {{productInformation}}, Promotional Text: {{promotionalText}}, Final Promotional Video: {{enhancedVideoURL}}. Highlight the most important results and deliverables." }, { "taskID": 216, "semanticTitleOfTask": "Generate a Final Output Selector HTML Page", "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": "A list of file URLs to be embedded and displayed on the HTML selector page. A description of each file should also be provided.", "inputRequired": [ "generatedImage", "promotionalText", "enhancedVideoURL" ], "outputDescription": "This skill returns a URL to the generated HTML page that allows easy selection and viewing of the various embedded elements from the previous skills.", "outputName": "outputSelectorURL", "promptInstruction": "Create an HTML page that embeds the following files: Generated Product Image {{generatedImage}}, Promotional Text {{promotionalText}}, Final Promotional Video {{enhancedVideoURL}}. Include a description with each file. The page should allow easy selection and review of the embedded promotional elements." }, { "taskID": 203, "semanticTitleOfTask": "Convert HTML URL to PDF", "taskDescription": "This skill converts a https link (ie a HTML file) to PDF file", "inputDescription": "The https URL of the HTML file to be converted", "inputRequired": [ "outputSelectorURL" ], "outputDescription": "This skill returns a link to the generated PDF file, providing both an internal server URL and an external URL.", "outputName": "pdfURL", "promptInstruction": "Please convert the promotional HTML file at the following URL into a PDF document: {{outputSelectorURL}}" }, { "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": "A CSV file URL, the email of the customer the software is for, a description of what the software should do, and a title for the software.", "inputRequired": [ "VARIABLE1", "VARIABLE2", "VARIABLE3" ], "outputDescription": "This skill returns a summary of the database software that was generated, including the URL where it is accessible and login instructions for the customer.", "outputName": "databaseSoftwareSummary", "promptInstruction": "Create a searchable and filterable database application using the data in this CSV file: {{VARIABLE1}}. The software is for the customer with email {{VARIABLE2}}. Here is a description of what the software should do: {{VARIABLE3}}. Provide a summary of the completed application, access URL and any login details." }, { "taskID": 205, "semanticTitleOfTask": "Build a Software Tool for Any 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": "A keyword, topic or product description that the software tool should be built around.", "inputRequired": [ "VARIABLE1" ], "outputDescription": "The skill returns a URL where the generated software can be accessed, along with a description of what the tool does.", "outputName": "softwareToolSummary", "promptInstruction": "Create a GPT powered software tool related to the following topic: {{VARIABLE1}}. The tool should provide some valuable functionality that a user would pay for. Provide the URL to access the completed tool and a description of its key features and benefits." } ] ```
Happy? Now Copy-Paste To Proceed...
BACK TO SUBAGENTS
COPY TO CLIPBOARD