Viral Video Factory From Research - 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

[
  {
    "taskID": 216,
    "semanticTitleOfTask": "Research Topic (Or Keyword) Deeply",
    "taskDescription": "Analyzes YouTube links and topic(s) to identify trending content, engagement metrics, and patterns for successful videos, then summarizes key findings in a concise format (up to 2000 characters).",
    "inputDescription": "Requires one or more YouTube channel URLs plus a list of topics to investigate. Gathers info on channel performance, audience engagement rates, posting frequency, and emerging content trends.",
    "inputRequired": [
      "VARIABLE1",
      "VARIABLE2"
    ],
    "outputDescription": "A single text output containing a structured research summary (up to 2000 characters) that highlights performance insights about the provided channels/topics.",
    "outputName": "research_summary",
    "promptInstruction": "As a YouTube content research specialist, analyze the provided channel(s) and topic(s). Focus on content patterns, typical view counts, engagement rates, posting frequencies, top-performing videos, and current audience trends. Compile a concise summary of findings (max 2000 chars) emphasizing practical insights for upcoming content."
  },
  {
    "taskID": 218,
    "semanticTitleOfTask": "Brainstorm Related Keywords",
    "taskDescription": "Processes the research summary to find 4–10 relevant, high-potential keywords or phrases, noting search volume, competition, and potential for audience interest in short-form content.",
    "inputDescription": "Takes the research summary to generate keywords with brief context on their viability, search volume, competition levels, and any notable trending behavior.",
    "inputRequired": [
      "research_summary"
    ],
    "outputDescription": "A text file/list containing 4–10 potential keywords, each with brief performance notes or data points about search trends, relevance, and short-form video potential.",
    "outputName": "keyword_ideas",
    "promptInstruction": "As a keyword research specialist, examine the research summary to generate 4–10 promising keywords or phrases. For each, include a heading and 1–2 lines of data about search volume, competition, and trending patterns. Focus on keywords that align strongly with the original topic(s) and have high potential for short-form video success."
  },
  {
    "taskID": 223,
    "semanticTitleOfTask": "Summarize Multiple Files Into A Single Output",
    "taskDescription": "Combines the research summary and the generated keyword list into a final JSON with top-level 'summary' and 'keywords' fields. Only the top 5 most promising keywords (with short data) should be included.",
    "inputDescription": "Needs the research summary and the keyword list. This information is merged into a single JSON structure containing the summary and 5 selected keywords.",
    "inputRequired": [
      "research_summary",
      "keyword_ideas"
    ],
    "outputDescription": "A final JSON object with two main fields: 'summary' (the up to 2000-char research) and 'keywords', an array of up to 5 objects featuring 'keyword' and 'data_points'.",
    "outputName": "topics_and_keywords",
    "promptInstruction": "Combine the full research summary with up to 5 relevant keywords into a single valid JSON object. Use the field name 'summary' for the research text. For the selected keywords, include an array 'keywords' where each entry has 'keyword' and 'data_points'. Ensure proper JSON formatting and character escaping."
  },
  {
    "taskID": 171,
    "semanticTitleOfTask": "Generate a High-Engagement Voice Over Script Based on Provided Research and Keywords",
    "taskDescription": "Creates a short-form (45–60 seconds) or long-form (3–10 minutes) voice-over script using the research data and script parameters. The script includes hooks, pacing cues, emphasis notes, and a natural, engaging tone to retain viewer attention.",
    "inputDescription": "Requires a JSON file with summarized research and keywords, plus script parameters specifying length, tone, and style. The data identifies trending topics while the parameters define the script’s direction and format needs.",
    "inputRequired": [
      "topics_and_keywords",
      "VARIABLE3"
    ],
    "outputDescription": "Outputs a single text-based structure containing both short-form and optional long-form scripts, integrating research data and following the specified length and style guidelines.",
    "outputName": "script_output",
    "promptInstruction": "You are an expert video script writer specializing in viral social media content. Using the provided research and keywords, create a [short-form/long-form] script that's engaging and optimized for faceless video content. Include a hook in the first 3 seconds, maintain pacing for voice-over delivery, and add timing markers and emphasis notes. Follow these script-parameters and topics_and_keywords. The final script should feel natural when read aloud and keep viewers watching throughout."
  },
  {
    "taskID": 170,
    "semanticTitleOfTask": "Convert Script Text to Natural-Sounding Voice Over in MP3",
    "taskDescription": "Generates an AI-narrated voice-over from the script text, ensuring proper pacing, tone, and clarity. Produces references to short-form and long-form MP3 files in a single output object.",
    "inputDescription": "Requires the text-based script output from the previous task. The TTS system processes the short-form and/or long-form script to produce MP3 voice-over tracks with consistent volume and clarity.",
    "inputRequired": [
      "script_output"
    ],
    "outputDescription": "A single JSON reference containing the file paths or metadata for the generated short-form and long-form voice-over MP3s.",
    "outputName": "voiceover_output",
    "promptInstruction": "no instruction"
  },
  {
    "taskID": 224,
    "semanticTitleOfTask": "Generate JSON Summary of All Script and Voice-Over Assets",
    "taskDescription": "Compiles references to all generated script text and MP3 voice-over files into a single JSON, including file paths, durations, word counts, format details, and timestamps.",
    "inputDescription": "Requires the final script text output and its corresponding voice-over output. The system extracts metadata such as file paths, creation times, durations, and word counts.",
    "inputRequired": [
      "script_output",
      "voiceover_output"
    ],
    "outputDescription": "Provides a JSON file outlining each script and voice-over reference, listing creation timestamps, durations, and assigned keywords or other metadata. This data is crucial for the next subagent.",
    "outputName": "script_vo_summary",
    "promptInstruction": "Create a comprehensive JSON summary listing each script and voice-over reference. For each, include file path, file type, duration (if audio), word count (if text), format (short/long), creation timestamp, relevant keywords, and any additional metadata. Organize the JSON to clearly separate short-form and long-form entries."
  },
  {
    "taskID": 201,
    "semanticTitleOfTask": "Generate short-form vertical text slide video",
    "taskDescription": "Processes relevant short-form script and MP3 voice-over from the summary to create a vertical (9:16) text slide video. It synchronizes text with the audio, producing a quick slideshow-style MP4 for short-form platforms.",
    "inputDescription": "Uses data in script_vo_summary to locate short-form script and voice-over, then renders text slides in sync with the voice-over, resulting in a vertical 9:16 video.",
    "inputRequired": [
      "script_vo_summary"
    ],
    "outputDescription": "A vertical (9:16) MP4 video displaying text slides synced to the voice-over, suitable for short-form content.",
    "outputName": "base_short_form_video",
    "promptInstruction": "no instruction"
  },
  {
    "taskID": 205,
    "semanticTitleOfTask": "Get royalty-free vertical stock footage",
    "taskDescription": "Retrieves up to five relevant vertical (9:16) stock footage clips based on keywords. Aims for dynamic, high-quality visuals without text overlays or prominent faces, suitable for short-form social media videos.",
    "inputDescription": "Takes in the research data from topics_and_keywords. For each keyword, it composes a search query to locate 9:16 footage that complements the topic.",
    "inputRequired": [
      "topics_and_keywords"
    ],
    "outputDescription": "A list of up to five URLs pointing to royalty-free vertical (9:16) video clips for enhancing the short-form video.",
    "outputName": "vertical_stock_footage_clips",
    "promptInstruction": "Generate a search query for stock footage that would complement a video about 'keyword'. The footage should be vertical (9:16) format and suitable for social media. Focus on dynamic, engaging visuals that illustrate 'keyword' without being too literal. Avoid footage with text overlays or people's faces. Prioritize clips with natural movement and high visual impact."
  },
  {
    "taskID": 199,
    "semanticTitleOfTask": "Combine vertical videos and finalize short-form output",
    "taskDescription": "Overlays or splices selected vertical stock footage clips onto the base short-form MP4. It can also incorporate additional visuals, creating a complete, polished short-form video.",
    "inputDescription": "Requires the base_short_form_video file and selected vertical stock footage clips. These are merged into a cohesive final short-form video.",
    "inputRequired": [
      "base_short_form_video",
      "vertical_stock_footage_clips"
    ],
    "outputDescription": "A final short-form MP4 (9:16) that merges the text slide video with relevant stock footage for an engaging video.",
    "outputName": "final_short_form_video",
    "promptInstruction": "no instruction"
  },
  {
    "taskID": 200,
    "semanticTitleOfTask": "Generate long-form horizontal text slide video",
    "taskDescription": "Processes a long-form script and MP3 voice-over from the summary to create a horizontal (16:9) text slide video, synchronizing text with audio in a slideshow-style MP4.",
    "inputDescription": "Takes references from script_vo_summary to locate the long-form script and voice-over, rendering text slides in a 16:9 aspect ratio.",
    "inputRequired": [
      "script_vo_summary"
    ],
    "outputDescription": "A base long-form MP4 video in 16:9 format containing text slides aligned to the voice-over.",
    "outputName": "base_long_form_video",
    "promptInstruction": "no instruction"
  },
  {
    "taskID": 204,
    "semanticTitleOfTask": "Get royalty-free horizontal stock footage",
    "taskDescription": "Retrieves up to five relevant horizontal (16:9) stock footage clips based on keywords. Aims for cinematic visuals without text overlays or prominent faces, suitable for long-form YouTube content.",
    "inputDescription": "Takes in the research data from topics_and_keywords to find 16:9 footage that complements the selected topic.",
    "inputRequired": [
      "topics_and_keywords"
    ],
    "outputDescription": "A list of up to five URLs pointing to royalty-free horizontal (16:9) video clips to enhance the long-form video.",
    "outputName": "horizontal_stock_footage_clips",
    "promptInstruction": "Generate a search query for stock footage that would complement a YouTube video about 'keyword'. The footage should be horizontal (16:9) format and suitable for standard YouTube viewing. Focus on professional, high-quality visuals that illustrate 'keyword' without being too literal. Avoid footage with text overlays or people's faces. Prioritize clips with smooth motion and cinematic quality."
  },
  {
    "taskID": 206,
    "semanticTitleOfTask": "Combine horizontal videos and finalize long-form output",
    "taskDescription": "Merges selected horizontal stock footage clips with the base long-form MP4. Can also integrate additional visuals or images, resulting in a comprehensive long-form video suitable for YouTube.",
    "inputDescription": "Requires the base_long_form_video and up to two chosen horizontal stock footage clips. These are spliced or overlaid for a cohesive final long-form video.",
    "inputRequired": [
      "base_long_form_video",
      "horizontal_stock_footage_clips"
    ],
    "outputDescription": "A finalized long-form MP4 (16:9) that combines the text slide video with relevant stock footage for a more engaging viewing experience.",
    "outputName": "final_long_form_video",
    "promptInstruction": "no instruction"
  },
  {
    "taskID": 225,
    "semanticTitleOfTask": "Summarize all outputs into JSON",
    "taskDescription": "Compiles the final short-form and (optionally) long-form video outputs into a JSON file. The summary references file paths or URLs along with relevant metadata.",
    "inputDescription": "Takes final_short_form_video and final_long_form_video. These references are gathered for easy retrieval or subsequent steps.",
    "inputRequired": [
      "final_short_form_video",
      "final_long_form_video"
    ],
    "outputDescription": "A single JSON file referencing the final short-form and long-form videos, forming an overview of the completed assembly process.",
    "outputName": "video_assembly_summary",
    "promptInstruction": "no instruction"
  },
  {
    "taskID": 202,
    "semanticTitleOfTask": "Extract Video Frames for Thumbnail Generation (Up to 3 Key Frames)",
    "taskDescription": "Automatically analyzes the final MP4 video(s) and identifies up to three key frames suitable for thumbnails. Focus on clear, visually appealing moments.",
    "inputDescription": "Requires video_assembly_summary and optional parameters specifying how to detect the best frames, such as frame count or content-based cues.",
    "inputRequired": [
      "video_assembly_summary",
      "frame_extraction_parameters"
    ],
    "outputDescription": "A collection of up to three extracted frames, referencing timestamps and providing a brief reason for selection.",
    "outputName": "extracted_thumbnails",
    "promptInstruction": "no instruction"
  },
  {
    "taskID": 222,
    "semanticTitleOfTask": "Generate Custom Thumbnail Images with Bold Text Overlay",
    "taskDescription": "Creates 1–2 custom thumbnail designs by overlaying relevant text and branding elements onto a background or extracted frame, targeting a high click-through rate.",
    "inputDescription": "Requires the topics_and_keywords for text content, as well as style or branding parameters such as fonts, color schemes, or platform guidelines.",
    "inputRequired": [
      "topics_and_keywords",
      "metadata_parameters",
      "brand_guidelines"
    ],
    "outputDescription": "Delivers 1–2 thumbnail images in PNG/JPG format, each featuring attention-grabbing text and visuals aligned with the provided guidelines.",
    "outputName": "custom_thumbnails",
    "promptInstruction": "You are a YouTube thumbnail designer specializing in high-CTR designs. Create a thumbnail design specification following these guidelines:\n1. Use the topic `topic` and keywords `keywords` as inspiration\n2. Design should be bold and eye-catching while remaining honest to content\n3. Include text placement suggestions (max 4-5 words)\n4. Specify background colors/gradients\n5. Define text styling (font, size, color, effects)\n6. Note additional visual elements or overlays\n7. Ensure design follows platform guidelines for dimension and text visibility\nProvide the complete design specification in clear, implementable terms."
  },
  {
    "taskID": 190,
    "semanticTitleOfTask": "Generate SEO-Optimized Video Title, Description, and Tags",
    "taskDescription": "Produces a keyword-focused video title (up to 60 characters), a compelling description that includes relevant hashtags and calls-to-action, and a list of tags to improve discoverability.",
    "inputDescription": "Requires target topic, main keywords, final video details, and any SEO or scheduling instructions. The information is used to craft a structured JSON with an optimized title, description, and tag list.",
    "inputRequired": [
      "topics_and_keywords",
      "metadata_parameters",
      "video_assembly_summary"
    ],
    "outputDescription": "A JSON object containing a recommended video title, detailed description (including hashtags), and a list of relevant tags, aligned with YouTube’s algorithm.",
    "outputName": "video_metadata",
    "promptInstruction": "You are a YouTube SEO specialist. Using the provided topic `topic` and keywords `keywords`, create:\n1. Title (max 60 characters): Include primary keyword naturally. Use numbers or power words when relevant. No clickbait.\n2. Description (2-3 paragraphs): Main keyword in first sentence. 2-3 relevant hashtags. If long-form, include timestamps. Provide calls to action and relevant links.\n3. Tags (10-15): Start with specific terms, then broader categories. Include trending relevant tags.\nFormat output as structured JSON."
  },
  {
    "taskID": 226,
    "semanticTitleOfTask": "Compile Final Thumbnail and Metadata Package into One JSON",
    "taskDescription": "Aggregates all generated thumbnails and the metadata file into a single JSON summary. References the paths to custom or extracted thumbnail images and the generated video metadata.",
    "inputDescription": "Receives the outputs from the thumbnail creation tasks and the SEO metadata file, consolidating them into a unified, easy-to-reference structure.",
    "inputRequired": [
      "extracted_thumbnails",
      "custom_thumbnails",
      "video_metadata"
    ],
    "outputDescription": "A comprehensive JSON file that references all thumbnail images and the metadata JSON file, forming the complete output package.",
    "outputName": "thumbs_and_metadata_summary",
    "promptInstruction": "no instruction"
  }
]

Happy? Now Copy-Paste To Proceed...

BACK TO SUBAGENTS

COPY TO CLIPBOARD