Ad Campaign Pack Generator - 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

```json
[
  {
    "taskID": 218,
    "semanticTitleOfTask": "Generate Niche-Specific Research Keywords",
    "taskDescription": "Transforms core business details into 8–12 highly targeted search terms that will surface the most relevant, top-performing competitor ads across major ad platforms.",
    "inputDescription": "Receives VARIABLE1 (business name), VARIABLE2 (industry / niche) and VARIABLE3 (combined target-audience + product / service description). It analyses these details to understand category, benefits, pain points and audience traits before producing research terms.",
    "inputRequired": ["VARIABLE1", "VARIABLE2", "VARIABLE3"],
    "outputDescription": "keywords_list – a simple text list containing 8-12 carefully crafted search terms (one per line).",
    "outputName": "keywords_list",
    "promptInstruction": "You are a digital marketing strategist. Given VARIABLE1 (business name), VARIABLE2 (industry / niche) and VARIABLE3 (audience + product description), brainstorm 8-12 keyword phrases that will uncover high-performing competitor ads. Include mixes such as: • Industry + audience descriptor • Product type + benefit • Service category + pain point • Platform modifiers (\"facebook ad\", \"instagram ads\"). Return the phrases line-by-line, no numbering or extra text."
  },
  {
    "taskID": 224,
    "semanticTitleOfTask": "Fetch Top Competitor Ads with Oracle Search",
    "taskDescription": "Runs multiple live queries with the generated keyword list and business context, retrieving raw text, image links and meta-data for the top ads currently performing in the specified niche.",
    "inputDescription": "Requires keywords_list, industry, target-audience and product-description to refine query parameters. The task issues about five platform-specific searches and aggregates the returned ad snippets into one raw text file.",
    "inputRequired": ["keywords_list", "industry", "target-audience", "product-description"],
    "outputDescription": "raw_ads_research – a UTF-8 text file containing every ad example returned, including headlines, body copy, CTAs, engagement metrics and any image or video URLs.",
    "outputName": "raw_ads_research",
    "promptInstruction": ""
  },
  {
    "taskID": 223,
    "semanticTitleOfTask": "Analyze Raw Ads to Produce Competitor Summary",
    "taskDescription": "Processes the unstructured ad research file to extract marketing angles, hooks, offers, CTAs and creative patterns, delivering a 1 000–2 500-word markdown report that distills actionable insights.",
    "inputDescription": "Takes raw_ads_research. The LLM scans the ads, clusters recurring themes and composes the markdown report.",
    "inputRequired": ["raw_ads_research"],
    "outputDescription": "competitor_summary – a markdown document detailing dominant angles, hooks, offers, CTAs, visual motifs and key takeaways.",
    "outputName": "competitor_summary",
    "promptInstruction": "You are an advertising analyst. Review RAW_ADS_RESEARCH and extract: 1) Dominant Marketing Angles (3-5) 2) Most Effective Hooks (3-5) 3) Popular Offer Structures (2-3) 4) Common CTA Patterns (2-3) 5) Recurring Visual/Creative Elements (3-4) 6) Key Copywriting Patterns (2-3). Give concrete ad examples. Format as markdown with clear H2 headings, bullet lists and a **Key Takeaways** section."
  },
  {
    "taskID": 185,
    "semanticTitleOfTask": "Generate Structured Ad Copy Variations",
    "taskDescription": "Leverages competitor insights and full business details to craft a complete, ready-to-use ad copy set: 5 headlines, 5 sub-headlines, 3 short bodies and 3 long bodies, output in strict JSON.",
    "inputDescription": "Requires competitor_summary plus business-name, industry, target-audience and product-description.",
    "inputRequired": ["competitor_summary", "business-name", "industry", "target-audience", "product-description"],
    "outputDescription": "ad_copy_json – a JSON document with keys: headlines, sub_headlines, short_form_copy, long_form_copy.",
    "outputName": "ad_copy_json",
    "promptInstruction": "You are an ad copywriter. Using COMPETITOR_SUMMARY and client info, create 5 headlines (≤65 chars), 5 sub-headlines (≤90 chars), 3 short-form bodies (≤100 words) and 3 long-form bodies (≤300 words). Ensure benefit-driven messaging that aligns with successful angles. Return ONLY a JSON object with the specified keys."
  },
  {
    "taskID": 2231,
    "semanticTitleOfTask": "Compile Insight & Copy Bundle Manifest",
    "taskDescription": "Creates a plain-text manifest enumerating every file in the insight-copy bundle, listing filename, byte size, description and timestamp.",
    "inputDescription": "Consumes competitor_summary and ad_copy_json.",
    "inputRequired": ["competitor_summary", "ad_copy_json"],
    "outputDescription": "insight_copy_manifest – a .txt file that documents competitor_summary.md, ad_copy.json and itself.",
    "outputName": "insight_copy_manifest",
    "promptInstruction": "List each file: competitor_summary.md, ad_copy.json, insight_copy_manifest.txt. For each include: Filename | Size (bytes) | One-sentence description | Last-modified ISO timestamp. One file per line."
  },
  {
    "taskID": 2232,
    "semanticTitleOfTask": "Generate Creative Brief from Ad Insights",
    "taskDescription": "Analyses competitor_summary and ad_copy_json, selects the 3-5 strongest headline/angle combinations and converts them into a structured creative brief for image creation.",
    "inputDescription": "Uses competitor_summary and ad_copy_json files.",
    "inputRequired": ["competitor_summary", "ad_copy_json"],
    "outputDescription": "creative_brief_json – a JSON array containing 3-5 objects each specifying filename, headline_text, optional_sub_text, call_to_action, visual_style, recommended_aspect_ratio and short_rationale.",
    "outputName": "creative_brief_json",
    "promptInstruction": "Analyse ad_copy.json and competitor_summary. Select the 5 strongest headline/angle combos for static ads. For each output JSON with keys: filename (creative_0X.png), headline_text, optional_sub_text, call_to_action, visual_style, recommended_aspect_ratio (1080×1350 default) and short_rationale (≤20 words). Return an array of 3-5 objects."
  },
  {
    "taskID": 222,
    "semanticTitleOfTask": "Generate Static Ad Creatives with Text Overlay",
    "taskDescription": "Creates 3-5 high-quality PNG ad images with specified headlines, sub-text, CTAs and visual styles.",
    "inputDescription": "Needs creative_brief_json for design specs and business-name for brand reference.",
    "inputRequired": ["creative_brief_json", "business-name"],
    "outputDescription": "image_creatives – a list or folder containing the generated PNG ad images.",
    "outputName": "image_creatives",
    "promptInstruction": "Generate a [recommended_aspect_ratio] PNG ad for “{business-name}”. Headline: “[headline_text]”. Sub-text/CTA: “[optional_sub_text or call_to_action]”. Style: [visual_style]. Use brand-safe colours, high contrast, no watermarks and professional layout."
  },
  {
    "taskID": 2233,
    "semanticTitleOfTask": "Create Image Manifest Documentation",
    "taskDescription": "Compiles metadata for every generated PNG and writes images_manifest.txt documenting filenames, headlines, rationales, alt text and prompt snippets.",
    "inputDescription": "Takes creative_brief_json and image_creatives.",
    "inputRequired": ["creative_brief_json", "image_creatives"],
    "outputDescription": "images_manifest_txt – a text file (~1-2 KB) listing filename, headline_text, short_rationale, alt_text, recommended_platform and prompt snippet for each creative.",
    "outputName": "images_manifest_txt",
    "promptInstruction": "Combine the list of generated images with creative_brief_json. For every creative, output: filename, headline_text, short_rationale, alt_text (≤15 words), recommended_platform and first 120 characters of the generation prompt. Separate entries with “---”."
  },
  {
    "taskID": 2234,
    "semanticTitleOfTask": "LLM-Storyboard Creation From Winning Angles",
    "taskDescription": "Transforms the strongest headlines and angles in ad_copy.json into a concise 3-5-scene vertical-ad storyboard timed to a 15–30 s runtime.",
    "inputDescription": "Requires business-name and ad_copy_json.",
    "inputRequired": ["business-name", "ad_copy_json"],
    "outputDescription": "storyboard_json – a JSON array where each scene includes time_range, voiceover, text_on_screen and visual_suggestion.",
    "outputName": "storyboard_json",
    "promptInstruction": "Using ad_copy.json, create a detailed 3-5-scene storyboard for a 15–30 s vertical video ad for {{business-name}}. Each scene must include: time_range, voiceover, text_on_screen and visual_suggestion. Return as a JSON array."
  },
  {
    "taskID": 171,
    "semanticTitleOfTask": "LLM-Voice-Over Script From Storyboard",
    "taskDescription": "Converts the storyboard into a single, energetic ≤200-word voice-over script that matches scene timings.",
    "inputDescription": "Needs storyboard_json and business-name.",
    "inputRequired": ["storyboard_json", "business-name"],
    "outputDescription": "video_script_txt – a conversational narration aligned with storyboard scene lengths, ready for TTS.",
    "outputName": "video_script_txt",
    "promptInstruction": "Transform storyboard_json into one flowing, conversational script for {{business-name}}. Max 200 words. Energetic tone for social media. Ensure timing matches the storyboard."
  },
  {
    "taskID": 170,
    "semanticTitleOfTask": "TTS Engine – Generate Voice-Over MP3",
    "taskDescription": "Uses a text-to-speech API to turn the voice-over script into a high-quality MP3 track.",
    "inputDescription": "Requires video_script_txt.",
    "inputRequired": ["video_script_txt"],
    "outputDescription": "voiceover_mp3 – 44.1 kHz audio ≤30 s matching the supplied script.",
    "outputName": "voiceover_mp3",
    "promptInstruction": ""
  },
  {
    "taskID": 198,
    "semanticTitleOfTask": "Speech-to-Text – Timestamped Transcription",
    "taskDescription": "Generates a word-level, time-coded transcript of the voice-over.",
    "inputDescription": "Takes voiceover_mp3 as audio input.",
    "inputRequired": ["voiceover_mp3"],
    "outputDescription": "transcription_with_timings_txt – a text or JSON file listing each word/phrase with start and end times.",
    "outputName": "transcription_with_timings_txt",
    "promptInstruction": ""
  },
  {
    "taskID": 201,
    "semanticTitleOfTask": "Video Generator – Build Text-Slide Base Video",
    "taskDescription": "Creates a 1080×1920 base video that automatically places animated text captions in sync with the voice-over.",
    "inputDescription": "Needs voiceover_mp3 and transcription_with_timings_txt.",
    "inputRequired": ["voiceover_mp3", "transcription_with_timings_txt"],
    "outputDescription": "base_text_video_mp4 – a caption-driven vertical video with clean typography.",
    "outputName": "base_text_video_mp4",
    "promptInstruction": ""
  },
  {
    "taskID": 205,
    "semanticTitleOfTask": "Media Fetcher – Curate Vertical B-Roll Clips",
    "taskDescription": "Searches royalty-free libraries for 3–5 portrait-oriented video clips that visually support the first keyword/angle in ad_copy.json.",
    "inputDescription": "Requires ad_copy_json to extract the primary theme for targeted search.",
    "inputRequired": ["ad_copy_json"],
    "outputDescription": "b_roll_list_txt – a list of MP4 URLs with short descriptions for shortlisted B-roll clips.",
    "outputName": "b_roll_list_txt",
    "promptInstruction": ""
  },
  {
    "taskID": 199,
    "semanticTitleOfTask": "Video Editor – Overlay B-Roll Onto Base",
    "taskDescription": "Combines the captioned base video with selected B-roll at logical breaks, retaining clear captions and brand consistency.",
    "inputDescription": "Requires base_text_video_mp4, b_roll_list_txt and transcription_with_timings_txt.",
    "inputRequired": ["base_text_video_mp4", "b_roll_list_txt", "transcription_with_timings_txt"],
    "outputDescription": "video_ad_mp4 – final 15–30 s vertical ad with integrated B-roll, synced audio and captions.",
    "outputName": "video_ad_mp4",
    "promptInstruction": ""
  },
  {
    "taskID": 2235,
    "semanticTitleOfTask": "LLM-Generate Video Asset Manifest",
    "taskDescription": "Creates a comprehensive manifest summarizing every produced video asset, their specs and deployment tips.",
    "inputDescription": "Needs video_script_txt, voiceover_mp3, storyboard_json, video_ad_mp4 and business-name.",
    "inputRequired": ["video_script_txt", "voiceover_mp3", "storyboard_json", "video_ad_mp4", "business-name"],
    "outputDescription": "video_manifest_txt – a reference file listing asset names, formats, durations, sizes, purposes and platform recommendations.",
    "outputName": "video_manifest_txt",
    "promptInstruction": "Create a manifest for the video ad assets of {{business-name}}. For each file include: Filename, File type, Duration, Size, Primary purpose, Usage guidelines, Technical specs. Provide an overview explaining how assets work together and any platform-specific recommendations."
  },
  {
    "taskID": 186,
    "semanticTitleOfTask": "Generate 6–8 Engaging Social-Media Captions",
    "taskDescription": "Uses competitor research and approved ad copy to craft 6–8 short, scroll-stopping captions highlighting key value propositions and CTAs.",
    "inputDescription": "Requires competitor_summary, ad_copy_json and business-name.",
    "inputRequired": ["competitor_summary", "ad_copy_json", "business-name"],
    "outputDescription": "raw_captions – a text file containing 6–8 creative captions separated by “---”.",
    "outputName": "raw_captions",
    "promptInstruction": "You are a social-media copywriter for {{business-name}}. Using the competitor summary and ad copy, write 6–8 unique captions (1–3 short paragraphs each). Each caption must hook in the first line, communicate one distinct value angle, end with a persuasive CTA and reflect brand tone. Separate captions with \"---\"."
  },
  {
    "taskID": 2236,
    "semanticTitleOfTask": "Transform Captions into JSON with Optimized Hashtags",
    "taskDescription": "Takes raw captions and appends 5–8 highly relevant hashtags to each, outputting a JSON array that pairs every caption with its hashtags.",
    "inputDescription": "Needs raw_captions.",
    "inputRequired": ["raw_captions"],
    "outputDescription": "captions_and_hashtags – a JSON array of objects with keys caption and hashtags.",
    "outputName": "captions_and_hashtags",
    "promptInstruction": "For each caption, generate 5–8 relevant hashtags mixing popular and niche tags, avoiding banned terms. Return valid JSON with objects {\"caption\":…, \"hashtags\":[…]} only."
  },
  {
    "taskID": 1851,
    "semanticTitleOfTask": "Write Comprehensive Quick-Start Deployment Guide",
    "taskDescription": "Creates a step-by-step markdown guide that inventories all assets, explains optimal placements, offers A/B testing advice and lists technical specs for immediate launch.",
    "inputDescription": "Consumes competitor_summary, ad_copy_json, image_creatives, video_ad_mp4, captions_and_hashtags and business-name.",
    "inputRequired": ["competitor_summary", "ad_copy_json", "image_creatives", "video_ad_mp4", "captions_and_hashtags", "business-name"],
    "outputDescription": "quick_start_guide – a markdown file with sections on asset overview, upload instructions, A/B testing, specs, budget and pro tips.",
    "outputName": "quick_start_guide",
    "promptInstruction": "Draft a markdown quick-start guide for {{business-name}} that includes: 1) Asset inventory, 2) Recommended placements (FB, IG, TikTok, etc.), 3) A/B testing plan, 4) Upload specs, 5) Starter budget tips, 6) Pro tips & common pitfalls. Use H2/H3 headings and bullet points."
  },
  {
    "taskID": "Internal-1",
    "semanticTitleOfTask": "Assemble Structured Directory Tree with All Assets",
    "taskDescription": "Builds the directory tree /copy, /creatives/images, /creatives/video and /deployment, then copies every asset into its proper location.",
    "inputDescription": "Requires competitor_summary, ad_copy_json, image_creatives, video_ad_mp4, captions_and_hashtags and quick_start_guide.",
    "inputRequired": ["competitor_summary", "ad_copy_json", "image_creatives", "video_ad_mp4", "captions_and_hashtags", "quick_start_guide"],
    "outputDescription": "structured_asset_tree – a populated directory tree at mini_ad_campaign_{business-name}/ ready for compression.",
    "outputName": "structured_asset_tree",
    "promptInstruction": ""
  },
  {
    "taskID": "Internal-2",
    "semanticTitleOfTask": "Compress Structured Asset Tree into ZIP",
    "taskDescription": "Creates mini_ad_campaign_{business-name}.zip with maximum compatibility settings.",
    "inputDescription": "Needs the root path of structured_asset_tree.",
    "inputRequired": ["structured_asset_tree"],
    "outputDescription": "campaign_zip – a compressed archive containing the entire directory hierarchy.",
    "outputName": "campaign_zip",
    "promptInstruction": ""
  },
  {
    "taskID": 2237,
    "semanticTitleOfTask": "Generate Human-Readable Delivery Manifest with Checksums",
    "taskDescription": "Creates delivery_manifest.txt listing every file in the ZIP, its size, SHA256 checksum and notes whether optional video assets are included.",
    "inputDescription": "Requires campaign_zip and business-name to document each asset accurately.",
    "inputRequired": ["campaign_zip", "business-name"],
    "outputDescription": "delivery_manifest – a text file that inventories all contents, sizes, checksums and provides a concise project overview.",
    "outputName": "delivery_manifest",
    "promptInstruction": "Produce a delivery manifest for {{business-name}}’s mini campaign. Start with a short overview paragraph, then list each file with its relative path, size (KB) and SHA256 checksum in a neatly aligned table. Add a final checklist for asset verification and note if video assets are present. End with a ‘Generated on’ timestamp."
  }
]
```

Happy? Now Copy-Paste To Proceed...

BACK TO SUBAGENTS

COPY TO CLIPBOARD