What Shall We Build Next?

Describe

Describe your task

Refine

Refine the plan

SubAgents

Review all agents

Deploy

Deploy your agent

A) SUBAGENT SUMMARY  
This subagent (VSL Script Segmenter) reads the entire VSL script and uses a powerful text-understanding LLM to break it into up to around 6 labeled segments, returning the exact text for each segment.

B) FINAL TASK OUTPUT  
[segmented-vsl-script] → A structured text output in which each segment is labeled (e.g., “Segment 1,” “Segment 2,” …) and contains the exact script text.

C) SUBAGENT INPUT  
{vsl-script} - The full text of the Video Sales Letter to be segmented.

E) SUBAGENT TASK SUMMARY  
1) Input: Receive {vsl-script}.  
2) Action Step (Skill #223 - Powerful LLM Prompt-to-Text Response):  
   • Prompt the LLM with instructions to identify main messaging or emotional beats in the provided script.  
   • Instruct it to return up to ~6 segments (though fewer or more are acceptable if the script’s natural flow warrants it).  
   • Each segment must be labeled clearly (“Segment 1,” “Segment 2,” etc.).  
   • Each segment must include the exact snippet of the VSL script that it represents.  
3) Output: The skill’s text response is the final subagent output, named [segmented-vsl-script].

F) SILOS  
Because this subagent only requires a single LLM action to transform the {vsl-script} into labeled segments, there are no separate silos. The entire segmentation process is contained in a single skill invocation.

SubAgent #1 - Diagram

Expand Diagram

A) SUBAGENT SUMMARY:  
The Visual Prompt Generator takes the labeled VSL segments, plus the product’s name and description, and produces 2–3 highly detailed visual prompt ideas for each segment.

B) FINAL TASK OUTPUT:  
[visual-prompts] → A single structured text output that, for each labeled VSL segment, lists 2–3 concise visual prompt ideas.

C) SUBAGENT INPUT:  
1. [segmented-vsl-script] (the labeled segments from Subagent 1)  
2. {product-name} (the name of the product)  
3. {product-description} (the product’s target audience, brand voice, and key selling points)

E) SUBAGENT TASK SUMMARY:  
Below is the step-by-step workflow for Subagent 2:

1) Receive subagent final inputs:  
   • [segmented-vsl-script]  
   • {product-name}  
   • {product-description}

2) Call Skill #223 (Powerful LLM Prompt-to-Text Response):  
   • Inputs to this skill:  
     - A prompt referencing each VSL segment from [segmented-vsl-script], together with {product-name} and {product-description}.  
     - Instruction to generate 2–3 distinct visual prompts for each labeled segment, describing scene, camera angle, lighting, mood, and how the product might appear or be symbolized.  
   • Output from this skill:  
     - A structured text or JSON-like array containing the visual prompts grouped by each labeled segment.

3) Subagent final output:  
   • [visual-prompts]: The consolidated list of visual prompt ideas for each segment.

F) SILOS:  
This subagent operates in a single silo:  
• SILO 1: “Generate Visual Prompts”  
  - Input: [segmented-vsl-script], {product-name}, {product-description}  
  - Action: Skill #223 → Generate 2–3 distinct visual prompt ideas per segment  
  - Output: [visual-prompts]

SubAgent #2 - Diagram

Expand Diagram

A) SUBAGENT SUMMARY  
This subagent (“Transitions & Music Advisor”) provides transition recommendations between VSL segments and also suggests suitable music genres/moods plus optional sound effects based on the product description, brand style, and the VSL’s pacing.

B) FINAL TASK OUTPUT  
[transitions-music-sfx] → A structured text-based output listing:  
• Recommended transition type for each segment boundary (e.g., Fade, Hard Cut, L-Cut)  
• 2–3 music genres or moods  
• 1–2 optional sound effects (if relevant)

C) SUBAGENT INPUT  
1) [segmented-vsl-script] (the labeled segments from Subagent 1)  
2) [visual-prompts] (optional visual ideas from Subagent 2, to understand pacing/visual style)  
3) {product-description} (includes brand voice, target audience, style cues)

E) SUBAGENT TASK SUMMARY  
1) Use Skill #218 (Brainstorm Related Keywords) with {product-description} to identify 2–3 keywords/themes relevant to the music or sound design.  
   Input → {product-description}  
   Output → [sound-related-keywords]

2) Use Skill #223 (Powerful LLM Prompt-to-Text Response) to generate the final text output that:  
   • Reads [segmented-vsl-script] to determine pacing and count of segments  
   • Optionally references [visual-prompts] to match transition style with visual approach  
   • Incorporates [sound-related-keywords] to propose 2–3 music genres/moods and 1–2 optional SFX ideas  
   • Lists transitions for each labeled segment boundary  
   Input → [segmented-vsl-script], [visual-prompts], [sound-related-keywords], {product-description}  
   Output → [transitions-music-sfx]

F) SILOS  
• SILO 1 – Brainstorm Sound Keywords  
   - Skill #218 (input: {product-description}) → output: [sound-related-keywords]

• SILO 2 – Compile Transitions, Music Suggestions, and SFX  
   - Skill #223 (input: [segmented-vsl-script], [visual-prompts], [sound-related-keywords], {product-description})  
   - Final Output = [transitions-music-sfx]

SubAgent #3 - Diagram

Expand Flow

A) SUBAGENT SUMMARY  
This subagent (Document Compiler) takes the segmented VSL script, the visual prompts per segment, and the transitions/music/sfx suggestions, then compiles everything into a single text document (“VideoAdCreativeBrief.txt”).

B) FINAL TASK OUTPUT  
[video-ad-creative-brief] → A single text-based document (named “VideoAdCreativeBrief.txt”) that includes:  
• Each labeled VSL segment (exact script text).  
• 2–3 associated visual prompt ideas per segment.  
• Transition suggestion after each segment (if applicable).  
• A dedicated section at the end for music and sound design suggestions.

C) SUBAGENT INPUT  
• [segmented-vsl-script]  (from Subagent 1)  
• [visual-prompts]        (from Subagent 2)  
• [transitions-music-sfx] (from Subagent 3)

E) SUBAGENT TASK SUMMARY  
1) The subagent receives all the inputs ([segmented-vsl-script], [visual-prompts], [transitions-music-sfx]).  
2) It then invokes Skill #223 (Powerful LLM Prompt-to-Text Response) with a carefully constructed prompt that:  
   • Takes each labeled VSL segment and includes it as “VSL Script Reference.”  
   • Pairs each segment with the corresponding 2–3 visual prompt ideas.  
   • Inserts the transition suggestion (from [transitions-music-sfx]) that goes after each segment.  
   • Appends a final section detailing music genres, moods, and (optional) SFX suggestions.  
3) The final textual output of Skill #223 is the fully compiled “VideoAdCreativeBrief.txt” document.  
4) This output is saved as [video-ad-creative-brief] and returned by the subagent.

F) SILOS  
For this subagent, there is only one main silo (the single LLM action to compile everything). No additional subdivisions or steps are needed.