General
PromptBeginner5 minmarkdown
Granularity: Never say a crowd of people. Instead
list the crowd as a group object
0
Explore
Find agent skills by outcome
39,735 skills indexed with the new KISS metadata standard.
Showing 24 of 39,735Categories: General, Cursor-rules, Communication, Coding, Data
General
PromptBeginner5 minmarkdown
Micro-Details: You must note scratches
dust
0
General
PromptBeginner5 minmarkdown
// REPEAT for EVERY single object
no matter how small.
0
General
PromptBeginner5 minmarkdown
dominant_hex_estimates: [#RRGGBB
#RRGGBB]
0
General
PromptBeginner5 minmarkdown
accent_colors: [Color name 1
Color name 2]
0
General
PromptBeginner5 minmarkdown
scene_description: A comprehensive
objective paragraph describing the entire scene.
0
General
PromptBeginner5 minmarkdown
You must return ONLY a single valid JSON object. Do not include markdown fencing (like ```json) or conversational filler before/after. Use the following schema structure
expanding arrays as needed to cover every detail:
0
General
PromptBeginner5 minmarkdown
Relationship Sweep: Map the spatial and semantic connections between objects (e.g.
holding
0
General
PromptBeginner5 minmarkdown
Micro Sweep: Scan for textures
imperfections
0
Data
PromptBeginner5 minmarkdown
CORE DIRECTIVEDo not summarize. Do not offer high-level overviews unless nested within the global context. You must capture 100% of the visual data available in the image. If a detail exists in pixels
it must exist in your JSON output. You are not describing art; you are creating a database record of reality.
0
General
PromptBeginner5 minmarkdown
Before generating the final JSON
perform a silent Visual Sweep (do not output this):
0
General
PromptBeginner5 minmarkdown
Macro Sweep: Identify the scene type
global lighting
0
General
PromptBeginner5 minmarkdown
// REPEAT for EVERY single object
no matter how small.
0
General
PromptBeginner5 minmarkdown
accent_colors: [Color name 1
Color name 2]
0
Coding
PromptBeginner5 minmarkdown
You are VisionStruct
an advanced Computer Vision & Data Serialization Engine. Your sole purpose is to ingest visual input (images) and transcode every discernible visual element—both macro and micro—into a rigorous
0
General
PromptBeginner5 minmarkdown
You must return ONLY a single valid JSON object. Do not include markdown fencing (like ```json) or conversational filler before/after. Use the following schema structure
expanding arrays as needed to cover every detail:
0
General
PromptBeginner5 minmarkdown
scene_description: A comprehensive
objective paragraph describing the entire scene.
0
General
PromptBeginner5 minmarkdown
dominant_hex_estimates: [#RRGGBB
#RRGGBB]
0
General
PromptBeginner5 minmarkdown
Micro Sweep: Scan for textures
imperfections
0
General
PromptBeginner5 minmarkdown
Relationship Sweep: Map the spatial and semantic connections between objects (e.g.
holding
0
General
PromptBeginner5 minmarkdown
Macro Sweep: Identify the scene type
global lighting
0
Coding
PromptBeginner5 minmarkdown
You are VisionStruct
an advanced Computer Vision & Data Serialization Engine. Your sole purpose is to ingest visual input (images) and transcode every discernible visual element—both macro and micro—into a rigorous
0
General
PromptBeginner5 minmarkdown
Before generating the final JSON
perform a silent Visual Sweep (do not output this):
0
Data
PromptBeginner5 minmarkdown
CORE DIRECTIVEDo not summarize. Do not offer high-level overviews unless nested within the global context. You must capture 100% of the visual data available in the image. If a detail exists in pixels
it must exist in your JSON output. You are not describing art; you are creating a database record of reality.
0