Explore

Find agent skills by outcome

98,977 skills indexed with the new KISS metadata standard.

Showing 24 of 98,977Categories: Data & Insights, Coding & Debugging, Creative, General, Cursor-rules, Data

Vision-to-json

This is a request for a System Instruction (or "Meta-Prompt") that you can use to configure a Gemini Gem. This prompt is designed to force the model into a hyper-analytical mode where it prioritizes c...

Find agent skills by outcome

Vision-to-json

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

Please output the translation in a clear

Use my voice: smart

scene_description: A comprehensive

dominant_hex_estimates: [#RRGGBB

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

Micro Sweep: Scan for textures

Micro Sweep: Scan for textures

Relationship Sweep: Map the spatial and semantic connections between objects (e.g.

Macro Sweep: Identify the scene type

Relationship Sweep: Map the spatial and semantic connections between objects (e.g.

Macro Sweep: Identify the scene type

I want people to say

Before generating the final JSON

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

accent_colors: [Color name 1

// REPEAT for EVERY single object

Hiccup and Toothless appear most frequently

Correct original outfits and dragon designs from the movies

Fully visible heads

● CTA (if any): [Subtle or direct

Sticker

Random scattered layout