Explore
124,489 skills indexed with the new KISS metadata standard.
Stage 1 creates identity anchors (neutral grey, no backgrounds). Scene direction uses two layers: the **original plan** (written upfront) and **evolved prompts** (adapted after seeing each panel's actual output). Both are stored.
Prompting the model to generate a 2×3 (or NxM) grid of sequential panels in a single image does not work for production comics.
Runs one production session producing investigations for a batch of users. The session agent reads CSVs, selects the correct template per user, spawns one subagent per investigation, validates output, and packages results.
The camera IS a character. The viewer doesn't watch a scene — they ARE in the scene. Every panel is one camera position or movement, like directing a video shoot frame by frame.
Prompt engineering techniques specifically for generating sepia-toned documentary-style images via Gemini. The default art style for GatorSquare investigations.
How to create production-quality reference sheets for ANY entity — characters, rooms, objects, props. Each entity gets its OWN folder with its OWN sheets. They're spices you pick and combine per-scene.
Only send character reference PNGs for characters whose faces/features are actually visible and close enough to matter in the current panel. Sending refs for distant or occluded characters causes visual bleed.
Every panel prompt in a first-person POV sequence must explicitly state the camera identity, height, and angle — not just the first panel.
In sequential POV, the camera IS a person walking through space. As they move forward, objects in frame grow larger naturally — this creates a zoom effect through physical movement, not lens manipulation.
The definitive routing table for GatorSquare Studio. When a task arrives, this skill tells you: which agent handles it, what files they need, what they produce, and who runs next.
Classical and modern techniques for creating convincing depth, volume, and spatial perception in 2D images — translated into prompt language for AI image generation.
Characters and key props get reference PNGs — generated with the most expensive model available. These PNGs are sent alongside prompts to anchor identity across the sequence.
Gemini image models ("Nano Banana" = Flash, "Nano Banana Pro" = Pro) respond to narrative-driven structured prompts, not keyword stuffing. These are language models that generate images — prompt them like you're briefing a cinematographer, not tagging a search engine.
Generate panel images for one investigation — **one model per project** (preferably Gemini) — with proper panel assignment, naming, download, and verification. No overlaps, no missed panels.
Use expensive models at anchor points, cheap models for everything between. Quality propagates through the chain.
The meta-skill. The skill that produces all other skills. The ability to recognize when something is a learning, codify it autonomously, and make it available for future sessions — without being told.
Extract structured knowledge from every panel's narration and scene direction. This is the intelligence layer that feeds the knowledge graph. Every moment carries entities, causality, emotion, visual elements, and logic. The AI that wrote the content extracts the knowledge — not a weaker NLP tool af
The knowledge graph is the connective tissue between investigations. Every investigation stands alone as a visual piece — the graph reveals that they are chapters in the same book.
**When to use:** After the investigation is written (brief.md, script.md, scene-plan.md complete). Before packaging for upload.
Generates one complete investigation (25 panels + basic metadata) for a single user/project combination. This is the production pipeline — one invocation produces one investigation.
Techniques for generating clear, accurate, visually compelling infographic panels and data visualizations using AI image generation. Covers chart types, visual hierarchy, Nano Banana prompting for data-heavy images, and mixed-media approaches.
- Research queries requiring Gemini's knowledge and source citations
Generate panel images for investigations using Gemini in the browser via Chrome MCP extension. Uses the **multi-tab fire-and-harvest** approach for throughput with reliable single-tab download accuracy.
The GatorSquare editorial voice — institutional weight with vivid investigative storytelling. Not pop science. Not academic. The register that gets read at Harvard and shared by economists.