Speckit.checklist
Generate a custom checklist for the current feature based on user requirements.
Explore
124,276 skills indexed with the new KISS metadata standard.
Generate a custom checklist for the current feature based on user requirements.
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
Phase 3 — Write the full IMRaD research paper, 15+ pages, using gathered sources
Phase 2 — Find, evaluate, and cite at least 5 credible sources for the paper
Phase 1 — Generate a structured outline and thesis statement from a topic
Phase 4 — Format and output the final research paper to .md and .docx
generic skill
generic skill
You ARE the narrator. The investigation speaks directly to you. Intimate, close, unsettling.
How the viewer-builder agent thinks about editorial design. Content analysis → design decisions. This is the intelligence layer that makes each investigation feel like a unique editorial product.
Intelligence report. You are reading a classified briefing that happens to have images.
> Extracted from Vercel Web Interface Guidelines, Designing Beautiful Websites (Tristan Manchester), and UI/UX Pro Max. Adapted for GatorSquare Studio viewer context.
Graphic novel. Panel grid. Multiple panels visible at once. Speech bubbles.
The energy of a graphic novel or infographic — but purely in text. Bold, chunky, high-impact. Think: a Vox video script meets an illustrated explainer meets a graphic investigation. Each panel is a FRAME — self-contained, punchy, visually distinct even without images.
Film. Image dominates everything. Text is minimal — like subtitles in a foreign film.
How to customize a template viewer for a specific investigation. The agent reads the project data and derives palette, intro, typography, and personality.
**When to use:** After knowledge extraction is complete. Creates the export.zip for GatorSquare upload.
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.