Composition & Framing — prompt skill for camera & shots

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

9 composition cards — thirds, symmetry, leading lines, negative space, 2.39:1 — for stills and video.

What it does

Composition written as placements a model can follow: where the subject sits, where it looks, and what fills the rest of the frame. Covers rule of thirds, centered symmetry, leading lines, frame within a frame, negative space (copy space for ad titles), foreground layering, two-shots, lead room and widescreen 2.39:1. The same clauses drive image models, so a Nano Banana or FLUX first frame can be composed before any video credits are spent.

Use when

Not for

Install

Not published as a standalone skill yet. Source: https://github.com/vargHQ/skills

Models it drives: veo_3_1, veo_3_1_fast, veo_3_1_lite, omni_flash_1_1, kling_v3, kling_v3_standard, seedance_2_5, seedance_2, minimax_h3_max, nano_banana_2_1, flux_3_image, gpt_image_2_5

Example output

https://skills.varg.ai/previews/craft-composition-framing.webp — Rule of thirds in a real frame: Sintel sits on the right-third line with her head near the upper-right intersection, the cliff fills the lower two thirds and the haze leaves negative space for a title. The thin thirds grid was drawn on by varg. Sintel (2010) frame at 11:34, 2048-px release on archive.org, full 2.35:1 frame. (credit: Sintel (CC BY 3.0) — © copyright Blender Foundation | durian.blender.org, https://archive.org/details/Sintel)

More camera & shots skills