Video Moodboard — style skill for style references
For AI agents: find the right skill in one call —
curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the how-to page. From a terminal:curl -fsSL https://varg.ai/install | shinstalls the vargai CLI (https://varg.ai/how-to/cli.md):vargai searchandvargai install <slug>with no key, every varg model aftervargai login.
A moodboard AI video models follow: lines ranked by what matters most, every line a number, drawn as a board and checked on stills. 450+ links.
- Type: Style · Style references
- Slug:
video-moodboard - Status: live
- Publisher: varg (varg, verified)
- License: MIT
- Source: https://github.com/vargHQ/skills/tree/main/video-moodboard
- Works in: Claude Code, Codex, Cursor, Gemini CLI
- Requires: python3 with Pillow (scripts/palette.py), Optional: a varg key for the 3 test stills
- Cost: 0 credits; test stills 5 each — Writing the board is free. Test stills on varg: Nano Banana 2.1 or Seedream 5 Pro, 5 credits each (measured 2026-11-03).
- Runtime: About 15 to 25 minutes with test stills
What it does
A moodboard for an AI video is a short list of lines a model can obey and a person can check: where the light comes from, which five colours, which lens, which film stock, which font, which camera move. This skill writes it in the order that matters most, taken from a 48-still test on Nano Banana 2.1 and Seedream 5 Pro with two blind judges, 6,086 X posts and 14 official prompt guides: references, light, subject lock, framing, palette, motion, texture, type, sound. Light was the only line that made frames look more like film; an invented hex palette was obeyed best but looked less like film, so hex comes from a reference frame. It writes moodboard.md and a visual board.html (light diagram, swatches, framing guide, motion timeline, type specimen), tests the board on 3 stills, checks each line (palette by ΔE), and stops for approval before any video. references/links.md holds 450+ sources: 72 reference and tool databases with access, price and terms, 50 tools creators name on X, every page of 14 vendor guides, benchmarks, and all 123 cited creator posts.
Use when
- Make a moodboard, style bible or look-and-feel board for an AI video
- Before prompting Seedance, Kling, Veo, Nano Banana or Midjourney
- Make it not look like AI: write light, palette, framing and texture as numbers
- Check test stills against the board before paying for video
- Find the right database for palette, light, type or motion references
Not for
- Finding references from scratch (use find-references first)
- Per-shot video prompts after the board is approved (use varg-video-prompting)
- Feeding found film frames into a model
Install
- Claude Code:
claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg - Codex:
npx skills add vargHQ/skills --skill video-moodboard -a codex -y - Cursor:
npx skills add vargHQ/skills --skill video-moodboard -a cursor -y - Gemini CLI:
npx skills add vargHQ/skills --skill video-moodboard -a gemini-cli -y - Any agent, with the vargai CLI:
vargai install video-moodboard
Example output
https://s3.varg.ai/files/4325c578-378d-4c43-ae53-3cc3218df1ea/file_6d1cb6e5cc93.mp4 — From the video-moodboard explainer (HyperFrames, varg branding, 2026-11-03): the same prompt without and with a board (credit: varg, https://github.com/vargHQ/skills/tree/main/video-moodboard)
More style references skills
- Find References: Real references before anything is made: seven sources, four kinds of reference with this week's numbers, ten visual ideas and a board to pick from.
- FrameThrower Film References: Film stills from 5,489 films, searchable by lighting, lens, shot size, color and mood.
- Are.na MCP: Build and read Are.na moodboard channels from your agent.
- Video references by Refs: 4,322 launch films, demos and motion pieces measured shot by shot, searchable free from your agent over MCP.
- GPT Image 2 Style Library: Pick styles and industrial prompt templates for GPT Image 2/2.5 from a 530+ case library (a 35K-star repo).
- Monocolor Editorial Print: Turns a theme, object or photo into an original one-ink or controlled two-ink editorial print: posters, zines, packaging, portraits, halftone on warm paper.