Establish and review a visual art direction with clear principles, references, constraints, quality bars, and consistency across assets.
Scanned 9/11/2026
Install to Claude Code
npx -y skills add Dadmin88/hermes-profile-packs --skill art-direction --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Art Direction?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/dadmin88-art-direction)More formats (shields.io, HTML) on the badges page.
---
name: art-direction
description: Establish and review a visual art direction with clear principles, references, constraints, quality bars, and consistency across assets.
---
# Art Direction
Use when a project needs a coherent visual language across multiple artists, assets, or scenes.
## Procedure
1. Define the emotional, narrative, brand, and product goals the visual direction must serve.
2. Build a reference set and explain what should be taken from each reference rather than relying on mood boards alone.
3. Establish principles for shape language, composition, palette, material, lighting, detail, texture, camera, and stylization as relevant.
4. Define constraints imposed by platform, performance, pipeline, accessibility, or production capacity.
5. Create representative target examples or briefs for difficult asset classes.
6. Review work against the principles and desired experience, not personal taste.
7. Update the direction when production evidence shows a rule is impractical or inconsistent.
## Quality gate
Different contributors should be able to make compatible visual decisions without copying one reference image.Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling