neo-industrial-design
elithrar/dotfiles · Agent Skill
Design or restyle web interfaces in a neo-industrial or editorial-brutalist style with engineered typography, grid discipline, and physically composed layouts.
Jump to install ↓Overview
| Publisher | |
|---|---|
| Repository | elithrar/dotfiles ↗ |
| Skill folder | neo-industrial-design |
| Stars | 221 |
| Forks | 16 |
| Bundled files | 4 |
| License | MIT |
| Last updated | October 18, 2026 |
| Links | Skill source ↗ · Repository ↗ |
Mozgi check
What we found in the skill files. Details come with a subscription.
Installation
A skill is a folder with a SKILL.md file. Pick your agent and run the commands in a terminal (macOS, Linux or Git Bash on Windows) from your project root.
Copy the prompt into Claude, Codex or another assistant: it will review the skill and install it for you.
Install the “neo-industrial-design” skill from mozgi.io (https://mozgi.io/skills/elithrar-neo-industrial-design/) for me. 1. Download the archive: https://mozgi.io/skills/elithrar-neo-industrial-design/download If it fails, take the skill folder from the source: https://github.com/elithrar/dotfiles/tree/main/.agents/skills/neo-industrial-design 2. Read SKILL.md and the other files. Check the skill is safe: no hidden commands, no sending data elsewhere, no scripts doing something other than described. If anything looks suspicious, stop and tell me. 3. Put the “neo-industrial-design” folder into your agent's skills folder: .claude/skills/ for Claude Code, .agents/skills/ for Codex, .cursor/skills/ for Cursor, .gemini/skills/ for Gemini CLI. Inside the project if we are in one, otherwise in the home folder (~/.claude/skills/ etc.). 4. Make sure <skills folder>/neo-industrial-design/SKILL.md exists. 5. Briefly tell me what this skill does and offer to try it on my task. If you cannot do a step yourself, tell me what to click or type.
git clone --depth 1 --branch main https://github.com/elithrar/dotfiles.git /tmp/dotfiles mkdir -p .claude/skills cp -r /tmp/dotfiles/.agents/skills/neo-industrial-design .claude/skills/neo-industrial-design
Restart Claude Code — the skill appears in the list; call it manually with /neo-industrial-design. For all projects use ~/.claude/skills.
git clone --depth 1 --branch main https://github.com/elithrar/dotfiles.git /tmp/dotfiles mkdir -p .agents/skills cp -r /tmp/dotfiles/.agents/skills/neo-industrial-design .agents/skills/neo-industrial-design
Codex looks for skills in .agents/skills from the current folder up to the repo root; call one with /skills or $neo-industrial-design. For all projects use ~/.agents/skills.
git clone --depth 1 --branch main https://github.com/elithrar/dotfiles.git /tmp/dotfiles mkdir -p .cursor/skills cp -r /tmp/dotfiles/.agents/skills/neo-industrial-design .cursor/skills/neo-industrial-design
Cursor picks the skill up on start; call it with “/” in Agent chat. Cursor also reads .claude/skills and .agents/skills. For all projects use ~/.cursor/skills.
git clone --depth 1 --branch main https://github.com/elithrar/dotfiles.git /tmp/dotfiles mkdir -p .gemini/skills cp -r /tmp/dotfiles/.agents/skills/neo-industrial-design .gemini/skills/neo-industrial-design
Gemini CLI offers to activate the skill when a task matches — you approve it. For all projects use ~/.gemini/skills.
Read SKILL.md and any companion files before deciding whether to install. Click a file to preview it.
SKILL.md contents
Original author text · read-onlyNeo-Industrial Design
Apply a coherent visual system to web content. The result should feel engineered, editorial, and physically composed: typography carries the hierarchy, a disciplined grid controls tension, imagery behaves as evidence, and technical graphics clarify structure or state.
The user's instructions and existing product requirements take precedence. Treat supplied copy, facts, information architecture, and imagery as content inputs. Do not research, fact-check, or rewrite substantive content unless the user explicitly asks. When required content is missing, use neutral placeholders or leave the region open rather than inventing subject matter.
Set the visual thesis
Infer these choices from the supplied brief and existing interface; make routine design decisions without a separate approval round:
1. Mode: editorial, instrumental, or hybrid. Editorial mode is type-led and poster-like. Instrumental mode is image- or interface-led. Hybrid mode alternates them.
2. Dominant gesture: one primary move, such as an edge-cropped title, a full-bleed image under a grid, a bracketed word, or a giant index.
3. Grid: columns, outer gutter, and recurring alignment axes. Deliberate violations should remain accountable to those axes.
4. Signal: one accent color with a consistent visual role such as action, selection, position, or emphasis.
Read references/visual-system.md ↗ before designing or restyling the interface. Use it as a system of relationships, not as a checklist of effects.
Build from macro to micro
1. Establish section proportions, dominant fields, reading order, and the type/image silhouette.
2. Lock the display, body, and annotation type roles and their scale contrast.
3. Apply the grid to content edges, rules, images, navigation, and repeated modules.
4. Introduce only the graphic motifs that reinforce an alignment, boundary, state, measurement, or interaction.
5. Compose both mobile and desktop around the primary task. In an instrumental interface, keep the map, data, or working surface dominant; oversized titles and decoration must not displace it.
Preserve semantic HTML, source-order clarity, keyboard access, visible focus, alt text, useful contrast, and readable body sizes. Technical styling does not justify inaccessible text or controls.
Make responsiveness compositional
- Recompose wide grids into fewer columns instead of shrinking the desktop canvas uniformly.
- Set intentional mobile headline breaks and preserve the primary reading path.
- Move secondary rails after main content; remove only redundant decoration.
- Prevent interactive content from clipping or causing horizontal scrolling.
- Retain deliberate display-type cropping only when the title remains understandable and fully available to assistive technology.
Review the rendered result
For implemented changes, use references/review.md ↗ to inspect the affected page at wide desktop and narrow phone widths. Fix failures in hierarchy, alignment, legibility, responsiveness, or interaction within the requested implementation. For review-only requests, report findings without changing or publishing the interface. Do not add motifs to compensate for a weak composition.
Output
Deliver a usable, responsive web interface with one legible visual thesis and a consistent design system. In the handoff, state the chosen mode and the most important visual correction made during rendered review.
Frequently asked questions
What does the neo-industrial-design skill do?
Design or restyle web interfaces in a neo-industrial or editorial-brutalist style with engineered typography, grid discipline, and physically composed layouts.
How do I install neo-industrial-design?
Open the “Installation” block on this page and pick your agent — Claude Code, Codex, Cursor or Gemini CLI — for ready-made commands that copy the skill folder to the right place. Or copy the prompt from the “Via assistant” tab and let the assistant review and install the skill.
Which AI models work with neo-industrial-design?
Skills are plain Markdown instructions (the Agent Skills format), so neo-industrial-design works with any agent that reads SKILL.md: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and more. The model loads the instructions only when a task matches the skill's description.
Is neo-industrial-design free?
The skill is published openly by elithrar under the MIT license. The skill itself costs nothing — you only pay your AI provider for the tokens you use.
Is it safe to install skills?
A skill is a set of instructions your agent will follow, so read SKILL.md and its companion files before installing. Scripts in the skill folder only run if your agent runs them — keep an eye on what it does and do not grant unnecessary permissions.
How is a skill different from an MCP server or a plugin?
An MCP server or plugin gives the model new tools — code that runs and returns a result. A skill gives it knowledge and process: how to approach a task, which steps to follow and what good output looks like. It needs no server or API key.