agentleFS
PierreAndreisPierreAndreis/pierre-skills/skills/design/SKILL.md

design

Skill1 starsChanged 3 months agoMITView on GitHub

Designs, builds, reviews, and refines distinctive production web interfaces with deliberate composition, rigorous color systems, typography, responsive behavior, accessibility, data presentation, and rendered verification. Use for pages, components, forms, dashboards, reports, landing pages, design systems, visual reviews, or any interface that feels generic, inconsistent, unclear, unfinished, or difficult to use.

197 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use banner-design, ui-styling and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • seikaikyoSkill

    banner-design

    Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage.

    Also in 38 projects that use this

  • MicrosoftSkill

    ui-styling

    Guide for the visual style, structure, and shared building blocks used by Semantic Link Labs interactive UI tools (HTML widgets and anywidget-based widgets). Use this when adding a new interactive UI, modifying an existing one, or adding shared visual components.

    Also in 39 projects that use this

  • seikaikyoSkill

    brand

    Brand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for branded content, tone of voice, marketing assets, brand compliance, style guides.

    Also in 43 projects that use this

  • mayankjain1815-commitsSkill

    infra-audit

    Reads docker-compose, env files, ORM configs, and connection strings to map current infrastructure. Flags missing layers (cache, queue, analytics) based on observed access patterns. Outputs a structured infrastructure manifest.

    Also in 3 projects that use this

  • JetBrainsSkill

    slides

    Create and edit presentation slide decks (`.pptx`) with PptxGenJS and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding charts/diagrams/visuals, or diagnosing layout issues such as overflow, overlaps, and font substitution.

    Also in 42 projects that use this

  • AnthropicSkill

    design-system

    Audit, document, or extend your design system. Use when checking for naming inconsistencies or hardcoded values across components, writing documentation for a component's variants, states, and accessibility notes, or designing a new pattern that fits the existing system.

    Also in 49 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 174 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use sentence-case headings that state the point directly.

    line 13
  2. Distinctive:

    Keep one continuous canvas unless a boundary communicates interaction, selection, warning, contrast, or real grouping.

    line 16
  3. Distinctive:

    Avoid generic centered hero copy followed by a card grid, repeated metric boxes, nested cards, decorative pills, arbitrary icon tiles, …

    line 17
  4. Distinctive:

    Use realistic content and preserve facts, qualifiers, units, formulas, states, privacy, and product behavior.

    line 18
  5. Distinctive:

    Verify the rendered interface.

    line 20
  6. Distinctive:

    Read only the playbooks the task activates, plus REFERENCE.md for shared completion rules.

    line 31

“Common” is measured: kept by at least 6 in 10 of the 174 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Design

Make the interface communicate before it decorates. Preserve the product's established language unless the user requests a new direction.

Non-negotiable defaults

  • Begin with the user's job, strongest supported answer, and information order.
  • Use sentence-case headings that state the point directly. Omit eyebrows, kickers, overlines, decorative section numbers, and all-caps labels above headings.
  • Establish hierarchy with composition, typography, spacing, and density before adding surfaces or color.
  • Give color semantic work. Default to one restrained accent plus reserved status colors; never scatter accents as decoration.
  • Keep one continuous canvas unless a boundary communicates interaction, selection, warning, contrast, or real grouping.
  • Avoid generic centered hero copy followed by a card grid, repeated metric boxes, nested cards, decorative pills, arbitrary icon tiles, gratuitous gradients, glows, glass, blobs, and ornamental shadows.
  • Use realistic content and preserve facts, qualifiers, units, formulas, states, privacy, and product behavior.
  • Build accessible semantics and touch behavior into the first implementation, not a cleanup pass.
  • Verify the rendered interface. Source inspection alone cannot establish visual quality.

Choose the mode

  • Build: establish direction, implement the complete surface, then verify it.
  • Refine: preserve the product model and correct the highest-leverage defects.
  • Review: inspect and report evidence before editing unless fixes were requested.
  • Explore: build three structurally different variants on named axes; cosmetic reskins do not count.

Route to the craft playbook

Read only the playbooks the task activates, plus REFERENCE.md for shared completion rules.

SituationRead
Direction is missing, generic, or structurally undecidedVisual direction and composition
Selecting, repairing, or reviewing a palette or themesColor systems
Type hierarchy, labels, headings, wrapping, or UI copyTypography and copy
Grid, spacing, density, surfaces, radii, or imageryLayout and surfaces
Buttons, forms, dialogs, menus, states, or component APIsComponents and controls
Narrow screens, touch, keyboard, focus, or assistive technologyResponsive and accessibility
Tables, charts, comparisons, metrics, or calculatorsData and evidence
Landing pages, reports, docs, pricing, or narrative pagesMarketing and editorial
Layout shift, asset loading, rendering cost, or motionPerformance and motion
Visual QA, review, screenshots, or handoffVerification and review

Working sequence

  1. Recon: inspect the rendered product, neighboring screens, tokens, primitives, assets, content, states, stack, and responsive behavior.
  2. Frame: state one sentence naming the intended character and the concrete choices that carry it.
  3. Compose: decide reading order and geometry before selecting components.
  4. Systematize: define semantic type, color, spacing, radius, elevation, and state roles; reuse the project's system where it is coherent.
  5. Implement: build the complete primary flow and its loading, empty, error, success, disabled, and destructive states.
  6. Observe: render representative narrow and wide viewports; use keyboard and touch-equivalent input; inspect light and dark themes when present.
  7. Refine: fix the highest-impact systemic defect, render again, and repeat until no known material visual or usability defect remains.

Deliver

State the direction, what changed, what was actually rendered and exercised, and any remaining subjective, browser, device, or content risk. In review mode, cite file:line, explain the user consequence, and propose the smallest coherent correction.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.