agentleFS
cabernectcabernect/caberos/skills/frontend-design/SKILL.md

frontend-design

Skill2 starsChanged 13 days agoMITView on GitHub

Distinctive visual design for web UI — use when the user wants a new page, app screen, or component designed, or an existing one visually reworked.

187 other projects use a version of this, 28 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use instantly-campaign, albert-dm 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.
  • yawningwhaleAISkill

    instantly-campaign

    Create a new Instantly cold-email campaign in the proven 5-email structure of the user's top-performing campaign (~16% reply rate). Use when the user wants to launch a new outbound campaign, write a cold email sequence, create an Instantly campaign, draft outreach for a new service or niche, or set up a sales sequence.

    Also in 6 projects that use this

  • yawningwhaleAISkill

    albert-dm

    Reply to DMs and messages the way Albert would. Use when the user asks "how would Albert reply to this", pastes a conversation and wants an Albert-style response, or asks you to draft/write a DM in Albert's voice. Albert sells AI voice agents / automations to local service businesses (Go High Level, lead follow-up, bookings).

    Also in 5 projects that use this

  • naman10parikhSkill

    ecosystem-reference

    Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.

    Also in 5 projects that use this

  • naman10parikhSkill

    fractal-delegation

    Also in 5 projects that use this

  • julianoczkowskiSkill

    brief-to-tasks

    Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan implementation order, or mentions "tasks" or "breakdown".

    Also in 7 projects that use this

  • SeifBenayedSkill

    file-reading

    Use this skill when a file has been uploaded but its content is NOT in your context — only its path at /mnt/user-data/uploads/ is listed in an uploaded_files block. This skill is a router: it tells you which tool to use for each file type (pdf, docx, xlsx, csv, json, images, archives, ebooks) so you read the right amount the right way instead of blindly running cat on a binary. Triggers: any mention of /mnt/user-data/uploads/, an uploaded_files section, a file_path tag, or a user asking about an uploaded file you have not yet read. Do NOT use this skill if the file content is already visible in your context inside a documents block — you already have it.

    Also in 6 projects that use this

  • +6 more from naman10parikh

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 181 edited versions we read keep these.

  • 5

    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:

    Treat copy as design material — see "Writing in design" below.

    line 29
  2. Distinctive:

    Write from the user's side of the screen: name things by what people control and recognize — a person manages notifications, not webhook …

    line 55
  3. Distinctive:

    Use active voice. A control says exactly what happens: "Save changes," not "Submit." An action keeps its name through the whole flow — the …

    line 57
  4. Distinctive:

    Treat failure and emptiness as direction: explain what went wrong and how to fix it, in the interface's voice, precisely.

    line 59
  5. Distinctive:

    Keep the register conversational: plain verbs, sentence case, tone matched to the brand and audience.

    line 61

“Common” is measured: kept by at least 6 in 10 of the 181 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

Frontend Design

Approach this as the design lead at a small studio known for giving every client a visual identity that could not be mistaken for anyone else's. This client has already rejected proposals that felt templated, and is paying for a distinctive point of view: make deliberate, opinionated choices about palette, typography, and layout that are specific to this brief, and take one real aesthetic risk you can justify.

Ground it in the subject

If the brief does not pin down what the product or subject is, pin it yourself before designing: name one concrete subject, its audience, and the page's single job, and state your choice. Use what MEMORY.md and the conversation say about the user's preferences, what they're building, and designs made before as hints. The subject's own world — its materials, instruments, artifacts, and vernacular — is where distinctive choices come from. Build with the brief's real content and subject matter throughout.

Design principles

For web designs, the hero is a thesis. Open with the most characteristic thing in the subject's world, in whatever form makes sense for it: a headline, an image, an animation, a live demo, an interactive moment. A big number with a small label, supporting stats, and a gradient accent is the template answer; choose it only when it is truly the best option.

Typography carries the personality of the page. Pair the display and body faces deliberately, choosing families specific to this project, and set a clear type scale with intentional weights, widths, and spacing. Make the type treatment itself a memorable part of the design.

Structure is information. Structural devices — numbering, eyebrows, dividers, labels — should encode something true about the content. Numbered markers (01 / 02 / 03) belong only where the content is a real sequence whose order the reader needs.

Leverage motion deliberately: a page-load sequence, a scroll-triggered reveal, hover micro-interactions, ambient atmosphere. One orchestrated moment usually lands harder than scattered effects, and restraint often reads as more crafted than abundance.

Match complexity to the vision. Maximalist directions need elaborate execution; minimal directions need precision in spacing, type, and detail. Elegance is executing the chosen vision well.

Treat copy as design material — see "Writing in design" below.

Process — two passes, gated

The design process has hard ordering: the written plan exists before any code does, and the critique happens between them. Both are checkable — a page produced without them failed the process even if it looks good.

For calibration: AI-generated design currently clusters around three looks: (1) a warm cream background (near #F4F1EA) with a high-contrast serif display and a terracotta accent; (2) a near-black background with a single bright acid-green or vermilion accent; (3) a broadsheet layout with hairline rules, zero border-radius, and dense newspaper-like columns. All three are legitimate for some briefs, but they are defaults rather than choices. Where the brief pins down a visual direction, follow it exactly — the brief's words always win, including when it asks for one of these looks. Where it leaves an axis free, spend that freedom on a choice made for this brief.

Step 1 — Write the plan. Before any HTML/CSS exists, write a compact design plan into design-plan.md in the workspace (or into your reply if the task is conversational): Color — 4–6 named hex values. Type — faces for 2+ roles (a characterful display face used with restraint, a complementary body face, a utility face for captions or data if needed). Layout — a one-sentence concept plus an ASCII wireframe. Signature — the single element this page will be remembered by.

Step 2 — Critique the plan. Read it back against the brief and list, in the file or reply, which parts are the default you would produce for any similar page — then revise those parts and say what changed and why. The brief's own direction always wins over this check.

Step 3 — Build. Derive every color and type decision from the revised plan. Watch CSS specificity: type-based selectors (.section) and element-based ones (.cta) easily cancel each other's paddings and margins.

Done when design-plan.md (or the plan in the conversation) exists with all four parts, the critique pass names what was revised, and the built page follows the plan.

Restraint and self-critique

Spend your boldness in one place. Let the signature element be the one memorable thing, keep everything around it quiet and disciplined, and cut decoration that does not serve the brief. Build to a quality floor without announcing it: responsive down to mobile, visible keyboard focus, reduced motion respected.

Critique the rendered result, not the code: when the page is served (a local dev server or a preview URL), open it with browser_open and capture it with browser_observe (visual: true), then fix what the screenshot shows. Before calling it done, take one element away — Chanel's mirror test.

Writing in design

Words appear in a design to make it easier to understand and use. Before writing anything, ask what the design needs to say and how it can best help the person navigate.

Write from the user's side of the screen: name things by what people control and recognize — a person manages notifications, not webhook config. Describe what something does in plain terms; specific beats clever.

Use active voice. A control says exactly what happens: "Save changes," not "Submit." An action keeps its name through the whole flow — the "Publish" button produces a "Published" toast.

Treat failure and emptiness as direction: explain what went wrong and how to fix it, in the interface's voice, precisely. An empty screen is an invitation to act.

Keep the register conversational: plain verbs, sentence case, tone matched to the brand and audience. Each element does exactly one job — a label labels, an example demonstrates.

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.