agentleFS
therapystherapys/dotagents/skills/frontend/SKILL.md

frontend

Skill8 starsChanged 2 months agoMITView on GitHub

Build and polish production-ready frontend interfaces using Emil Kowalski's design-engineering approach. Use when creating or restyling web pages, components, or apps; reviewing UI polish; adding or fixing animations and transitions; choosing UI primitives; improving mobile touch behavior; or stress-testing layouts with real-world data. Covers HTML/CSS/JS, React, Vue, and other web frameworks.

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 44 edited versions we read keep these.

  • 3

    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:

    Verify with available checks and browser tooling.

    line 36
  2. Distinctive:

    Use pointer-down for immediate visual feedback, not for committing actions.

    line 40
  3. Distinctive:

    Prefer transform/opacity for motion, but do not assume every CSS/WAAPI animation or clip-path is compositor-accelerated.

    line 42

“Common” is measured: kept by at least 6 in 10 of the 44 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 Engineering

Build interfaces that feel right: purposeful motion, responsive controls, good defaults, and invisible correctness. This replaces the previous aesthetic-first frontend guidance with Emil Kowalski's approach. The code is the deliverable, not a mood board.

Load the right guidance

Paths are relative to this skill's directory, not the project's working directory.

  1. Always read Design Engineering before building, polishing, or reviewing UI. It defines the philosophy, motion decisions, component details, and Before/After/Why review table.
  2. Load additional guides when relevant:
TaskRead
Build an animation, transition, or gestureAnimate; its RECIPES.md for matching components
Choose accessible primitives or a frontend dependencyPick UI Library
Mobile layouts, touch, safe areas, viewport, keyboard, PWAMobile Native
Stress-test realistic edge casesBreak UI and its CATALOG.md
Animation performance triagePerformance Cheatsheet

These are bundled reference guides, not independently installed slash commands. References to emil-design-eng, animate, mobile-native, pick-ui-library, or break-ui mean the local guides above. Other upstream skills mentioned in those guides are not bundled: do not claim to invoke them. For a motion review or audit, use the Design Engineering checklist and Animate's rules; for other missing workflows, say what's unavailable if it matters.

The upstream "Initial Response" blocks and invocation metadata are for standalone skills. Here, follow the user's concrete request immediately; do not insert a canned introduction or wait for another question. The library guide may be read as a reference without a separate explicit invocation.

Workflow

  1. Inspect the existing UI, framework, dependencies, tokens, and project conventions. Identify audience, task, content, states, and constraints. Ask one focused question at a time only where a missing decision materially changes the implementation.
  2. Preserve established visual identity and use existing tokens. Do not replace fonts, palettes, layout, or dependencies merely to look different. If a project has additional local design-system guidance, read it and treat its brand-specific layout, typography, surface, and motion rules as authoritative.
  3. Choose accessible primitives before hand-rolling dialogs, menus, toasts, or focus management. Reuse installed equivalents; do not churn libraries without a request. Apply React-specific recommendations only in React projects.
  4. Gate every animation by frequency and purpose before choosing tool, properties, easing, duration, interruption, and exit. No motion is a valid result. Use the cheapest tool that fits; ship reduced-motion behavior and touch-safe hover gating with it.
  5. Implement working, semantic, responsive code. Cover loading, empty, error, disabled, and populated states as applicable. Preserve labels, contrast, visible keyboard focus, focus restoration, and keyboard operation.
  6. Verify with available checks and browser tooling. Check narrow and wide layouts, supported themes, realistic content, rapid interruption, keyboard input, and reduced motion. Mobile emulation is not hardware verification. Say plainly which checks you could not run.

Application guardrails

  • Use pointer-down for immediate visual feedback, not for committing actions. Keep semantic button/link activation so keyboard users work and pointer users can cancel a press.
  • Reduced motion must actually disable existing movement and transform transitions, not merely add a fade beside them. Preserve essential state changes and feedback.
  • Prefer transform/opacity for motion, but do not assume every CSS/WAAPI animation or clip-path is compositor-accelerated. Verify in the target browser; treat blur and layout animation as measured exceptions, not defaults.
  • Stress-test with plausible or schema-backed values. A dev-only fixture toggle must never ship to production. In a requested audit, report design tradeoffs before fixing; in a requested implementation, address unambiguous bugs within scope.

Output

Ship code in the project's files and summarize changes, checks, and any unverified behavior briefly. For UI reviews, use an actual Before / After / Why markdown table. For a dedicated worst-case audit, use Break UI's findings format. Do not claim visual or device verification you did not perform.

Source and adaptation notes: UPSTREAM.md.

Download now (ZIP)

  • Other versions50 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 50

    1. langwatch/langwatch★ 5ksame name
    2. atopile/atopile★ 4ksame name
    3. leookun/cursor-byok★ 3.2ksame name
    4. theopenco/llmgateway★ 1.7ksame name
    5. notque/vexjoy-agent★ 444same name
    6. notque/claude-code-toolkit★ 442same name
    7. AlexPEClub/ai-coding-starter-kit★ 382same name
    8. OyadotAI/oya-browser★ 351same name
    9. speakeasy-api/gram★ 275same name
    10. ThePrimeagen/skills★ 234same name

    40 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use programming, backend 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.
    • DevNewbie1826Skill

      programming

      MUST USE for work on Python, Rust, TypeScript, or Go source files and project manifests. Triggers: write or edit code; new project; Go HTTP service (gin lane); Bubble Tea TUI; CJK IME; Connect-Go RPC; sqlc or pgx; branded IDs; exhaustive matching; unsafe Rust; Miri; oversized file; refactoring; logging, log levels, structured logging, or observability; arena, allocator, bumpalo, const fn, const generics, compile-time programming, zero-allocation APIs, bitfields, repr, scope guards, errdefer-style cleanup, Zig-like patterns, zero-copy parsing, packed data, or FFI; Rust public API design or macros.

      Also in 3 projects that use this

    • wewpellex21Skill

      backend

      Servers, routes, APIs, and backend architecture. Activated when Claude creates server-side code, API routes, or Express/Fastify/Next.js API handlers.

      Also in 7 projects that use this

    • launch52-aiSkill

      data

      Generate data layer code (Freezed DTOs, repository implementations, data sources) from feature specifications or API references. Creates the bridge between domain entities and external data sources. Use after /domain to implement the data layer.

      Also in 4 projects that use this

    • AnthropicSkill

      architecture

      Create or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and consequences, reviewing a system design proposal, or designing a new component from requirements and constraints.

      Also in 7 projects that use this

    • 0xSeroSkill

      security

      Also in 7 projects that use this

    • BlockSkill

      debugging

      Debugging guidelines and best practices

      Also in 5 projects that use this

  • In this repository20 other files it gives its agents.

Does it work?

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

Reviews can't be read right now.

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.