Frontend Architecture logo

Frontend Architecture

OrganizationPopular
exceptionless
frontend-architecture

Apply Exceptionless Svelte conventions when adding or restructuring frontend features.

Overview

Publisherexceptionless
RepositoryExceptionless
Skill namefrontend-architecture
Stars
2.5K
Forks
508
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by exceptionless on GitHub. Read the source before you install it.

Installation

Install the Frontend Architecture AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/exceptionless/Exceptionless/tree/main/.agents/skills/frontend-architecture
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/exceptionless/Exceptionless.git /tmp/Exceptionless
mkdir -p .claude/skills
cp -r /tmp/Exceptionless/.agents/skills/frontend-architecture .claude/skills/frontend-architecture
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Frontend Architecture in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Frontend Architecture on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Frontend Architecture is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Frontend Architecture

Work in src/Exceptionless.Web/ClientApp, the sole application frontend at /, and follow its AGENTS.md. Generate root routes with $app/paths; preserve primary historical hash links through the incoming-link compatibility layer.

Feature structure

Keep feature behavior in src/lib/features/<feature>/: API operations in api.svelte.ts, local types in models.ts, validation in schemas.ts or validators.ts, and UI in components/. Reuse generated API types through feature aliases. Match the nearest current feature instead of copying a static scaffold.

Local UI conventions

  • Reuse $comp, $shared, and $lib helpers. In particular, use createQueryParameters for route query binding.
  • Use shared formatter components in src/lib/features/shared/components/formatters/ for dates, relative time, duration, bytes, numbers, currency, percentages, booleans, and date math.
  • Match the existing dense, restrained operational UI and its theme tokens.
  • Use href for ordinary navigation; use action handlers when work must finish before navigating.
  • Prefer derived state for computed values; reserve effects for side effects. Use current Svelte event attributes and snippets.
  • Preserve accessible labels, focus behavior, dialog titles, and field-error associations.

Svelte and TypeScript details

  • Use options.ts for shared option sets within a feature. Use $features for feature imports and $generated for generated contracts; extend generated types in feature-owned files.
  • Prefer named imports; use namespace imports for composite components such as Dialog, DropdownMenu, Field, and Card.
  • Keep files and directories kebab-case. Follow the app's ESLint rules for braces and statement formatting.
  • Avoid any; use generated types, explicit interfaces, unknown, and type guards. Spell out identifiers such as organization and filter.
  • Await asynchronous work and handle failures at the appropriate local boundary. Do not let rejected promises bypass error UI or mark an operation complete before its required work finishes.
  • Use $derived for computed values and $effect for side effects. Use untrack() selectively when an incidental read should not become an effect dependency; do not hide dependencies needed for correctness.
  • Use Svelte event attributes (onclick, oninput) and snippets. Use array class syntax or cn() for conditional classes.

Accessibility and interaction

  • Preserve native semantic elements, landmarks, and a clear heading hierarchy. Shared UI components complement document semantics rather than replacing them with styled divs.
  • Associate each control with a label. Give icon-only buttons an accessible name and hide decorative icons from assistive technology.
  • Give dialogs a title, even when visually hidden. Preserve keyboard navigation and visible focus states.
  • Set aria-invalid on invalid controls and connect help/error messages with aria-describedby.
  • For motion work, consult the frontend's installed emil-design-eng skill. Apply its interaction principles through existing Svelte components, preserving reduced-motion behavior and the operational UI's restraint.

Verification

Use colocated Vitest/Testing Library tests and local Playwright flows as appropriate. Prefer role and label queries. Follow the app's validation command policy; inspect the rendered flow when UI behavior changes.

Frequently asked questions

What does the Frontend Architecture AI skill do?

Apply Exceptionless Svelte conventions when adding or restructuring frontend features.

Why use Frontend Architecture on TypingMind?

Because you install it once and use it with any model. Frontend Architecture is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Frontend Architecture in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/exceptionless/Exceptionless/tree/main/.agents/skills/frontend-architecture. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Frontend Architecture?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Frontend Architecture?

As many as you like. As long as a model supports skills, you can use Frontend Architecture with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Frontend Architecture AI skill free?

Yes. It is published on GitHub by exceptionless under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇