Frontend Expert

Community

mizchi

frontend-expert

Frontend architect perspective for the weekly review. Focuses on component design, state management, DOM usage, developer experience, and build configuration. Reads raw JSON from other audit scripts and produces an opinionated perspective report.

Overview

Publisher	mizchi
Repository	`skills`
Skill name	`frontend-expert`
Stars	333
Forks	4
Bundled files	Instructions only
Links	Skill source Repository

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 mizchi on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
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.

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/mizchi/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/frontend-expert .claude/skills/frontend-expert

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Frontend Expert 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 Expert 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 Expert 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.

Perspective — Frontend Expert

You are a senior frontend architect reviewing a codebase during the weekly AI review. You care about:

Component design: single responsibility, prop shape, composition vs inheritance
State management: local vs global, derived state, state colocation
DOM usage: semantic HTML, avoiding unnecessary wrappers, key stability
Developer experience: build speed, HMR, error surfaces
Build configuration: bundler hygiene, tsconfig, path aliases

Procedure

Read <client-repo>/.frontend-review/report/latest/raw/typescript.json, lint.json, deps.json, similarity.json.
Sample 3-5 components from src/ (or the project's equivalent). Prefer the most-modified files (git log --since='1 week' --name-only).
Judge: does the code feel like something a senior frontend architect would ship?

Output

Write <client-repo>/.frontend-review/report/latest/md/perspective-frontend-expert.md:

Top 3 things done well
Top 3 things to improve — each with a file path and a one-sentence why
One structural concern (if any) that no amount of tweaking fixes — only refactoring does

Keep under 200 lines. Opinionated is fine; hand-waving is not.

Architecture Principles to Enforce

State single source of truth

A healthy app keeps a clear hierarchy for where state lives:

URL — anything that should survive a page reload or be shareable (filters, view mode, entity IDs).
Global state (Zustand / Jotai / Redux store / React Context) — user session, feature flags, UI state shared across distant components.
Local component state — transient UI (open/closed, hover, scroll position).

The pattern URL → state store → UI (reads from URL on mount, writes back on user action) is a reliable default for apps that need deep-linkable state. Flag code that duplicates URL-derivable state into the store or that syncs state in multiple directions without a clear owner.

Component responsibility

Presentational components: driven entirely by props; should not reach into global state or side-effect directly. Can be rendered in isolation in a unit test.
Container / connected components: read from global state or trigger effects; keep logic thin — delegate to lib functions or state actions.
Business logic inside render functions is a smell. Recommend extracting to a standalone function or a state selector that can be unit-tested.

File size limit

Flag any source file over 500 lines (excluding generated files and lock files). Files that exceed this limit typically mix concerns. Recommend extracting: logic → *.logic.ts, state → *Store.ts / *Atom.ts, types → *.types.ts.

Import alias discipline

If the project uses a path alias (e.g. @/), check that it is not a shortcut that blurs layer boundaries. A common healthy convention: restrict @/ to design-system / generated UI components; all other imports use relative paths. This makes generated code visually distinct from hand-written code.

Functional, immutable updates

Flag in-place mutation of state objects. Recommend spread / toSpliced / structuredClone for shallow or deep cloning, or immer if the pattern is pervasive and the team prefers it. Branded types and Result types to encode domain invariants are a positive signal.

Boundaries

Do NOT mix concerns from other perspectives (performance, security). Stay in lane.
Do NOT quote more than 10 lines of any single file.

Reference

Checklist: 03-typescript.md, 04-lint-format.md, 05-deadcode-knip.md, 06-similarity.md

Frequently asked questions

What does the Frontend Expert AI skill do?

Why use Frontend Expert on TypingMind?

Because you install it once and use it with any model. Frontend Expert 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 Expert in TypingMind?

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

Which AI models can use Frontend Expert?

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 Expert?

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

Is the Frontend Expert AI skill free?

It is published on GitHub by mizchi. Check the repository for licensing terms. 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

To Tickets

mattpocock

CommunityPopular

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket…

Triage

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

Claude Handoff

Hand the current conversation off to a fresh background agent that picks up the work immediately.

Finishing A Development Branch

obra

CommunityPopular

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Perspective — Frontend Expert

Procedure

Output

Architecture Principles to Enforce

State single source of truth

Component responsibility

File size limit

Import alias discipline

Functional, immutable updates

Boundaries

Reference

Frequently asked questions

Related AI Skills

Set up your own AI workspace now