Frontend Review Weekly

Community

mizchi

frontend-review-weekly

Use for the weekly AI review. Orchestrates all frontend-review-* skills in order, dispatches the 5 perspective sub-skills in parallel, diffs against last week's KPIs, and produces a weekly report that feeds the ratchet.

Overview

Publisher	mizchi
Repository	`skills`
Skill name	`frontend-review-weekly`
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 Review Weekly 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-review-weekly .claude/skills/frontend-review-weekly

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

Use it in TypingMind

Enable Frontend Review Weekly 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 Review Weekly 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 Review Weekly 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 Review — Weekly Orchestrator

You are running the weekly AI review. Your job is NOT to make new judgments — it's to:

Re-run every frontend-review-* skill in the correct order.
Dispatch the 5 perspective sub-skills in parallel.
Diff the KPIs against last week's baseline.
File GitHub issues for repeat findings.
Propose static-rule promotions for patterns that appear 3+ weeks in a row.

Procedure

Phase 1: raw data collection

Run, in this order:

frontend-review-triage
frontend-review-ci
frontend-review-hygiene
frontend-review-deps
frontend-review-testing
frontend-review-security

Each of these writes to <client-repo>/.frontend-review/report/latest/.

Phase 1.5: architecture review (run when findings are suspected)

Run these on-demand, or always for the first weekly of a new engagement:

frontend-review-state
frontend-review-performance

These write to <client-repo>/.frontend-review/report/latest/md/.

Phase 2: perspective review (parallel)

Dispatch the 5 perspective skills concurrently using the dispatching-parallel-agents skill. Each reads the raw JSON and produces a perspective-specific markdown report:

frontend-expert
react-expert
performance-expert
security-expert
frontend-ops-expert

Phase 3: KPI diff and ratchet

Compare <client-repo>/.frontend-review/report/latest/raw/*.json against <client-repo>/.frontend-review/kpi/baseline.json. Flag:

Any regression (bad) — these must be fixed before the next weekly
Any improvement (good) — these update the baseline (ratchet tightens)

Phase 4: repeat-finding detection

Compare this week's findings with the previous 2 report/weekly-*.md files. Any finding that appears in all three weeks is a candidate for static rule promotion: propose an eslint/biome custom rule, a codemod, or a CI gate that would make the check automatic. Write these proposals to <client-repo>/eslint-rules/proposals/<rule-name>.md (create the directory if needed) but do NOT implement them — that's a separate engineering task.

Phase 5: report

Write <client-repo>/.frontend-review/report/weekly-$(date +%Y-w%V).md with:

KPI delta table (per category)
Regressions (must fix)
Improvements (ratchet updates)
Perspective summaries (1 paragraph per perspective)
Static rule promotions (pointer to proposals)
Issues filed (gh issue create output)

Trend Monitoring

Alongside KPI diffing, check the following external signals once per weekly cycle to detect ecosystem drift early.

Monitoring sources

Source	Cadence	What to look for
jser.info	Weekly (Sunday publish)	Major releases, RFCs, breaking changes, security advisories affecting the project's dependencies
State of JS (yearly, ~Dec)	Annual	Usage/satisfaction trends; two consecutive years of satisfaction decline is a switch-trigger
State of CSS (yearly)	Annual	CSS adoption trends, Tailwind / CSS-in-JS sentiment
JavaScript Rising Stars (yearly, ~Jan)	Annual	GitHub star growth; early signal for emerging tools
Official release blogs	On release	Track the project's direct dependencies (framework, bundler, test runner, linter, TypeScript) for major releases

For the weekly run, WebFetch https://jser.info/ and scan for any mention of packages listed in package.json. Flag anything relevant under an Ecosystem Signals heading.

Switch triggers

Recommend investigating a tool replacement when any two of these conditions are met:

Satisfaction score has declined for 2 consecutive years in State of JS / State of CSS.
No major release in the past 6 months and GitHub issue accumulation is trending up.
A maintainer departure or deprecation notice was reported.
A clear superior alternative exists: feature parity + significant performance or DX improvement + realistic migration path.

AI / Human Responsibility Split

AI can act on (without human pre-approval):

Auto-fixable lint / typecheck errors
Expanding test coverage for existing patterns
Dependency version bumps (after lint + test pass)

Human must decide:

Test failure triage: is the spec wrong, the implementation wrong, or the test wrong?
New library additions or removals
Architecture boundary changes (new state layer, new routing pattern, new async boundary)
Any change that modifies what the app does, not just how it does it

Flag any AI-generated PRs in the weekly report that appear to cross into the human-decision zone.

Boundaries

Do NOT skip any of the Phase 1 domain skills, even if time is short.
Do NOT modify source code in the client repo.
Do NOT silently update kpi/baseline.json on a regression. Only update on improvement.

Reference

Checklist: 11-ai-review.md, 13-kpi-tracking.md
Phase: week-4-ai-review.md, ongoing.md
Related skills: all frontend-review-* plus frontend-expert, react-expert, performance-expert, security-expert, frontend-ops-expert
External skill: superpowers:dispatching-parallel-agents

Frequently asked questions

What does the Frontend Review Weekly AI skill do?

Why use Frontend Review Weekly on TypingMind?

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

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

Which AI models can use Frontend Review Weekly?

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 Review Weekly?

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

Is the Frontend Review Weekly 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

Tdd

mattpocock

CommunityPopular

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

To Spec

Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.

To Tickets

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.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Frontend Review — Weekly Orchestrator

Procedure

Phase 1: raw data collection

Phase 1.5: architecture review (run when findings are suspected)

Phase 2: perspective review (parallel)

Phase 3: KPI diff and ratchet

Phase 4: repeat-finding detection

Phase 5: report

Trend Monitoring

Monitoring sources

Switch triggers

AI / Human Responsibility Split

Boundaries

Reference

Frequently asked questions

Related AI Skills

Set up your own AI workspace now