Frontend Review Ci

Q: Why use Frontend Review Ci on TypingMind?

Because you install it once and use it with any model. Frontend Review Ci 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.

Q: How do I install Frontend Review Ci in TypingMind?

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

Q: Which AI models can use Frontend Review Ci?

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.

Q: How many AI models can I use with Frontend Review Ci?

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

Q: Is the Frontend Review Ci 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.

Q: 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.

Q: 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.

Community

mizchi

frontend-review-ci

Use when CI is slow (>10 min), flaky, or the user asks to optimize GitHub Actions for a frontend project. Analyzes `gh run list` history, identifies bottleneck steps, proposes sharding / cache / concurrency improvements. Runs `scripts/audit-ci.sh`.

Overview

Publisher	mizchi
Repository	`skills`
Skill name	`frontend-review-ci`
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 Ci 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-ci .claude/skills/frontend-review-ci

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

Use it in TypingMind

Enable Frontend Review Ci 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 Ci 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 Ci 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 — CI Optimization

You are optimizing GitHub Actions CI for a frontend project. The target is median ≤ 10 minutes, max ≤ 15 minutes. Faster CI means developers trust it; trust is what makes the ratchet work.

Procedure

Run scripts/audit-ci.sh --repo <client-repo>.
Read <client-repo>/.frontend-review/report/latest/raw/ci.json.

For the slowest runs, dig into step-level timing:

bash
gh run view <run-id> --log | grep -E '^\d{4}-' | head -200

Inventory current workflows under .github/workflows/ and note:
- Does every job (lint, build, test, coverage, etc.) use a pnpm/npm store cache? A common miss: test.yml has cache but lint.yml and pages.yml do not.
- Does actions/setup-node use cache: pnpm, or is there a manual actions/cache block for the pnpm store? Either is fine; the key must include hashFiles('**/pnpm-lock.yaml').
- Does actions/cache cache the Playwright browser store (~/.cache/ms-playwright)?
- Is there a concurrency: block?
- Are vitest / playwright sharded?
- Are jobs serialized via needs: unnecessarily?
- Are lint and typecheck in the same serial job? They have no dependency on each other and should be separate parallel jobs.

Output

Write <client-repo>/.frontend-review/report/latest/md/ci-analysis.md with:

Current median / max duration
Slowest 3 steps in a representative failing + passing run
Concrete recommendations, each mapped to a line in a YAML patch (not full rewrite)
Estimated wins per recommendation

Then produce a draft PR description that the user can copy into gh pr create, naming the branch ci/optimize.

Development Iteration Timing Targets

Use these as reference thresholds when diagnosing CI slowness. Any stage exceeding 2× its target warrants a dedicated bottleneck issue.

Stage	Target	How to measure
HMR (edit → screen)	< 500 ms	Vite `--debug` output
Unit test — single file	< 1 s	vitest / jest output
`test:ci` — full suite	< 1 min	CI step duration
`typecheck`	< 30 s	CI step duration
`lint`	< 30 s	CI step duration
E2E — one shard	< 50 s	CI step duration
PR CI total (parallel)	< 5 min	GitHub Actions wall-clock
`install` (cache hit)	< 15 s	CI step duration
`build`	< 30 s	CI step duration

The PR CI total target is the critical gate. CI slower than 5 minutes is routinely bypassed by developers.

Bottleneck Identification Procedure

Pull step-level timing from the slowest recent run:

bash
gh run view <run-id> --log | grep -E '^\d{4}-' | head -200

Identify the single slowest job in the DAG — only the longest path in a parallel graph determines wall-clock time.
Within that job, identify the slowest step.
Propose one change per PR — bundling multiple optimisations makes regression attribution impossible.
Measure wall-clock before/after on the same branch to verify the win.

Typical Optimisation Patterns

Area	Common fix
`install`	pnpm / npm store cache key, `--frozen-lockfile`, narrow `onlyBuiltDependencies`. Audit every workflow file — partial cache (only some jobs cached) is the most common oversight; `install` without cache is ~20-25 s, with cache hit it drops to ~2-3 s
`lint + typecheck`	Split into two parallel jobs (no mutual dependency). On a project with ~170 TS files, this alone cuts the lint-job wall-clock in half
`typecheck`	Project References split, `skipLibCheck: true`, resolve circular type imports
`lint`	lint-staged for PR (changed files only), enable linter's own incremental cache
`vitest`	`isolate: false`, tune `--pool` thread count, exclude test fixtures from coverage
Playwright	Tune shard count to test volume, `page.route()` to mock external APIs, move flaky tests to daily-only tag
Runner size	Larger runner (4-core+) only as a last resort after exhausting the above

Boundaries

Do NOT actually create the PR or push the branch — just draft the description.
Do NOT modify workflow YAML in the client repo; the user does that after reviewing your proposal.

Reference

Checklist: checklist/09-ci-optimization.md
Phase: phase/week-1-ci-baseline.md
Templates: templates/github-actions/ci.yml, templates/github-actions/e2e.yml

Frequently asked questions

What does the Frontend Review Ci AI skill do?

Why use Frontend Review Ci on TypingMind?

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

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

Which AI models can use Frontend Review Ci?

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 Ci?

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

Is the Frontend Review Ci 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

Qa Only

garrytan

CommunityPopular

Report-only QA testing. (gstack)

Setup Browser Cookies

garrytan

CommunityPopular

Import cookies from your real Chromium browser into the headless browse session. (gstack)

Investigate First

Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.

Surgical Patch

Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Frontend Review — CI Optimization

Procedure

Output

Development Iteration Timing Targets

Bottleneck Identification Procedure

Typical Optimisation Patterns

Boundaries

Reference

Frequently asked questions

Related AI Skills

Set up your own AI workspace now