Frontend change quality review

Skill SHIHAOZOU/ai-frontend-engineering-skills/skills/frontend-change-quality-review

Production-ready frontend Agent Skills for Codex, Claude Code & Cursor—covering React development, debugging, refactoring, code review, bilingual docs, and npx skills installation. 面向 Codex、Claude Code 与 Cursor 的生产级前端 Agent Skills，覆盖 React 开发、Bug 修复、重构、Code Review 与双语工程规范，支持 npx skills 安装。

Install

npx -y skills add SHIHAOZOU/ai-frontend-engineering-skills --skill frontend-change-quality-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

17 days oldThe repository was created 17 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Review frontend changes for correctness, types, architecture, accessibility, performance, security, naming, tests, and maintainability. Use for pull requests, diffs, patches, or pre-merge quality audits.

SKILL.md

2.8 KB, as published. Nobody here has run it

Frontend Code Review Skill

For the Simplified Chinese reference, read references/zh-CN.md when the user communicates primarily in Chinese or requests Chinese output.

Purpose

Find actionable defects and risks in changed code while separating blocking issues from optional improvements.

When to Use

Use for pull request review, local diff review, release readiness, or acceptance-criteria verification.

Inputs

Diff or changed files
Requirement and acceptance criteria
Repository rules and validation output
Runtime evidence when available

Outputs

Findings ordered by severity
File and line references
Evidence, impact, and focused remediation
Validation gaps and residual risk

Workflow

Read the requirement and repository instructions.
Inspect the full diff and affected call paths.
Verify behavior against acceptance criteria.
Check types, architecture, state, errors, accessibility, performance, security, naming, and tests.
Reproduce high-risk findings where practical.
Report only actionable findings with evidence.
Summarize validation gaps after findings.

Decision Tree

flowchart TD
  A[Potential issue] --> B{Caused by this change?}
  B -->|No| C[Do not report as a finding]
  B -->|Yes| D{Observable impact or concrete risk?}
  D -->|No| E[Optional note only]
  D -->|Yes| F{Blocks correctness, safety, or release?}
  F -->|Yes| G[High severity]
  F -->|No| H[Medium or low severity]

Checklist

Findings are caused by the reviewed change.
Severity matches impact and likelihood.
Each finding includes a precise location.
Suggested remediation is smaller than a rewrite.
Missing tests are tied to concrete risk.
Summary does not hide important findings.

Constraints

MUST lead with findings, ordered by severity.
MUST NOT report style preference as a defect when conventions are met.
MUST NOT claim a bug without a plausible failing scenario.
SHOULD distinguish verified facts from uncertainty.

Examples

Finding: “High — src/cart/save.ts:42 retries a non-idempotent purchase request after timeout, which can create duplicate orders. Add an idempotency key or disable automatic retry.”

Anti-patterns

Summarizing the diff without reviewing it
Producing many low-value style comments
Missing security or accessibility regressions
Giving vague feedback without location or impact