本文へ移動
cccskills
無料GitHub で公開

review-frontend

Use when reviewing, debugging, or improving frontend code in this repo (website/ HTML, CSS, JS, service workers, PWA assets) or when asked to "review frontend", "revisa el html/css", "review JS", or "audita el frontend". Reviews for correctness, browser compatibility, accessibility, performance, security (XSS), responsive behavior, and PWA/service-worker correctness, and ends with a "what a user/reviewer would catch" pass.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md4.4 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Frontend Review (HTML / CSS / JavaScript)

You review frontend code like a user, a screen-reader user, a security reviewer, and a mobile browser all at once. You assume the site will be opened on a slow phone with a screen reader, and that every input is hostile.

Steps

  1. Read all files in scope (HTML, CSS, JS, service worker) as a unit — the bug is usually in the interaction between them.
  2. Check the structure mechanically — for JS, node --check file.js for syntax; look for unbalanced tags, missing closing braces, undefined functions used. Note the repo has no build step: the browser runs these files as-is.
  3. Review the dimensions below.
  4. Scenario pass — think like a user on a phone, on an old browser, with JS disabled, offline, with a screen reader.
  5. Report in the output format at the bottom.

Review dimensions

  1. Correctness — does the JS do what it claims? Right element selected, right event wiring, no null/undefined access, no stale references after DOM changes. Watch for code that only works when scripts load in one order.
  2. Security (XSS and injection) — never insert untrusted text into the DOM via innerHTML/outerHTML/insertAdjacentHTML or document.write. Use textContent for data. Escape URLSearchParams/location.hash values before rendering. Check every place user/URL/query data reaches the DOM.
  3. Accessibility — semantic HTML (<nav>, <main>, headings in order), alt text on images, labels tied to inputs, keyboard navigability, focus states visible, aria used correctly and not overused, contrast meets WCAG AA, no content-only-on-hover. A screen reader must be able to use the site.
  4. Performance — render-blocking scripts, image sizes, no layout thrash (DOM writes between reads), passive listeners for scroll/touch, no unbounded DOM growth, requestAnimationFrame for visual work, caching headers/service-worker strategies sensible for static content.
  5. Responsive/mobile — viewport meta present, no fixed pixel widths that break on small screens, touch targets large enough, media queries testable, horizontal overflow from long content.
  6. Browser compatibility — features used are supported or guarded (IntersectionObserver, optional chaining ?., fetch) with graceful fallbacks; old browsers degrade, not crash.
  7. Service worker / PWA correctness — correct scope, cache versioning (bump or the new version never ships), no stale-cache-after-update bug, offline fallback sane, no aggressive cache-first for HTML that goes stale, sw-precache.js/sw.js strategy matches the asset list.
  8. Robustness — JS fails gracefully if an element or API is missing; no try/catch that swallows real errors; network errors handled (not just .catch(console.error)).

Scenario checklist (the superpower)

  • Screen reader — can a non-sighted user complete the core task?
  • Phone + slow network — what does it look like at 3G with a 2s first-paint?
  • JS disabled — is content readable and links working?
  • Offline — does the service worker serve something useful?
  • Hostile input — paste <img src=x onerror=alert(1)> into every input and URL param: does it render or execute?
  • Old browser — does it crash or degrade?

Output format

  • Verdict — per-dimension pass/fail.
  • Issues prioritized:
    • Critical — XSS, broken core interaction, service worker serving stale content forever, inaccessible core path.
    • Important — performance problems, missing fallbacks, a11y gaps, unhandled errors.
    • Style — consistency, naming, cleanup. Each with file:line, the problem, and the fix as a code snippet.
  • Scenario results — how the site behaves in each scenario above.
  • When asked to fix, apply edits and re-check the touched files (syntax check, re-trace the scenario) before reporting done.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Use when asked to analyze a file, a directory, or the whole codebase to understand structure, architecture, dependencies, complexity, duplication, dead code, or technical debt — e.g. "analyze this", "análisis total", "explain this codebase", "mapa del código", "how does X work", "technical debt". Produces a complete, structured picture with verified commands, not guesses. Distinct from review-* skills (which judge quality); this skill explains and maps.

日本語の概要は準備中です。原文の説明を表示しています。

sazardev/networking-with-go582026年8月8日 更新

Use when asked to audit or harden security in this repo — e.g. "security audit", "auditoría de seguridad", "revisa la seguridad", "is this secure", "hardening", "vulnerabilities". Audits code, config, workflows, and secrets exposure. Covers injection, secrets, TLS, untrusted input, dependency risk, and CI supply-chain hygiene. Runs when the user asks about security, not just for code reviews.

日本語の概要は準備中です。原文の説明を表示しています。

sazardev/networking-with-go582026年8月8日 更新

Use when reviewing the structure, ordering, coherence, and narrative flow of the book as a whole or across chapters. Checks chapter sequencing against the ID scheme, cross-references and forward hooks between chapters, README/index link integrity, exercise-to-chapter pairing, duplicate or contradictory content, and progression of difficulty. Best paired with a full-docs review rather than a single-chapter proofread.

日本語の概要は準備中です。原文の説明を表示しています。

sazardev/networking-with-go582026年8月8日 更新

Use when writing, expanding, rewriting, or drafting any chapter (.mdx) or Go exercise for this book. Encodes the authorial voice, the mdx-pdf-format rules, the ID/naming scheme, the zero-emoji rule, chapter/exercise pairing, and the "theory first, then code" pedagogy so new or edited content reads like the rest of the book and keeps the PDF compiling.

日本語の概要は準備中です。原文の説明を表示しています。

sazardev/networking-with-go582026年8月8日 更新

Use when brainstorming, evaluating ideas, designing architectures, writing technical plans, or choosing between approaches — e.g. "give me ideas", "ideas para", "diseña la arquitectura", "how should I structure this", "compare approaches", "plan". Turns vague ideas into concrete, prioritized, buildable designs with explicit tradeoffs. Use before writing code, not after.

日本語の概要は準備中です。原文の説明を表示しています。

sazardev/networking-with-go582026年8月8日 更新

Use when proofreading, copy-editing, or verifying English in any docs/**/*.mdx chapter or code comment in this repo. Catches grammar, punctuation, spelling, syntax, article/tense/agreement errors, wordiness, tone drift, and style inconsistencies, and rewrites text in the book's confident second-person voice without changing meaning or breaking the mdx/PDF format rules.

日本語の概要は準備中です。原文の説明を表示しています。

sazardev/networking-with-go582026年8月8日 更新

sazardev のスキルをすべて見る

このスキルの問題を報告する