메뉴
Run Lighthouse audits on a website, analyze the results across all four categories (Performance, Accessibility, Best Practices, SEO), prioritize fixes by impact, implement them, and verify the scores improved. Use when asked to improve Lighthouse scores, optimize web performance, fix Core Web Vitals, or audit a site.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Harden a self-hosted Linux server. Detects current state, runs a full interview to understand what the user wants, warns about edge cases (no SSH keys, password-only auth, provider firewalls), then implements only the selected steps in a safe order.
Systematic edge case discovery, test coverage, and hardening for any feature or codebase area. Spawns parallel subagents to enumerate edge cases across eight categories, writes tests for each, runs them, and fixes unhandled cases. Use after implementation to ensure robustness before shipping.
Add a time-boxed free trial to any app with a payment integration. Handles trial start, expiry tracking, gating, expiry emails, and the upgrade prompt flow. Use when adding a trial period to an existing subscription or paywall.
Convert any YouTube video into a reusable Claude Code skill. Paste a YouTube URL and this skill fetches the transcript, extracts the actionable content, and writes a ready-to-use .claude/skills/<name>.md file. Best for tutorial videos, how-to guides, workflow demos, or instructional content.
Make a site agent-ready using Cloudflare AI Search and the isitagentready.com checklist. Audits the current site, then implements: Cloudflare AI Search (hybrid vector + keyword), markdown content negotiation (acceptmarkdown.com), robots.txt AI rules, sitemap, MCP Server Card, and Agent Skills discovery. Use when asked to add search, make a site agent-ready, or optimize for AI agents.
Scaffolds a Better T Stack project via a structured interview. Uses AskUserQuestion to let the user pick frontend, backend, runtime, database, ORM, API layer, auth, payments, addons, example templates, and where to create the project. Assembles and runs the exact create-better-t-stack CLI command with no manual prompts.
| name | lighthouse |
| description | Run Lighthouse audits on a website, analyze the results across all four categories (Performance, Accessibility, Best Practices, SEO), prioritize fixes by impact, implement them, and verify the scores improved. Use when asked to improve Lighthouse scores, optimize web performance, fix Core Web Vitals, or audit a site. |
| argument-hint | <URL or local dev server address> |
You are auditing and optimizing a website for Lighthouse scores. Work through each phase in order. Do not skip phases.
Target: {{args}}
If {{args}} is empty, ask for the target URL before running anything. If it's a local dev server, start it first.
Ensure Lighthouse is available: npx lighthouse --version 2>/dev/null
On Windows, run the multi-line bash commands and
2>/dev/null(here and in Phase 5) via the Bash tool / Git Bash. PowerShell does not support\line continuation or2>/dev/null- use a single line with backtick continuation and2>$nullinstead.
Run the baseline audit:
npx lighthouse {{args}} --output=json --output-path=./lighthouse-baseline.json \
--chrome-flags="--headless --no-sandbox" \
--only-categories=performance,accessibility,best-practices,seo --quiet
Display scores (🔴 0–49, 🟡 50–89, 🟢 90–100) and Core Web Vitals: LCP < 2.5s | INP < 200ms | CLS < 0.1 | FCP < 1.8s | TTFB < 800ms | TBT < 200ms
Spawn 4 parallel subagents, each reading ./lighthouse-baseline.json:
| Subagent | Category | What to extract |
|---|---|---|
| 1 | Performance | Failed audits, opportunity savings (ms/KB), diagnostics sorted by impact |
| 2 | Accessibility | Failed audits, affected element counts, WCAG failure type |
| 3 | Best Practices | Failed audits, deprecation warnings, console errors, security issues |
| 4 | SEO | Failed audits, missing meta tags, crawlability issues, structured data problems |
Consolidate findings. Assign Impact (High/Medium/Low), Effort (Low/Medium/High), and Category (P/A/B/S) to each issue. Present a ranked table and ask: "Which issues should I fix? (all / just Performance / select numbers)" Do not implement anything until the user answers.
Work through selected fixes one at a time. For each fix:
Performance fixes: see references/performance-fixes.md
Accessibility fixes: see references/accessibility-fixes.md
Best Practices & SEO fixes: see references/best-practices-seo-fixes.md
Re-run Lighthouse (same flags, --output-path=./lighthouse-after.json) and display a before/after table for all four categories plus Core Web Vitals.
If any score went down, investigate why and fix before reporting done.
If running locally: open in browser, run DevTools Lighthouse to confirm scores match CLI results, verify the golden path (navigation, forms, key interactions), and check for visual regressions.
width/height set, lazy loading added, LCP image prioritizedfont-display: swap, preloaded if criticalCache-Control headers<img> elements have alt attributes<html lang=""> and <title> present on all pages<meta name="description"> and viewport tag presenttarget="_blank" links have rel="noopener noreferrer"