Frontend Performance
Use when the user asks about bundle size, slow page loads, code splitting by route, lazy loading, rendering cost, memoization or a frontend performance budget in a framework app. Produces measure-first, framework-level optimizations. Not for Core Web Vitals field data and CrUX diagnosis (use web-performance) or image pipelines (use frontend-image-optimization).
Install
npx skills add j4flmao/agent-skills --skill frontend-performancegit clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/frontend/universal/performance ~/.claude/skills/frontend-performancePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Frontend Performance
## Purpose
Optimize Core Web Vitals (LCP, CLS, INP) and bundle size. Measure before and after every optimization. Never optimize without data.
## Agent Protocol
### Trigger
Exact user phrases: "performance", "slow page", "bundle size", "lazy loading", "code splitting", "LCP", "CLS", "INP", "web vitals", "image optimization", "caching", "page speed", "load time".
### Input Context
Before activating, verify:
- The performance issue is identified (slow page load, janky interaction, large bundle) or ask.
- The framework is known (React, Vue, Angular, Next.js, Nuxt).
- Whether the target is lab metrics (Lighthouse) or field metrics (RUM data).
### Output Artifact
No file output. Produces optimization recommendations as text.
### Response Format
```
Metric: {LCP/CLS/INP/bundle}
Current: {measured value}
Target: {target value}
Root cause: {specific cause}
Fix: {specific change with code}
Expected improvement: {estimated factor}
```
No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output — why use many token when few do trick.
### Completion Criteria
- [ ] Metric measured before optimization (Lighthouse, Web Vitals, or bundle analysis).
- [ ] Root cause identified from the measurement data.
- [ ] Specific fix provided with code example.
- [ ] Performance budget defined.
- [ ] One optimization at a time with before/after measurement.
### Max Response Length
Per optimization: 10 lines. Code example: 8 lines.Details
- Skill name
frontend-performance- Repository
- j4flmao/agent-skills
- Path
skills/frontend/universal/performance/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Frontend Performance skill do?
Use when the user asks about bundle size, slow page loads, code splitting by route, lazy loading, rendering cost, memoization or a frontend performance budget in a framework app. Produces measure-first, framework-level optimizations. Not for Core Web Vitals field data and CrUX diagnosis (use web-performance) or image pipelines (use frontend-image-optimization).
How do I install the Frontend Performance skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill frontend-performance. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Frontend Performance popular?
It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.
Related skills
Agent Observability
45j4flmao/agent-skills
Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).
AI Agent Architectures
45j4flmao/agent-skills
Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).
AI Agent Core Loop
45j4flmao/agent-skills
Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).
Frontend Pwa
45j4flmao/agent-skills
Use when the user asks to make the site installable and work offline, PWA, web app manifest, service worker with Workbox or vite-plugin-pwa, update prompts, background sync or web push. Produces manifest, caching strategies and a safe update flow with real browser limits. Not for HTTP cache headers (use frontend-browser-caching).
Frontend Patterns
45j4flmao/agent-skills
Use when the user asks about frontend component patterns: compound components, container/presentational, custom hooks, render props, HOCs, provider pattern, state reducer or headless components. Produces pattern choices with framework examples. Not for app folder structure (use react-architecture) or picking a state library (use frontend-state-management).
Frontend Qwik Patterns
45j4flmao/agent-skills
Use when the user asks about useSignal, useStore, component$, routeLoader$, routeAction$, server$, the Qwik optimizer or Qwik prefetching. Produces fine-grained reactive Qwik patterns and serialization-safe lazy boundaries for an existing app. Not for Qwik project setup (use frontend-qwik-architecture).
Browse the most popular Claude skills, all frontend & design skills, or write your own with the skills generator.