Summary
Runs browser-based performance measurements against your live app, capturing Core Web Vitals (LCP, INP, CLS) plus load metrics, resource optimization, and bundle analysis. You get actual Performance API data, not static analysis. It's built around Google's 2024 thresholds and compares your numbers against HTTP Archive benchmarks. Best used before launches or when pages feel slow but you're not sure why. The five-phase approach is thorough, maybe overkill for a quick check, but if you need to justify performance work to stakeholders or catch what Lighthouse misses in local dev, it delivers the evidence.
Install to Claude Code
npx -y skills add shiplightai/agent-skills --skill performance-review --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →First SeenJun 3, 2026
