import { AgentSkillsExplainer } from "@/components/AgentSkillsExplainer"; import { DomainRadar } from "@/components/DomainRadar"; import { HomeBackground } from "@/components/HomeBackground"; import { Leaderboard } from "@/components/Leaderboard"; import { HowItWorks } from "@/components/HowItWorks"; import { ReleasePerformance } from "@/components/ReleasePerformance"; import { TaskCards } from "@/components/TaskCards"; import { TimePerformance } from "@/components/TimePerformance"; import { WhosCiting } from "@/components/WhosCiting"; import { Button } from "@/components/ui/button"; import { getTasks } from "@/utils/tasks"; import { ArrowRight } from "lucide-react"; import type { Metadata } from "next"; import Link from "next/link"; export const metadata: Metadata = { title: "SkillsBench — Benchmarking How Well Agent Skills Work", description: "The first evaluation framework measuring how AI agent skills improve performance. SkillsBench v1.1 ships 87 native BenchFlow task.md packages for BenchFlow.", alternates: { canonical: "https://skillsbench.ai" }, }; export default async function Home() { const tasks = await getTasks(); const recentTasks = tasks.slice(0, 20); return (
{/* Custom Hero Section */}
{/* Soft Glow Background for better text visibility */}
New release · SkillsBench v1.1

Bench: Benchmarking How Well Skills Work Across Diverse Tasks

The first evaluation framework that measures how skills work, and the first dataset that measures how powerful models are at using skills on expert-curated tasks across high-GDP-value, diverse domains.

{/* Buttons wrapped in 'dark' class to ensure they look correct against the dark background regardless of system theme */}
{/* How SkillsBench Works (main column) + Cited By (right rail) */}
); }