632 lines
15 KiBLFS
HTML
632 lines
15 KiBLFS
HTML
<!DOCTYPE html>
|
|
<html lang="en">
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<title>SkillsBench - Academic</title>
|
|
<style>
|
|
@import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700&family=Source+Serif+4:opsz,wght@8..60,500;8..60,600;8..60,700&family=JetBrains+Mono:wght@400;500&display=swap');
|
|
|
|
* { margin: 0; padding: 0; box-sizing: border-box; }
|
|
|
|
body {
|
|
font-family: 'Inter', -apple-system, sans-serif;
|
|
background: #e8e8e8;
|
|
display: flex;
|
|
justify-content: center;
|
|
align-items: center;
|
|
min-height: 100vh;
|
|
padding: 20px;
|
|
}
|
|
|
|
.infographic {
|
|
width: 1080px;
|
|
height: 1080px;
|
|
background: #fafafa;
|
|
padding: 32px 44px;
|
|
display: flex;
|
|
flex-direction: column;
|
|
}
|
|
|
|
/* ==================== HEADER ==================== */
|
|
.header {
|
|
display: flex;
|
|
justify-content: space-between;
|
|
align-items: flex-start;
|
|
margin-bottom: 12px;
|
|
}
|
|
|
|
.header-left h1 {
|
|
font-family: 'Source Serif 4', Georgia, serif;
|
|
font-size: 78px;
|
|
font-weight: 700;
|
|
color: #111;
|
|
letter-spacing: -2px;
|
|
line-height: 1;
|
|
}
|
|
|
|
.header-left .subtitle {
|
|
font-size: 20px;
|
|
color: #555;
|
|
margin-top: 12px;
|
|
max-width: 620px;
|
|
line-height: 1.5;
|
|
}
|
|
|
|
.header-right {
|
|
text-align: right;
|
|
padding-top: 8px;
|
|
}
|
|
|
|
.header-venue {
|
|
font-size: 14px;
|
|
font-weight: 700;
|
|
color: #111;
|
|
background: #f0f0f0;
|
|
padding: 6px 14px;
|
|
border-radius: 4px;
|
|
}
|
|
|
|
.header-meta {
|
|
font-size: 12px;
|
|
color: #888;
|
|
margin-top: 6px;
|
|
}
|
|
|
|
/* ==================== CONTEXT BAR ==================== */
|
|
.context-bar {
|
|
display: grid;
|
|
grid-template-columns: 1fr 1fr 1fr;
|
|
background: #111;
|
|
border-radius: 10px;
|
|
overflow: hidden;
|
|
margin-bottom: 10px;
|
|
}
|
|
|
|
.context-col {
|
|
padding: 18px 16px;
|
|
text-align: center;
|
|
border-right: 1px solid #333;
|
|
}
|
|
|
|
.context-col:last-child {
|
|
border-right: none;
|
|
background: #1a1a2e;
|
|
}
|
|
|
|
.context-label {
|
|
font-size: 12px;
|
|
font-weight: 700;
|
|
text-transform: uppercase;
|
|
letter-spacing: 2px;
|
|
color: #666;
|
|
margin-bottom: 4px;
|
|
}
|
|
|
|
.context-title {
|
|
font-size: 22px;
|
|
font-weight: 700;
|
|
color: #fff;
|
|
margin-bottom: 4px;
|
|
}
|
|
|
|
.context-sub {
|
|
font-size: 13px;
|
|
color: #888;
|
|
}
|
|
|
|
/* ==================== TIMELINE ==================== */
|
|
.timeline-bar {
|
|
background: #fff;
|
|
border: 1px solid #e0e0e0;
|
|
border-radius: 8px;
|
|
padding: 16px 22px;
|
|
margin-bottom: 10px;
|
|
display: flex;
|
|
align-items: center;
|
|
gap: 18px;
|
|
}
|
|
|
|
.timeline-title {
|
|
font-size: 13px;
|
|
font-weight: 700;
|
|
text-transform: uppercase;
|
|
letter-spacing: 1px;
|
|
color: #888;
|
|
flex-shrink: 0;
|
|
}
|
|
|
|
.timeline {
|
|
flex: 1;
|
|
position: relative;
|
|
height: 50px;
|
|
}
|
|
|
|
.timeline::before {
|
|
content: '';
|
|
position: absolute;
|
|
top: 6px;
|
|
left: 0;
|
|
right: 0;
|
|
height: 2px;
|
|
background: linear-gradient(90deg, #ddd 0%, #111 100%);
|
|
}
|
|
|
|
.timeline-item {
|
|
position: absolute;
|
|
display: flex;
|
|
flex-direction: column;
|
|
align-items: center;
|
|
z-index: 1;
|
|
transform: translateX(-50%);
|
|
}
|
|
|
|
/* Proportional positioning: Nov'24(0%) --4mo-- Mar'25(31%) --7mo-- Oct'25(85%) --2mo-- Dec'25(100%) */
|
|
.timeline-item:nth-child(1) { left: 0%; transform: translateX(0); }
|
|
.timeline-item:nth-child(2) { left: 31%; }
|
|
.timeline-item:nth-child(3) { left: 85%; }
|
|
.timeline-item:nth-child(4) { left: 100%; transform: translateX(-100%); }
|
|
|
|
.timeline-dot {
|
|
width: 14px;
|
|
height: 14px;
|
|
border-radius: 50%;
|
|
background: #fff;
|
|
border: 3px solid #bbb;
|
|
margin-bottom: 6px;
|
|
}
|
|
|
|
.timeline-item.highlight .timeline-dot {
|
|
background: #111;
|
|
border-color: #111;
|
|
box-shadow: 0 0 0 4px rgba(0,0,0,0.1);
|
|
}
|
|
|
|
.timeline-date {
|
|
font-size: 14px;
|
|
font-weight: 600;
|
|
color: #333;
|
|
white-space: nowrap;
|
|
}
|
|
|
|
.timeline-text {
|
|
font-size: 12px;
|
|
color: #888;
|
|
white-space: nowrap;
|
|
}
|
|
|
|
/* ==================== GAP STATEMENT ==================== */
|
|
.gap-section {
|
|
background: linear-gradient(135deg, #f5f5f5 0%, #ebebeb 100%);
|
|
border-left: 4px solid #111;
|
|
border-radius: 0 8px 8px 0;
|
|
padding: 18px 22px;
|
|
margin-bottom: 10px;
|
|
}
|
|
|
|
.gap-title {
|
|
font-size: 22px;
|
|
font-weight: 700;
|
|
color: #111;
|
|
margin-bottom: 8px;
|
|
}
|
|
|
|
.gap-text {
|
|
font-size: 16px;
|
|
color: #555;
|
|
line-height: 1.55;
|
|
}
|
|
|
|
.gap-text strong {
|
|
color: #111;
|
|
background: #fff3cd;
|
|
padding: 1px 4px;
|
|
border-radius: 2px;
|
|
}
|
|
|
|
/* ==================== RESEARCH QUESTIONS ==================== */
|
|
.rq-section {
|
|
display: grid;
|
|
grid-template-columns: 1fr 1fr;
|
|
gap: 12px;
|
|
margin-bottom: 10px;
|
|
}
|
|
|
|
.rq-card {
|
|
background: #fff;
|
|
border: 1px solid #e0e0e0;
|
|
border-radius: 10px;
|
|
padding: 20px 18px;
|
|
display: flex;
|
|
gap: 14px;
|
|
align-items: flex-start;
|
|
}
|
|
|
|
.rq-num {
|
|
width: 44px;
|
|
height: 44px;
|
|
background: #111;
|
|
color: #fff;
|
|
border-radius: 50%;
|
|
font-size: 22px;
|
|
font-weight: 700;
|
|
display: flex;
|
|
align-items: center;
|
|
justify-content: center;
|
|
flex-shrink: 0;
|
|
}
|
|
|
|
.rq-content {
|
|
flex: 1;
|
|
}
|
|
|
|
.rq-label {
|
|
font-size: 11px;
|
|
font-weight: 700;
|
|
text-transform: uppercase;
|
|
letter-spacing: 1.5px;
|
|
color: #888;
|
|
margin-bottom: 4px;
|
|
}
|
|
|
|
.rq-text {
|
|
font-size: 19px;
|
|
font-weight: 600;
|
|
color: #111;
|
|
line-height: 1.35;
|
|
margin-bottom: 6px;
|
|
}
|
|
|
|
.rq-sub {
|
|
font-size: 15px;
|
|
color: #666;
|
|
line-height: 1.45;
|
|
}
|
|
|
|
/* ==================== BENCHMARK ==================== */
|
|
.benchmark-section {
|
|
background: #fff;
|
|
border: 1px solid #e0e0e0;
|
|
border-radius: 10px;
|
|
padding: 22px 24px;
|
|
margin-bottom: 12px;
|
|
}
|
|
|
|
.benchmark-header {
|
|
display: flex;
|
|
justify-content: space-between;
|
|
align-items: center;
|
|
margin-bottom: 12px;
|
|
}
|
|
|
|
.benchmark-title {
|
|
font-size: 16px;
|
|
font-weight: 700;
|
|
text-transform: uppercase;
|
|
letter-spacing: 1px;
|
|
color: #111;
|
|
}
|
|
|
|
.benchmark-badge {
|
|
font-family: 'JetBrains Mono', monospace;
|
|
font-size: 11px;
|
|
color: #888;
|
|
background: #f5f5f5;
|
|
padding: 4px 10px;
|
|
border-radius: 4px;
|
|
}
|
|
|
|
.benchmark-grid {
|
|
display: grid;
|
|
grid-template-columns: auto auto 1fr;
|
|
gap: 20px;
|
|
align-items: center;
|
|
}
|
|
|
|
.stat-box {
|
|
background: #f8f8f8;
|
|
border-radius: 8px;
|
|
padding: 16px 28px;
|
|
text-align: center;
|
|
}
|
|
|
|
.stat-num {
|
|
font-size: 42px;
|
|
font-weight: 700;
|
|
color: #111;
|
|
line-height: 1;
|
|
}
|
|
|
|
.stat-label {
|
|
font-size: 13px;
|
|
color: #888;
|
|
margin-top: 4px;
|
|
text-transform: uppercase;
|
|
letter-spacing: 0.5px;
|
|
}
|
|
|
|
.tags-section {
|
|
display: flex;
|
|
flex-direction: column;
|
|
gap: 8px;
|
|
}
|
|
|
|
.tags-label {
|
|
font-size: 12px;
|
|
font-weight: 600;
|
|
text-transform: uppercase;
|
|
letter-spacing: 1px;
|
|
color: #888;
|
|
}
|
|
|
|
.tags-wrap {
|
|
display: flex;
|
|
flex-wrap: wrap;
|
|
gap: 6px;
|
|
}
|
|
|
|
.tag {
|
|
background: #f0f0f0;
|
|
padding: 5px 10px;
|
|
border-radius: 4px;
|
|
font-size: 13px;
|
|
color: #555;
|
|
display: flex;
|
|
align-items: center;
|
|
gap: 6px;
|
|
}
|
|
|
|
.tag-count {
|
|
background: #111;
|
|
color: #fff;
|
|
padding: 2px 6px;
|
|
border-radius: 3px;
|
|
font-size: 10px;
|
|
font-weight: 600;
|
|
}
|
|
|
|
.difficulty-box {
|
|
display: flex;
|
|
flex-direction: column;
|
|
gap: 8px;
|
|
min-width: 140px;
|
|
}
|
|
|
|
.diff-label {
|
|
font-size: 10px;
|
|
font-weight: 600;
|
|
text-transform: uppercase;
|
|
letter-spacing: 1px;
|
|
color: #888;
|
|
}
|
|
|
|
.diff-bar {
|
|
height: 8px;
|
|
background: #eee;
|
|
border-radius: 4px;
|
|
overflow: hidden;
|
|
display: flex;
|
|
}
|
|
|
|
.diff-hard {
|
|
background: #111;
|
|
width: 65%;
|
|
}
|
|
|
|
.diff-med {
|
|
background: #888;
|
|
width: 35%;
|
|
}
|
|
|
|
.diff-legend {
|
|
display: flex;
|
|
justify-content: space-between;
|
|
font-size: 10px;
|
|
color: #888;
|
|
}
|
|
|
|
/* ==================== SUMMARY ROW ==================== */
|
|
.summary-row {
|
|
display: grid;
|
|
grid-template-columns: repeat(4, 1fr);
|
|
gap: 10px;
|
|
margin-top: 12px;
|
|
padding-top: 12px;
|
|
border-top: 2px solid #e0e0e0;
|
|
}
|
|
|
|
.summary-item {
|
|
background: #fff;
|
|
border: 1px solid #e8e8e8;
|
|
border-radius: 8px;
|
|
padding: 16px 16px;
|
|
}
|
|
|
|
.summary-label {
|
|
font-size: 12px;
|
|
font-weight: 700;
|
|
text-transform: uppercase;
|
|
letter-spacing: 1px;
|
|
color: #888;
|
|
margin-bottom: 6px;
|
|
}
|
|
|
|
.summary-value {
|
|
font-size: 16px;
|
|
font-weight: 600;
|
|
color: #111;
|
|
}
|
|
|
|
/* ==================== FOOTER ==================== */
|
|
.footer {
|
|
margin-top: 16px;
|
|
display: flex;
|
|
justify-content: space-between;
|
|
font-size: 14px;
|
|
color: #888;
|
|
}
|
|
|
|
.footer-left {
|
|
font-weight: 600;
|
|
color: #111;
|
|
}
|
|
</style>
|
|
</head>
|
|
<body>
|
|
<div class="infographic">
|
|
|
|
<!-- ① HEADER -->
|
|
<div class="header">
|
|
<div class="header-left">
|
|
<h1>SkillsBench</h1>
|
|
<p class="subtitle">The first gym-style benchmark for AI Agent Skills—measuring how well agents apply procedural knowledge, not just connect to tools.</p>
|
|
</div>
|
|
<div class="header-right">
|
|
<div class="header-venue">Open Source</div>
|
|
<div class="header-meta">skillsbench.ai</div>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- ② CONTEXT: MCP + Skills = SkillsBench -->
|
|
<div class="context-bar">
|
|
<div class="context-col">
|
|
<div class="context-label">MCP</div>
|
|
<div class="context-title">Tool Provisioning</div>
|
|
<div class="context-sub">"What tools can an agent use?"</div>
|
|
</div>
|
|
<div class="context-col">
|
|
<div class="context-label">Skills</div>
|
|
<div class="context-title">Training Materials</div>
|
|
<div class="context-sub">"How should an agent work?"</div>
|
|
</div>
|
|
<div class="context-col">
|
|
<div class="context-label">SkillsBench</div>
|
|
<div class="context-title">First Benchmark</div>
|
|
<div class="context-sub">Measuring expertise transfer at scale</div>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- ③ TIMELINE -->
|
|
<div class="timeline-bar">
|
|
<div class="timeline-title">Timeline</div>
|
|
<div class="timeline">
|
|
<div class="timeline-item">
|
|
<div class="timeline-dot"></div>
|
|
<div class="timeline-date">Nov '24</div>
|
|
<div class="timeline-text">MCP ships</div>
|
|
</div>
|
|
<div class="timeline-item">
|
|
<div class="timeline-dot"></div>
|
|
<div class="timeline-date">Mar '25</div>
|
|
<div class="timeline-text">OpenAI adopts</div>
|
|
</div>
|
|
<div class="timeline-item">
|
|
<div class="timeline-dot"></div>
|
|
<div class="timeline-date">Oct '25</div>
|
|
<div class="timeline-text">Skills beta</div>
|
|
</div>
|
|
<div class="timeline-item highlight">
|
|
<div class="timeline-dot"></div>
|
|
<div class="timeline-date">Dec '25</div>
|
|
<div class="timeline-text">9 agents adopt</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- ④ THE GAP -->
|
|
<div class="gap-section">
|
|
<div class="gap-title">The Gap: No Benchmark for Skills</div>
|
|
<div class="gap-text">
|
|
MCP benchmarks measure tool connectivity. But Skills are training materials—procedural knowledge that teaches agents <em>how</em> to work.
|
|
No systematic framework exists for evaluating whether Skills actually transfer expertise effectively.
|
|
<strong>SkillsBench fills this gap.</strong>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- ⑤ RESEARCH QUESTIONS -->
|
|
<div class="rq-section">
|
|
<div class="rq-card">
|
|
<div class="rq-num">1</div>
|
|
<div class="rq-content">
|
|
<div class="rq-label">Research Question</div>
|
|
<div class="rq-text">Do Skills help agents perform better?</div>
|
|
<div class="rq-sub">Comparing agent performance with vs. without Skills on identical tasks</div>
|
|
</div>
|
|
</div>
|
|
<div class="rq-card">
|
|
<div class="rq-num">2</div>
|
|
<div class="rq-content">
|
|
<div class="rq-label">Research Question</div>
|
|
<div class="rq-text">Can agents compose multiple Skills?</div>
|
|
<div class="rq-sub">Measuring how well agents select and combine Skills for complex workflows</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- ⑥ ECOSYSTEM ADOPTION -->
|
|
<div class="benchmark-section">
|
|
<div class="benchmark-header">
|
|
<div class="benchmark-title">Ecosystem Adoption</div>
|
|
<div class="benchmark-badge">Dec 2025</div>
|
|
</div>
|
|
<div class="benchmark-grid">
|
|
<div class="stat-box">
|
|
<div class="stat-num">28k+</div>
|
|
<div class="stat-label">Smithery.ai</div>
|
|
</div>
|
|
<div class="stat-box">
|
|
<div class="stat-num">45k+</div>
|
|
<div class="stat-label">GitHub SKILL.md</div>
|
|
</div>
|
|
<div class="tags-section">
|
|
<div class="tags-label">Domains</div>
|
|
<div class="tags-wrap">
|
|
<span class="tag">Research</span>
|
|
<span class="tag">Coding</span>
|
|
<span class="tag">Writing</span>
|
|
<span class="tag">Data</span>
|
|
<span class="tag">Design</span>
|
|
<span class="tag">Planning</span>
|
|
<span class="tag">Office</span>
|
|
<span class="tag">Logistics</span>
|
|
<span class="tag">Bio</span>
|
|
<span class="tag">Finance</span>
|
|
<span class="tag">Security</span>
|
|
<span class="tag">DevOps</span>
|
|
<span class="tag">Marketing</span>
|
|
<span class="tag">Legal</span>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- ⑦ SUMMARY ROW -->
|
|
<div class="summary-row">
|
|
<div class="summary-item">
|
|
<div class="summary-label">Evaluation</div>
|
|
<div class="summary-value">State → Action → Reward</div>
|
|
</div>
|
|
<div class="summary-item">
|
|
<div class="summary-label">Format</div>
|
|
<div class="summary-value">Filesystem-native</div>
|
|
</div>
|
|
<div class="summary-item">
|
|
<div class="summary-label">Properties</div>
|
|
<div class="summary-value">Versionable · Composable</div>
|
|
</div>
|
|
<div class="summary-item">
|
|
<div class="summary-label">Environment</div>
|
|
<div class="summary-value">Docker + BenchFlow</div>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- ⑧ FOOTER -->
|
|
<div class="footer">
|
|
<span class="footer-left">skillsbench.ai</span>
|
|
<span>github.com/benchflow-ai/skillsbench</span>
|
|
</div>
|
|
|
|
</div>
|
|
</body>
|
|
</html>
|