← Methodology
v3.20.0 1 / 7

SkillCheck
Methodology

25
categories
14
sources
5
phases
5
months
getskillcheck.com/methodology
→ swipe to explore
Dec 2025 → Apr 2026
Phase I · Build to Spec 2 / 7
Build to
Spec
v1.0–1.4 · Dec 2025 · 3 sources
10 categories
1–10
Phase II · From Practice 3 / 7
From
Practice
v3.10–3.14 · Mar 2026 · 1 source
08 categories
11–18
Phase III · From the Field 4 / 7
From the
Field
v3.16–3.17 · Apr 2026 · 2 sources
03 categories
19–21
Phase IV · Ecosystem 5 / 7
Ecosystem
v3.18.0 · Apr 2026 · 3 sources
01 category
22

A single category, but a decisive one. Anchored by Hasan and Wang's arXiv papers measuring description-quality smells across thousands of MCP servers.

Phase V · Marketplace 6 / 7
Marketplace
v3.20.0 · Apr 2026 · 5 sources
03 categories
23–25
Empirical Anchors 7 / 7
Hasan et al. · description smell rate
97%

of 856 MCP tools across 103 servers contained at least one description smell.

Wang et al. · selection probability
72%vs20%

Across 10,831 MCP servers, standard-compliant descriptions get picked by an agent 72% of the time. Non-compliant descriptions get picked 20% of the time.

Starting score
100

Critical −20 · Warning −5 · Suggestion −1

Navigate with / or click the dots. Append ?clean=1#s2 to URL to view a single slide without nav (used for PNG export).