The MCP ecosystem often has several independent packages implementing the same tool — and "Agent Skills" currently has 4. Every one of them was scanned with the same deterministic engine, so the numbers below are directly comparable: the Trust Score (A–F), the capability blast radius, and how much of the package the scan could actually inspect. They are ranked by score; ties break toward unscoped, longer-established packages.
| Implementation | Package | Trust | Capability | Coverage | Findings | Scanned |
|---|---|---|---|---|---|---|
| Agent Skills Source verifiedbest by eforest-finance | @eforest-finance/agent-skills
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Agent Skills by aasm3535 | mcp-agent-skills
npm |
A 100/100 | High | Source | 1 | 2026-07-22 |
| Agent Skills by DiscreteTom | agent-skills-mcp
PyPI |
A 98/100 | Minimal | Source | 1 | 2026-07-22 |
| Agent Skills by DiscreteTom | agent-skills-mcp
npm |
A 94/100 | High | Source | 2 | 2026-07-22 |
A higher-ranked implementation is not "the official one" — ranking reflects only what the deterministic scan found in each published package. Open an implementation to read its individual findings with evidence, its scan history per version, and to grab an embeddable badge. Scores are automated opinions, recomputed on every rescan.