Question 1

Does SkillzBench support script-bearing skills or only instruction-only SKILL.md packages?

Accepted Answer

At launch, SkillzBench's scope is instruction-only skills — SKILL.md packages plus text references — which get the full Discover, Verify, Benchmark, and Equip treatment. Script-bearing skills will be listed link-out only, so you can find them but they won't run through the sandbox benchmarking pipeline initially.

Question 2

How does SkillzBench measure whether a skill actually improves my AI agent?

Accepted Answer

Every skill is benchmarked in a sandbox using the same model, tested both with and without the skill, and the difference is published as a Lift score in percentage points. Lift is always shown separately from ratings, and money never touches scores — so the number you see reflects measured performance, not promotion.

Question 3

What goes into the SkillzBench Trust Score, and how do I know a skill is safe to equip?

Accepted Answer

The Trust Score runs 0-100 and combines security, quality, license, maintenance and community signals. Every version is pinned to a commit SHA and goes through validation, license-checking, security scanning, and quality judgment before it's listed, so you're never equipping an unverified snapshot.

Question 4

Can I control which skills and tools each of my agents can access?

Accepted Answer

Yes — that's the Equip pillar. You connect one MCP server and build per-agent loadouts, toggling skills and tools per agent. Each agent only sees what was chosen for it, which keeps your Claude Code, Codex, Cursor, or Gemini CLI setups clean and predictable.

Question 5

How is SkillzBench different from browsing GitHub or an MCP registry directly?

Accepted Answer

Registries and GitHub list skills; SkillzBench tests them. It continuously crawls and dedupes skills from GitHub, pins versions to commit SHAs, security-scans and license-checks them, benchmarks them in a sandbox with published Lift, and keeps you current by tracking upstream changes, re-scanning, re-benchmarking, and notifying you when anything shifts. It's an independent testing lab, not a marketplace.

MCP Server Discovery for Students