Question 1

How does SkillzBench security-scan a SKILL.md agent skill?

Accepted Answer

SkillzBench's Verify pillar pins every skill version to a commit SHA, then runs validation, license checks, security scanning and a quality judgment on the instruction package. The results feed into a 0-100 trust score built from security, quality, license, maintenance and community signals — so you get a clear verdict before enabling a skill.

Question 2

Can a skill pass the security scan and still be a bad skill?

Accepted Answer

Yes — which is why SkillzBench separates safety from usefulness. Every skill is benchmarked in a sandbox with the same model, run with and without the skill, and the Lift is published in percentage points. Lift is always shown separately from ratings, and money never touches scores.

Question 3

Does SkillzBench support skills that contain scripts, or only instruction files?

Accepted Answer

At launch, SkillzBench covers instruction-only skills — SKILL.md files plus text references. Script-bearing skills are listed link-out only, so you can discover them but they aren't verified or benchmarked in the same depth.

Question 4

Which agents and tools does SkillzBench work with?

Accepted Answer

SkillzBench targets agent skills for Claude Code, Codex, Cursor, Gemini CLI and chat-app agents. The Equip pillar delivers one MCP server plus per-agent loadouts, so you toggle skills and tools per agent and the agent only sees what was chosen.

Question 5

When can I start using SkillzBench, and what will it cost?

Accepted Answer

SkillzBench is pre-launch and actively being built — the waitlist and newsletter are live now. The pricing hypothesis includes a generous free tier, Pro at roughly $9-15/mo for more agents and unlimited enabled skills, Teams at ~$15-25/seat/mo for org loadouts, allowlists and audit, and a Creator tier at ~$5-10/mo for verified authors.

Agent Security Scanning for Developers