Question 1

How does SkillzBench calculate its 0-100 trust score for agent skills?

Accepted Answer

The trust score combines security, quality, license, maintenance, and community signals into a single 0-100 rating. Critically, benchmark Lift is always shown separately from the trust score, and money never touches scores — verified authors or vendors cannot pay to improve a rating.

Question 2

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

Accepted Answer

At launch, SkillzBench verifies instruction-only skills — SKILL.md packages plus text references. Script-bearing skills are listed link-out only rather than fully verified, so you always know exactly what level of scrutiny a listed skill has received.

Question 3

Which AI coding agents and tools does SkillzBench work with?

Accepted Answer

SkillzBench focuses on agent skills (SKILL.md instruction packages) for Claude Code, Codex, Cursor, Gemini CLI, and chat-app agents. Distribution happens through one MCP server with per-agent loadouts, so you can manage skills across your agent fleet from a single control panel.

Question 4

When can I start using SkillzBench?

Accepted Answer

SkillzBench is pre-launch and actively being built — the waitlist and newsletter are live now, but the product is not yet public. Joining the waitlist gets you launch notifications and early access as the Discover, Verify, Benchmark, Equip, and Stay-current pillars roll out.

Question 5

How is SkillzBench different from just searching GitHub for SKILL.md files?

Accepted Answer

GitHub gives you raw, unvetted files with no security scan, no license check, and no performance evidence. SkillzBench dedupes the ecosystem, pins every version to a commit SHA, security-scans and quality-judges each skill, and benchmarks real Lift in a sandbox — so you compare verified options instead of gambling on popularity.

Question 6

Can SkillzBench help me justify AI agent investment to leadership?

Accepted Answer

Yes — through evidence. With over 80% of enterprise AI projects failing to reach production and Gartner predicting of agentic AI projects canceled by 2027, leadership skepticism is warranted. SkillzBench's published Lift scores in percentage points give you concrete, independently measured impact data for every skill you propose adopting.

Verified Agent Skills for Product Managers