Question 1

How do I move Claude Code skills to Gemini CLI or Cursor without breaking things?

Accepted Answer

Agent Skills is an open SKILL.md standard supported by 25+ agent frameworks, but quality and safety vary wildly between packages. SkillzBench verifies every skill — pinned to a commit SHA, security-scanned, license-checked and quality-judged — then benchmarks its Lift so you know it works before equipping it on a different agent via per-agent loadouts.

Question 2

What does SkillzBench actually benchmark, and how is Lift measured?

Accepted Answer

SkillzBench runs every skill in a sandbox with the same model, once with the skill and once without, and publishes the difference as Lift in percentage points. Lift is always shown separately from ratings and trust scores, and money never touches scores — so the number reflects the skill, not the seller.

Question 3

Are script-bearing skills supported, or only SKILL.md instruction packages?

Accepted Answer

At launch, SkillzBench covers instruction-only skills — SKILL.md plus text references. Script-bearing skills are listed link-out only, which keeps the verified surface area safe while the platform matures.

Question 4

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 (~$9-15/mo) for more agents and unlimited enabled skills, Teams (~$15-25/seat/mo) for org loadouts, allowlists and audit, and Creator (~$5-10/mo) for verified authors.

Question 5

Why not just browse GitHub for skills and install them myself?

Accepted Answer

GitHub has no verification layer: no commit-pinned versions, no security scans, no license checks, and no benchmarked Lift. With research showing roughly of skills carry at least one vulnerability and 88% of organizations reporting agent security incidents, SkillzBench's trust score and sandbox benchmarks exist precisely because raw GitHub listings can't tell you what's safe or effective.

Agent Skill Migration for Developers