Question 1

Can I migrate SKILL.md skills from Claude Code to Gemini CLI or Cursor through SkillzBench?

Accepted Answer

SkillzBench is built around the SKILL.md instruction-package standard that works across Claude Code, Codex, Cursor, Gemini CLI and chat-app agents. It verifies, benchmarks and equips skills through one MCP server with per-agent loadouts, so the same skill can be toggled on for whichever agent you run. Launch scope covers instruction-only skills; script-bearing skills are listed link-out only.

Question 2

How does SkillzBench tell me whether a skill update is safe to adopt?

Accepted Answer

Every skill version is pinned to a commit SHA and put through validation, license checks, security scans and quality judging. The Stay Current pillar tracks upstream changes, re-scans and re-benchmarks automatically, and notifies you — so you always know what changed before you adopt it.

Question 3

What does the benchmark actually measure, and can I trust the ratings?

Accepted Answer

Each skill is tested in a sandbox with the same model, with and without the skill installed, and the resulting Lift is published in percentage points. Lift is always shown separately from the Trust score, and money never touches scores — SkillzBench is an independent testing lab, not a sponsored marketplace.

Question 4

Is SkillzBench available now, and how do I get access?

Accepted Answer

SkillzBench is pre-launch and actively being built; the waitlist and newsletter are live but the product is not yet public. Join the waitlist for early access. The pricing hypothesis includes a generous free tier, Pro at roughly $9-15/mo, Teams at roughly $15-25/seat/mo, and a Creator tier for verified authors.

Question 5

How is this different from just pulling skills off GitHub myself?

Accepted Answer

Raw GitHub skills come with no compatibility guarantees and no safety signal — published research found roughly of skills carry at least one vulnerability. SkillzBench dedupes skills from GitHub, pins versions to commit SHAs, security-scans and license-checks them, benchmarks their Lift, and lets you equip them per agent via one MCP server — with continuous upstream tracking after adoption.

Agent Skill Migration for Founders