Question 1

Is SkillzBench live yet, 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 itself is not yet public. Join the waitlist to be notified as Discover, Verify, Benchmark, Equip, and Stay current come online.

Question 2

Which kinds of agent skills does SkillzBench support at launch?

Accepted Answer

Launch scope is instruction-only skills — SKILL.md files plus text references — for Claude Code, Codex, Cursor, and Gemini CLI. Script-bearing skills will be listed link-out only, so you can find them without SkillzBench executing their code.

Question 3

How does the trust score work, and can authors pay to boost it?

Accepted Answer

Every skill gets a 0-100 trust score from security, quality, license, maintenance, and community signals. Money never touches scores — Lift is always shown separately from ratings, so commercial considerations can't contaminate evaluation.

Question 4

How is a skill benchmarked — what does 'Lift' actually mean?

Accepted Answer

SkillzBench tests every skill in a sandbox with the same model, running tasks with and without the skill, then publishes the Lift in percentage points — a like-for-like measure of how much a skill actually improves performance, separate from any rating.

Question 5

How does SkillzBench differ from just browsing GitHub for skills?

Accepted Answer

GitHub gives you raw, unpinned files with no verification. SkillzBench dedupes skills, pins versions to commit SHAs, license-checks, security-scans, and quality-judges them, benchmarks them in a sandbox, and tracks upstream changes with re-scans and notifications — all through one MCP server with per-agent loadouts.

Verified Agent Skills for Content Creators