Question 1

What exactly is a curated agent loadout for writers?

Accepted Answer

A loadout is the specific set of skills and tools you assign to a given agent. With SkillzBench's Equip pillar, you toggle skills and tools per agent through one MCP server, and the agent only sees what was chosen — so your drafting, editing, and research agents can each run a purpose-built, vetted toolkit.

Question 2

How does SkillzBench decide whether a skill is trustworthy?

Accepted Answer

Every skill gets a Trust Score from 0-100 built from security, quality, license, maintenance, and community signals. Versions are pinned to a commit SHA, validated, license-checked, security-scanned, and quality-judged. Lift is always shown separately from ratings, and money never touches scores.

Question 3

Are agent skills actually a security risk for my writing workflow?

Accepted Answer

Yes — published research found roughly of agent skills carry at least one vulnerability, and 67% of executives report data leaks or incidents tied to unapproved AI tools. SkillzBench addresses this by security-scanning every skill and publishing its Trust Score before you equip it.

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 itself is not yet public. Joining the waitlist gets you early access as the Discover, Verify, Benchmark, Equip, and Stay-current pillars come online.

Question 5

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

Accepted Answer

GitHub gives you raw, unvetted packages with no quality or security signal. SkillzBench continuously crawls and dedupes skills from GitHub, then verifies, benchmarks, and scores them — publishing each skill's Lift in percentage points from sandbox tests with the same model, with and without the skill. At launch, instruction-only skills are fully supported; script-bearing skills are listed link-out only.

Curated Agent Loadouts for Writers