Score7.7
Popularity72.0
Risknone
TierGold
Score breakdown
Usefulness7.0
Novelty8.0
Momentum7.0
Maturity7.6
Open-source/build8.4
Evidence7.2
Workflow potential8.8
Setup ease6.4
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for agent teams that ship a directory of skills and want a regression suite: pin the benchmark version, add it to CI for the agent under test, and treat drops in skill-level scores as build failures the same way you would for unit tests.
Who should use it
Who should skip it
Skip if the source link, docs, or setup requirements do not match your workflow.
Risk explanation
benchmark scores can be gamed; pair SkillsBench with at least one real user task in your CI.