Agents
Why Implexa
Pricing
Resources
Install
Sign in
Sign up
back to leaderboard
RI
@rivin-dong
contributor on implexa, with 2 skills ranked by
SkillRank
across 1 source.
rivin-dong on github
publishes to clawhub
skills, ranked by SkillRank
score
source
skill
7.9
clawhub
prompt-eval
prompt-eval provides a structured 6-step pipeline for testing and optimizing ai prompts through test plan generation, ~50 test cases, execution, automated scoring across quantitative/qualitative/safety dimensions, and evidence-based iteration with csv-first output artifacts.
6.4
clawhub
skill-evaluation
skill-evaluation provides a systematic diagnostic pipeline for testing ai skills across five phases with structured output artifacts and pass/fail criteria, but procedure steps lack granularity and edge case handling is underdeveloped.
