Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkillsAuthors › Confident AI

Confident AI

@confident-ai on GitHub →

3 Claude Code skills authored by Confident AI.

updated 2026-05-23 · showing 1–3 of 3 by quality score

Average Pro QualityScore: 72.0/100

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

Run local adversarial attack passes against agents, RAG pipelines, and chatbots to surface concrete failure classes before production rollout.
Run repeatable eval suites against prompts, RAG pipelines, and agents so regressions surface before release.
Use when discussing or working with DeepEval (the python AI evaluation framework)
Search all 3 skills by Confident AI →