Suede AI eval design and coverage audit: AI-SPEC, failure-mode rubric with severity scoring, concrete pass/fail eval cases, coverage and infrastructure scores, and mechanical acceptance gates. Use when a change ships LLM, RAG, agent, classifier, prompt, or generated-media behavior, or when asked to write evals for an AI feature, design test cases for a model surface, audit existing eval…
Install
npx skills add JasonColapietro/suede-creator-skills --skill suede-ai-evalnpx skills add JasonColapietro/suede-creator-skills --skill suede-ai-eval -a claude-code -gnpx skills add JasonColapietro/suede-creator-skills --skill suede-ai-eval -a codex -ggemini skills install https://github.com/JasonColapietro/suede-creator-skills.git --path skills/suede-ai-evalgh skill install JasonColapietro/suede-creator-skills suede-ai-evalgit clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills /tmp/JasonColapietro__suede-creator-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/JasonColapietro__suede-creator-skills/skills/suede-ai-eval ~/.claude/skills/suede-ai-eval # Claude Code
cp -R /tmp/JasonColapietro__suede-creator-skills/skills/suede-ai-eval ~/.agents/skills/suede-ai-eval # Codex, Cursor, Gemini CLI, Copilot, OpenCode