Analyze a finished coder-eval run and write analysis.md — cluster failures into systemic patterns and recommend fixes. Use when the user wants to know why a run failed, what regressed or got worse since a previous run, what to fix, or what a run says about their tasks.
Install
npx skills add UiPath/coder_eval --skill analyzenpx skills add UiPath/coder_eval --skill analyze -a claude-code -gnpx skills add UiPath/coder_eval --skill analyze -a codex -ggemini skills install https://github.com/UiPath/coder_eval.git --path plugins/coder-eval/skills/analyzegh skill install UiPath/coder_eval analyzegit clone --depth 1 https://github.com/UiPath/coder_eval /tmp/UiPath__coder_eval
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/UiPath__coder_eval/plugins/coder-eval/skills/analyze ~/.claude/skills/analyze # Claude Code
cp -R /tmp/UiPath__coder_eval/plugins/coder-eval/skills/analyze ~/.agents/skills/analyze # Codex, Cursor, Gemini CLI, Copilot, OpenCode