Strip AI-slop patterns from reasoning traces (chain-of-thought, extended thinking, agent decomposition) — not final prose. Reasoning text has its own slop catalog that regular unslop doesn't target: over-explaining the question, over-hedging, over-decomposing trivial problems into 6-bullet substeps, infinite-loop rationalization.
Install
npx skills add MohamedAbdallah-14/unslop --skill unslop-reasoningnpx skills add MohamedAbdallah-14/unslop --skill unslop-reasoning -a claude-code -gnpx skills add MohamedAbdallah-14/unslop --skill unslop-reasoning -a codex -ggemini skills install https://github.com/MohamedAbdallah-14/unslop.git --path skills/unslop-reasoninggh skill install MohamedAbdallah-14/unslop unslop-reasoninggit clone --depth 1 https://github.com/MohamedAbdallah-14/unslop /tmp/MohamedAbdallah-14__unslop
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/MohamedAbdallah-14__unslop/skills/unslop-reasoning ~/.claude/skills/unslop-reasoning # Claude Code
cp -R /tmp/MohamedAbdallah-14__unslop/skills/unslop-reasoning ~/.agents/skills/unslop-reasoning # Codex, Cursor, Gemini CLI, Copilot, OpenCode