Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. A secondary Codex agent evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
Install
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill result-to-claimnpx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill result-to-claim -a claude-code -gnpx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill result-to-claim -a codex -ggemini skills install https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git --path skills/skills-codex/result-to-claimgh skill install wanshuiyin/Auto-claude-code-research-in-sleep result-to-claimgit clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep /tmp/wanshuiyin__Auto-claude-code-research-in-sleep
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/wanshuiyin__Auto-claude-code-research-in-sleep/skills/skills-codex/result-to-claim ~/.claude/skills/result-to-claim # Claude Code
cp -R /tmp/wanshuiyin__Auto-claude-code-research-in-sleep/skills/skills-codex/result-to-claim ~/.agents/skills/result-to-claim # Codex, Cursor, Gemini CLI, Copilot, OpenCode