When you need to run Monte Carlo searches, ensemble methods, or any recursive optimization loop where you're tempted to spin up dozens of trials and pick a winner, this skill forces you to write down what you did. Every rollout logs its timestamp, search space, trial count, top candidates, and a coherence check against the prior winner. The ledger structure keeps you honest about drift and prevents you from promoting a candidate to production just because the latest run looked good. Built for trading strategies, capital allocation, or any high-stakes decision where recursive confidence shouldn't be confused with actual approval. Default stance is paper mode until explicit promotion gates pass.
npx -y skills add affaan-m/ecc --skill recursive-decision-ledger --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
mattpocock/skills