Recursive Decision Ledger

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.

skills.sh installs: 5.3K
GitHub stars: 300.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/ecc --skill recursive-decision-ledger --agent claude-code

Installs into .claude/skills of the current project.

Files

Recursive Decision Ledger

Use this skill when the user is trying to force deeper computation through repeated rollouts or "Prime Gauss" style recursive prompting. Preserve the useful part: repeated trials, prior memory, fresh information, and explicit marks. Remove the unsafe part: pretending the loop proves certainty.

Ledger Contract

Every rollout should record:

rollout id and timestamp;
prior accepted winner and prior watchlist;
fresh information ingested;
search space size;
model families or heuristics used;
trial count and effective trial count;
top candidates;
decision marks;
coherence marks against the prior ledger;
promotion gate result.

Prefer JSONL for append-only ledgers and Markdown for human summaries.

Rollout Loop

Load the prior ledger.
Capture new information at time-step zero.
Run the bounded search.
Mark each candidate: accept, watch, reject, decay watch, or needs replay.
Compare winners against prior winners and latest marked rollout.
Downgrade candidates when drift, tail risk, stale data, or failed replay invalidates the previous mark.
Append artifacts before summarizing.