recursive-decision-ledger

原文涵盖的主题

• Recursive Decision Ledger
• Ledger Contract
• Rollout Loop
• Coherence Mark
• Promotion Rules
• Summary Shape

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. 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. 1. Load the prior ledger. 2. Capture new information at time-step zero. 3. Run the bounded search. 4. Mark each candidate: accept, watch, reject, decay watch, or needs replay. 5. Compare winners against prior winners and latest marked rollout. 6. Downgrade candidates when drift, tail risk, stale data, or failed replay invalidates the previous mark. 7. Append artifacts before summarizing. Include a compact coherence mark: For trading, capital allocation, production deploys, migrations, or destructive ops, recursiv

这里只展示节选，请以完整原文和当前要求为准。