Recursive Decision Ledger

作者 affaan-mef648e01899bMIT275K 个星标收录于 2026年10月8日更新于 2026年10月8日仓库3天前更新

Run repeated rollouts ("Prime Gauss" style recursive prompting) while keeping an append-only decision ledger of trials, marks, coherence checks, and promotion gates, so recursive confidence never auto-approves live trading, deploy, or destructive actions. Use when the user asks for repeated rollouts, marked decision processes, high-dimensional search, stochastic optimization, local-optima exploration, ensemble comparison, or recursive reasoning with a visible evidence trail.

AI 生成的概览

运行重复 rollout,并以仅追加的决策台账记录试验、标记、一致性检查与晋升门禁。

功能
该技能把重复 rollout 或递归提示组织成有记录的循环:加载既有台账、采集新信息、执行有界搜索,并将每个候选标记为接受、观察、拒绝、衰减观察或需要重放。它记录 rollout 元数据,如试验次数、最佳候选、与既有台账的一致性标记以及晋升门禁结果,并建议用 JSONL 保存仅追加台账、用 Markdown 生成人类可读摘要。它还规定晋升规则,明确递归置信度不足以批准实盘交易、资金分配、生产部署、迁移或破坏性操作。
适用场景
当用户要求重复 rollout、带标记的决策流程、高维搜索、随机优化、局部最优探索、集成比较,或需要可见证据链的递归推理时使用。当循环产生的置信度可能被误当作对实盘或破坏性操作的批准时,也适用。
运行要求
不附带脚本,仅为指令。代理需要 Read、Write、Edit、Bash、Grep 和 Glob 工具来加载并追加台账产物。

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

  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.

Coherence Mark

Include a compact coherence mark:

text
Ensemble matches prior winner: trueRecursive matches prior winner: falseLatest rollout match: trueLive promotion allowed: falseReason: replay and freshness gates not satisfied

Promotion Rules

For trading, capital allocation, production deploys, migrations, or destructive ops, recursive confidence is not approval.

Default to paper, dry-run, read-only, preview, or staged mode unless the user explicitly approves the live action and the repo/service gate supports it.

Promote only when:

  • the candidate beats the prior accepted winner on the chosen metric;
  • correctness and replay checks pass;
  • risk limits are explicit;
  • the evidence is durable;
  • the user has approved the live step when needed.

Summary Shape

Lead with the decision, not the drama:

text
Rollout 15 complete. The prior winner still holds, but edge deteriorated 17%.Status: watch, not live. Next gate: 20 replay fills with fresh orderbook agebelow threshold.

来源与署名

来源:affaan-m/ecc位于skills/recursive-decision-ledger提交ef648e0

许可证: MIT

内容归原作者所有。SourceWeft 从公开仓库中收录这些内容。

举报或申请下架