recursive-decision-ledger
GitHub用于处理重复推演、递归推理及高维搜索的技能。通过维护结构化决策账本，记录每次试验的候选项、证据链及一致性标记。旨在支持深度计算与随机优化，同时强制实施风险控制，确保在交易或部署等场景下仅在有充分证据和用户批准时才推进操作。
Trigger Scenarios
Install
npx skills add NeverSight/learn-skills.dev --skill recursive-decision-ledger -g -y
SKILL.md
Frontmatter
{
"name": "recursive-decision-ledger",
"tools": "Read, Write, Edit, Bash, Grep, Glob",
"origin": "ECC",
"description": "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."
}
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.
Coherence Mark
Include a compact coherence mark:
Ensemble matches prior winner: true
Recursive matches prior winner: false
Latest rollout match: true
Live promotion allowed: false
Reason: 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:
Rollout 15 complete. The prior winner still holds, but edge deteriorated 17%.
Status: watch, not live. Next gate: 20 replay fills with fresh orderbook age
below threshold.
Version History
- e0220ca Current 2026-07-05 23:48
