首页/AI 智能体编排协作/recursive-decision-ledger
R

recursive-decision-ledger

by @affaan-mv
4.4(120)

此技能用于管理递归决策过程,通过记录回滚、一致性标记和晋升规则,帮助AI Agent进行反复推理和证据追踪。适用于高维搜索、随机优化、局部最优探索等需要多轮决策评估的场景。

decision-ledgerrecursive-promptsrollout-managementcoherence-checkevidence-trailGitHub
安装方式
npx skills add https://github.com/affaan-m/ecc --skill recursive-decision-ledger
compare_arrows

Before / After 效果对比

1 组
使用前

用户在没有此技能时,手动跟踪多轮决策过程,关键证据容易丢失,回滚混乱,每次决策审查平均耗时60分钟,错误率约30%。

使用后

此技能自动记录每次回滚和决策,一致性检查和晋升规则确保证据可靠,将决策审查时间缩短至10分钟,错误率降至5%。

SKILL.md

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:

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.

用户评价 (0)

发表评价

效果
易用性
文档
兼容性

暂无评价

统计数据

安装量4.1K
评分4.4 / 5.0
版本
更新日期2026年10月22日
对比案例1 组

用户评分

4.4(120)
5
37%
4
43%
3
13%
2
5%
1
2%

为此 Skill 评分

0.0

兼容平台

🤖claude-code

时间线

创建2026年7月26日
最后更新2026年10月22日
🎁 Agent 知识卡片
调研问卷