recursive-decision-ledger
Tracks systematic decision-making and search rollouts, keeping a visible audit trail of trials, winners, and logic for reproducibility.
Install
mkdir -p .claude/skills/recursive-decision-ledger && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15351" && unzip -o skill.zip -d .claude/skills/recursive-decision-ledger && rm skill.zipInstalls to .claude/skills/recursive-decision-ledger
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
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.Key capabilities
- →Record rollout IDs and timestamps
- →Capture fresh information ingested
- →Track search space size and model heuristics
- →Mark candidates as accept, watch, reject, decay watch, or needs replay
- →Compare winners against prior winners
- →Append artifacts before summarizing
How it works
This skill records detailed information for each rollout in a ledger, including fresh data, search parameters, candidate marks, and coherence checks, to manage recursive decision processes.
Inputs & outputs
When to use recursive-decision-ledger
- →Running repeated search rollouts
- →Managing recursive optimization tasks
- →Tracking ensemble decisions
About this skill
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.
When not to use it
- →When the user is not asking for repeated rollouts or high-dimensional search
- →When the goal is to prove certainty through recursive prompting
- →When the task does not require a visible evidence trail
Limitations
- →The skill requires recording specific ledger contract items for each rollout
- →The skill does not approve live actions based on recursive confidence alone
- →The skill focuses on managing decision processes, not executing them
How it compares
This skill formalizes recursive decision-making with a structured ledger and explicit coherence marks, providing an auditable trail that differs from informal iterative processes.
Compared to similar skills
recursive-decision-ledger side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| recursive-decision-ledger (this skill) | 0 | 2mo | No flags | Advanced |
| docetl | 2 | 2mo | Review | Intermediate |
| slm-lab-benchmark | 1 | 5mo | Review | Advanced |
| document-classification | 0 | 2mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by yashas-30
View all by yashas-30 →You might also like
docetl
ucbepic
Build and run LLM-powered data processing pipelines with DocETL. Use when users say "docetl", want to analyze unstructured data, process documents, extract information, or run ETL tasks on text. Helps with data collection, pipeline creation, execution, and optimization.
slm-lab-benchmark
kengz
Run SLM-Lab deep RL benchmarks, monitor dstack jobs, extract results, and update BENCHMARKS.md. Use when asked to run benchmarks, check run status, extract scores, update benchmark tables, or generate plots.
document-classification
leviadi-lang
Use when working on document classification — `classify_document` tool, OCR pipeline, document type taxonomy for insurance/pension documents.
tss-pipeline
LocNguyen-247
Use when implementing or debugging the TSS remote-sensing workflow in this workspace: Landsat/Sentinel preprocessing, ACOLITE atmospheric correction, cloud/water masking, adjacency correction, station matchup, and model training.
reasoning-judge
kamaz66137-byte
推理判断技能:二分类判断、多分类判断、阈值判定、置信度评估、异常检测、排序判断。触发场景:当用户提到"判断"、"分类"、"是否"、"评估"、"异常"、"judge"、"classify"、"threshold"、"confidence"、"anomaly"时加载。
image-analysis
ComeOnOliver
图片分析与识别,可分析本地图片、网络图片、视频、文件。适用于 OCR、物体识别、场景理解等。当用户发送图片或要求分析图片时必须使用此技能。