Catalog
affaan-m/recursive-decision-ledger

affaan-m

recursive-decision-ledger

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.

global
0installs0uses~603
v1.0Saved May 25, 2026

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.
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

78/100

Grade

B

Good

Safety

85

Quality

75

Clarity

78

Completeness

70

Summary

This skill guides agents to implement a recursive decision-making process with a durable, auditable ledger. It structures repeated search rollouts (optimization, ensemble comparison, or stochastic exploration) while preserving prior winners, decision marks, and coherence checks. The skill emphasizes safety guardrails: paper/dry-run defaults, explicit replay gates, and risk limits before live actions.

Detected Capabilities

read ledger fileswrite decision artifacts (JSONL/Markdown)bash execution for bounded searchgrep for prior state lookupedit decision records

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

recursive rollout optimizationdecision ledger auditensemble ranking comparisonstaged deployment gaterepeated trial tracking

Use Cases

  • Optimize high-dimensional search problems with repeated trials and evidence tracking
  • Compare ensemble model outputs and track confidence across rollouts
  • Implement staged deployment decisions with decision audit trails
  • Explore local optima while maintaining explicit promotion criteria
  • Build capital allocation or trading decisions with durable ledger proof

Quality Notes

  • Excellent safety-first framing: explicitly warns against treating recursive confidence as proof, defaults to paper/dry-run modes
  • Clear contract structure: ledger schema is explicit and reproducible (rollout id, timestamp, marks, coherence check)
  • Well-documented promotion rules with concrete guard conditions (replay checks, risk limits, user approval required)
  • Strong emphasis on durable evidence trails and coherence marks enables auditability and prevents drifting decisions
  • Good practical guidance on summary shape — lead with decision, not narrative
  • Limitation: no worked example walkthrough showing a complete ledger artifact or multi-rollout scenario
  • Minor: 'Prime Gauss' reference is unexplained; context for when recursive prompting is useful could be clearer
Model: claude-haiku-4-5-20251001Analyzed: May 25, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Add affaan-m/recursive-decision-ledger to your library

Command Palette

Search for a command to run...