$ loading_
Run recursive decision rollouts with visible evidence trails and option comparisons.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "recursive-decision-ledger" skill from askskill: 1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/recursive-decision-ledger/SKILL.md 2. Save it as ~/.claude/skills/recursive-decision-ledger/SKILL.md 3. Reload skills and tell me it's ready
Use a recursive decision ledger to compare three strategies: price discount, launch a premium tier, or keep things unchanged. In each round, label assumptions, evidence, risks, and next steps, run 3 rollout rounds, and end with a recommendation and rationale.
A round-by-round comparison with evidence trails, risk analysis, and a final recommendation.
For improving landing page conversion, generate 5 different optimization paths and, with a visible decision trail, reason through where each may get stuck in a local optimum, how to escape it, and the expected upside. Summarize the results in a comparison table.
Multiple rollout paths, local-optimum analysis, and a structured comparison table.
I have 4 candidate research directions. Perform randomized multi-round evaluation and ensemble comparison. For each option, record the basis for judgment, key uncertainties, and possible biases, then provide an overall ranking and validation suggestions.
An evidence-backed evaluation with rankings and suggested validation steps.
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.
Every rollout should record:
Prefer JSONL for append-only ledgers and Markdown for human summaries.
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
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:
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.
Run repo tasks, debug CI, and deliver fixes with verified evidence.
Organize inboxes, draft emails, verify sending, and follow up safely.
Run a pre-release verification loop for Quarkus builds, tests, scans, and reviews.
Speed up complex tasks with parallel execution while preserving correctness.
Learn practical Kotlin Ktor server patterns for building and testing backend apps.
Learn idiomatic Go patterns and best practices for robust, maintainable applications.
Log and retrieve decisions with provenance, supersession, and audit trails.
Gather independent multi-model plans and debates for implementation and architecture decisions.
Refine retrieved context iteratively to improve subagent understanding and output quality.
Search across connected sources to quickly recover decisions, docs, and discussions.
Lets AI check a team's decision ledger before acting on past decisions.
Verify decisions in a local MCP flow and execute only when allowed.