Menu
Build a deterministic reproducer only after verification, and prove that it works repeatably under recorded conditions.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | crypto_solver-build |
| description | Build a deterministic reproducer only after verification, and prove that it works repeatably under recorded conditions. |
| metadata | {"short-description":"Turn a verified weakness into a reproducible solver with verification artifacts"} |
This skill packages the validated weakness into an executable reproducer. It is not the place to discover the attack. It is the place to encode an already-verified path cleanly, document its assumptions, and verify repeatability.
artifacts/out/solver_plan.jsonartifacts/out/solver_verification.jsonartifacts/logs/solve_run1.txtartifacts/logs/solve_run2.txtartifacts/scripts/Do not build or approve a solver until you can answer yes to all of these:
Pass only if the solver plan matches the verified hypothesis path and the verification artifact proves reproducible success or honestly documents the bounded non-determinism.
Enforce artifact-contract, presence, dependency, freshness, and cross-reference correctness for the artifact graph.
Reuse prior work only when hashes, dependencies, and artifact semantics still support it.
Normalize remote configuration and connection hints into machine-readable, ambiguity-aware remote artifacts.
Run a bounded, evidence-heavy cribdrag workflow for suspected keystream reuse and XOR-style leakage.
Drive decode-first problems through explicit candidate generation, convergence tests, and branch stop conditions.
Map mixed decode-plus-crypto chains into explicit stages, transitions, and evidence-backed branch routes.