| name | audit-modeling-evidence |
| description | Audit existing mathematical-modeling data, backend ownership, experiments, innovation claims, results, constraints, reproducibility, and claim-to-evidence links. Use when the primary request is to check or validate an existing modeling project rather than solve a complete new problem. |
Audit Modeling Evidence
Audit without silently repairing, rerunning, or promoting unsupported claims. Return the smallest defensible repair and a clear status: pass, warn, failed, or blocked.
Workflow
- Identify source-of-truth files, active subquestions, evidence/data mode, ambition, workflow stage, result status, and audit scope.
- Select only applicable lanes: intake/data; backend; method/experiment; candidate validation; simulator/decision trace; innovation/readiness; frozen evidence/manuscript.
- Resolve
SKILL_ROOT as this Skill directory and invoke scripts by absolute quoted path.
- Run the smallest deterministic check first. Preserve input hashes, commands, environment, and artifact paths.
- Distinguish observed, inferred, diagnostic-only, validated, frozen, and out-of-scope evidence. Rewriting a claim cannot turn failed evidence into a pass.
- Report each issue with file, field/row, observed condition, required condition, affected downstream artifacts, and smallest repair.
Script routing
- Data/leakage:
scripts/audit_dataset.py.
- MATLAB capability and numerical ownership:
scripts/audit_backend_contract.py.
- Experiment budgets/runs:
scripts/register_experiment.py, scripts/run_experiment.py.
- Candidate evidence/promotion:
scripts/audit_candidate_evidence.py, scripts/promote_validated_candidate.py.
