Quality Assurance Auditor
Perform the final submission-level audit of mathematical-modeling workflow integrity...
Install
npx skills add zhnnky329/MathModeling-skills --skill quality-assurance-auditor -g -a claude-code -y- Repository
- zhnnky329/MathModeling-skills1.1k
- Category
- Engineering
- Updated
- 1mo ago
- License
- MIT
- Context cost
- Lightabout 508 tokens
- Runs scripts
- No, instructions only
What it does
Perform the final submission-level audit of mathematical-modeling workflow integrity, evidence quality, anti-fabrication, paper coherence, figures, references, and contest readiness after consistency and completeness audits pass.
Preconditions
rigor_profileissubmission.- All Qx reached G5.
- Final consistency and completeness audits exist.
Audit Dimensions
-
Workflow integrity
- G1, G5 passed per Qx.
- Human judgments trace to the decision ledger.
- Main/baseline/fallback execution respected approved scope.
-
Evidence integrity
- No fabricated data, references, experiments, metrics, or figures.
- Main claims trace to frozen numbers and robustness evidence.
- Limitations and uncertainty are visible.
-
Method quality
- Baseline is usable.
- Assumptions, units, objectives, constraints, and solution steps are coherent.
- Output concentration/degeneracy and failure triggers were addressed.
-
Paper quality
- Problem, method, results, and conclusions align.
- Claims are proportional to tested comparisons.
- Human-owned physical meaning and contribution are present.
-
Presentation
- Required figures/tables exist and passed render checks.
- Figure types are used correctly.
- References are real, complete, and consistently cited.
- AI-use disclosure follows the current contest profile and verified rules.
Workflow
- Read the two earlier audits and unresolved blockers.
- Sample canonical sources directly; do not trust summaries alone.
- Record blocking and nonblocking findings with artifact paths and repair owners.
- Save
paper/qa_report.md. - Set verdict:
PASSEDFAILEDNOT_RUN
Rules
- Do not approve on partial audits.
- Do not use artifact count or bullet count as a proxy for quality.
- Do not repair issues inside QA.
- Do not hide uncertainty or downgrade a blocker silently.
- Do not claim compliance with time-varying contest rules without verification.
