Intensive mathematical analysis for numerical stability, algorithm correctness, and alignment with authoritative standards. Triggers: math review, numerical stability, algorithm correctness, mathematical verification, scientific computing, numerical analysis, derivation check Use when: reviewing math-heavy code, verifying algorithm correctness, checking numerical stability, aligning with mathematical standards DO NOT use when: general algorithm review - use architecture-review. DO NOT use when: performance optimization - use parseltongue:python-performance. Use this skill for mathematical code verification.
/plugin marketplace add athola/claude-night-market/plugin install parseltongue@claude-night-marketThis skill inherits all available tools. When active, it can use any tool Claude has access to.
modules/derivation-verification.mdmodules/numerical-stability.mdmodules/requirements-mapping.mdmodules/testing-strategies.mdIntensive analysis ensuring numerical stability and alignment with standards.
/math-review
math-review:context-syncedmath-review:requirements-mappedmath-review:derivations-verifiedmath-review:stability-assessedmath-review:evidence-loggedpwd && git status -sb && git diff --stat origin/main..HEAD
Enumerate math-heavy files (source, tests, docs, notebooks). Classify risk: safety-critical, financial, ML fairness.
Translate requirements → mathematical invariants. Document pre/post conditions, conservation laws, bounds. Load: modules/requirements-mapping.md
Re-derive formulas using CAS. Challenge approximations. Cite authoritative standards (NASA-STD-7009, ASME VVUQ). Load: modules/derivation-verification.md
Evaluate conditioning, precision, scaling, randomness. Compare complexity. Quantify uncertainty. Load: modules/numerical-stability.md
pytest tests/math/ --benchmark
jupyter nbconvert --execute derivation.ipynb
Log deviations, recommend: Approve / Approve with actions / Block. Load: modules/testing-strategies.md
Default (200 tokens): Core workflow, checklists +Requirements (+300 tokens): Invariants, pre/post conditions, coverage analysis +Derivation (+350 tokens): CAS verification, standards, citations +Stability (+400 tokens): Numerical properties, precision, complexity +Testing (+350 tokens): Edge cases, benchmarks, reproducibility
Total with all modules: ~1600 tokens
Correctness: Formulas match spec | Edge cases handled | Units consistent | Domain enforced Stability: Condition number OK | Precision sufficient | No cancellation | Overflow prevented Verification: Derivations documented | References cited | Tests cover invariants | Benchmarks reproducible Documentation: Assumptions stated | Limitations documented | Error bounds specified | References linked
## Summary
[Brief findings]
## Context
Files | Risk classification | Standards
## Requirements Analysis
| Invariant | Verified | Evidence |
## Derivation Review
[Status and conflicts]
## Stability Analysis
Condition number | Precision | Risks
## Issues
[M1] [Title]: Location | Issue | Fix
## Recommendation
Approve / Approve with actions / Block
Build robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and transaction costs. Use when developing trading algorithms, validating strategies, or building backtesting infrastructure.