scientific-rust-numerical-correctness-review
Review a scientific Rust plan or implementation for numerical correctness, reference validity, floating-point failure paths and reproducible scientific evidence; read-only by default.
- License 许可
- MIT
- 最近更新
- 2026-10-30
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- scientific-rust-numerical-correctness-review
- description
- Review a scientific Rust plan or implementation for numerical correctness, reference validity, floating-point failure paths and reproducible scientific evidence; read-only by default.
03 SKILL.md 正文
Use the canonical shared review procedure and report fields; resolve its review skill through native discovery rather than duplicating it. Select this activated pack's scientific-rust-numerical-methods-engineer profile. Read numerical correctness and relevant research provenance. If the shared workflow is unavailable, report that limitation before presenting a partial numerical assessment.
Establish target, intended baseline, scientific requirements and acceptance tolerances. Follow units, dimensions, discretization, stopping criteria, precision conversions and caller error handling through actual code. Inspect comparator nonfinite/shape behavior, cancellation, near-zero cases, overflow, reduction order and debug/optimized differences as relevant. Examine reference independence and whether tests distinguish the intended method from realistic wrong alternatives.
Separate confirmed implementation defects from hypotheses and from scientific model-validation questions. Cite evidence, a concrete failing scenario, correction and regression test with severity/confidence. Do not claim mathematical/physical validity from compilation, a passing test suite or conserved quantity alone. Zero findings is valid. Do not edit files, regenerate reference data, execute expensive experiments without authorization, weaken tolerances or waive required checks. Report missing expert/reference evidence and local versus integrated verification accurately.
04 同仓库更多 Skills
example-review
Review synthetic example changes for their stated acceptance criteria.
second-reader
Independent second reader for supply-chain and data documents (RFQs, supplier quotes, emails, PDFs including scanned, spreadsheets, CSV/JSON). Extracts values with source evidence, runs deterministic checks, compares quotes against an RFQ and a bid price, and briefs the human on what they may have missed while they review the same material. Every step is logged in a SQLite ledger.
second-reader-offline
The no-AI, no-network variant of second-reader for confidential client documents. Reads with local rules and OCR, checks and compares with code, and produces a self-contained HTML report on the user's own machine. The assistant must not read the documents or the report.
review
Review an engineering plan, diff, code or architecture from a general or selected professional perspective, challenging assumptions with evidence and no automatic implementation edits.
review-diff
Compatibility entry point for evidence-based diff review; establish the intended baseline and inspect consequential changes read-only.
plan-feature
Plan a new subsystem, cross-cutting feature, migration or explicitly requested design before implementation. Routine local edits can proceed directly.