Skip to main content

neqsim-code-review

Independently review NeqSim source-code changes for correctness, maintainability, API compatibility, numerical stability, state ownership and performance. Use for code PR review and refactoring acceptance; engineering report review remains separate.

Source facts

Repository
equinor/neqsim
Last source activity
November 7, 2026 at 11:21
Detected SKILL.md language
English
Stars
168
Forks
78

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

Showing SKILL.md

SKILL.md
Source instructions · Read-only preview
name
neqsim-code-review
description
Independently review NeqSim source-code changes for correctness, maintainability, API compatibility, numerical stability, state ownership and performance. Use for code PR review and refactoring acceptance; engineering report review remains separate.
# Review the source change Read `docs/development/CODE_HEALTH.md` and the relevant domain contracts. Use the exact base/head diff, changed implementations, callers and raw test evidence. Keep this review read-only. This role reviews source; `@review` reviews task deliverables. 1. Derive the intended behavior from the task and current contracts, independently of the author's explanation. Inspect the implementation before accepting a claimed pass. 2. Check API compatibility and units, state mutation/ownership, initialization, cloning, serialization, thread safety, error reporting and extension-hook dispatch. 3. Check whether tests exercise failure/boundary cases and would catch the original defect. Flag assertions copied from new outputs without an independent basis. 4. For numerical paths inspect conservation, equilibrium, finite values, derivative consistency, convergence and valid operating ranges. Require representative paired performance evidence for hot-path changes; a faster isolated case is insufficient. 5. Inspect baseline changes, suppressed diagnostics, removed assertions and changed tolerances. Distinguish a tool/configuration failure from a source defect. 6. Confirm documentation and executable examples agree with the implementation. Separate measured checks from unrun CI, and qualification from source discovery. Report concrete findings with severity, file/location, trigger, impact and a reproducible check where possible. Give a concise verdict and residual uncertainty. Do not invent findings to fill a quota. Hand required changes to `@refactor` with `neqsim-safe-refactoring`, or new investigation to `@code-health` with `neqsim-code-health`. Never approve a change by accepting the author's self-review alone.
View on GitHub