agentleFS
equinorequinor/neqsim/.github/skills/neqsim-code-review/SKILL.md

neqsim-code-review

Skill167 starsChanged 7 months agoApache-2.0View on GitHub

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.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read docs/development/CODE_HEALTH.md and the relevant domain contracts.

    line 8
  2. Very specific:

    Use the exact base/head diff, changed implementations, callers and raw test evidence.

    line 9
  3. Very specific:

    Keep this review read-only.

    line 10
  4. Distinctive:

    Check API compatibility and units, state mutation/ownership, initialization, cloning, serialization, thread safety, error reporting and …

    line 14
  5. Distinctive:

    Check whether tests exercise failure/boundary cases and would catch the original defect.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.