Results for “correctness”

Standard reviewer for correctness and reproducibility. Use when the user asks to talk to Omen, requests a code review, or needs reproducibility verification.

Delivers measurement-driven performance optimization for latency, throughput, memory, and tail behavior, with correctness preservation and regression guards.

Validates custom dotnet new templates for correctness before publishing, catching missing fields, parameter bugs, shortName conflicts, constraint issues, and common authoring mistakes.

Reviews pull request diffs for correctness, security, maintainability, and test coverage, providing severity-ranked findings and a close-out recommendation.

Reviews MATLAB fixed-point (fi) code for performance, code generation efficiency, and correctness. Identifies antipatterns and suggests idiomatic improvements. Use when reviewing fi, fimath, numerictype, or quantizenumeric code.

Conducts multi-axis code review across correctness, readability, architecture, security, and performance before merging any change.

SSOT（Single Source of Truth）と実際のファイル/設定の整合性をチェックし、乖離があれば修正するスキル。 「SSOTチェックして」「SSOT整合性チェックして」「SSOT整理して」「SSOTのズレを直して」 「00_SYSTEM更新して」「乖離を修正して」と言った時にトリガーする。 /ssot-check でも呼び出せる。

Enforces a principal-engineer self-review checklist on every code block before output, covering correctness, performance, security, naming, and testability.

Update or correct an existing skill file based on judge feedback or improved understanding.

Rehearse

Reviews CUDA, OpenMP, and OpenCL code for parallel correctness, covering data races, memory model violations, synchronization bugs, numerical precision issues, and API-specific pitfalls.

Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.

Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing.

When reviewing code, generate the complete corrected version — not just the issues, but the exact fixed code ready to copy-paste.

Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing.

Verify code changes work by running them. Proves through execution, not just inspection.

Execute self-learning system that captures corrections during sessions and syncs them to CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something. Trigger with phrases like "remember this", "don't forget", "use X not Y", or "actually...".

Strengthen interfaces against edge cases, errors, internationalization issues, and real-world usage scenarios that break idealized designs.

Verify that a change really works before you claim completion

Generate comprehensive checklists to validate requirements quality (Unit Tests for Specs). Critically examine the spec for clarity, completeness, and consistency before implementation starts.

LLaVA-NeXT: Improved Reasoning, OCR, and World Knowledge

Reconcile canonical declarative documents under docs/ with verified implementation discoveries after a FULLY_IMPLEMENTED moonspec-verify verdict. Use when an orchestration run must decide whether verified discoveries show the owning canonical document is impossible, unclear, or inconsistent, apply the smallest correct doc update, or escalate ambiguous authority conflicts and deliberate divergences instead of editing.

Formally verify programs by writing Lean 4 proofs. Trigger this skill whenever the user wants to formally verify code, generate Lean 4 proofs, prove properties about algorithms or smart contracts, verify invariants, convert program logic into formal specifications, or anything involving Lean 4 and formal verification. Also trigger when the user mentions "qedgen", "lean proof", "formal proof", "verify my code", "prove correctness", "formal verification", or wants mathematical guarantees about their implementation.

Strengthen interfaces against edge cases, errors, internationalization issues, and real-world usage scenarios that break idealized designs.

Identify grammar, logical, and flow errors in text and suggest targeted fixes without rewriting the entire text. Use when proofreading content, checking writing quality, or reviewing a draft.

xUnit.net testing framework with Fact, Theory, fixtures, DI, and mocking with Moq and NSubstitute. Covers .NET testing best practices. USE WHEN: user mentions "xUnit", ".NET testing", "Fact", "Theory", "InlineData", "Moq", "NSubstitute", "C# unit test" DO NOT USE FOR: NUnit - use `nunit`, Vitest - use `vitest`, Jest - use `jest`, Playwright - use `playwright`

Autonomously repairs failed task verification by choosing retry, decompose, prune, or escalate strategies before surfacing to the user.

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md. Identifying inconsistencies, duplications, ambiguities, and underspecified items.

Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.

Detect and fix code-quality and correctness issues in AEM as a Cloud Service projects locally, without external services or network calls.