Code Review

863 skills.

Browse

deslopmillioncoSimplify and refine recently modified code while preserving functionality. Use when asked to "deslop", "clean up code", "simplify code", or after making changes that could benefit from refinement.clean-architecturemindrallyGuidelines for implementing Clean Architecture patterns in Flutter and Go applications, with emphasis on separation of concerns, dependency rules, and testability.cppmindrallyGuidelines for modern C++ development with C++17/20 standards, memory safety, and performance optimization general-best-practicesmindrallyGeneral software development best practices covering code quality, testing, security, performance, and maintainability across technology stacks logging-best-practicesmindrallyLogging best practices for applications and services including structured logging, log levels, and log management strategies nodejs-developmentmindrallyNode.js development guidelines covering Payload CMS, Vue.js with TypeScript, and general TypeScript best practices hunk-reviewmodem-devInteracts with live Hunk diff review sessions via CLI. Inspects review focus, navigates files, hunks, and exact lines, reloads session contents, adds inline review comments, and paints attention marks on character ranges. Use when the user has a Hunk session running or wants to review diffs interactively.hardware-countersmohitmishra786Hardware performance counter skill for low-level CPU analysis. Use when collecting PMU events with perf stat, using the PAPI library, measuring cache miss rates and branch misprediction ratios, computing IPC, or correlating PMU events to source lines. Activates on queries about hardware counters, PMU events, perf stat -e, PAPI, cache miss rate, branch misprediction, IPC measurement, or CPU performance events.static-analysismohitmishra786Static analysis skill for C/C++ codebases. Use when hardening code quality, triaging noisy builds, running clang-tidy, cppcheck, or scan-build, interpreting check categories, suppressing false positives, or integrating static analysis into CI. Activates on queries about clang-tidy checks, cppcheck, scan-build, compile_commands.json, code hardening, or static analysis warnings.code-reviewmrgoonieUse when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing f investiguenaiersaidaneInvestiguer méthodiquement un bug en 4 phases validées : localiser/reproduire, 3 hypothèses classées sur la cause racine, logs ciblés, fix minimal. Utilise sur /investigue, ou dès que l'utilisateur décrit un symptôme (\"ça plante quand…\", \"je vois X mais j'attends Y\", \"comportement inattendu\", \"pourquoi ça crash\", \"investigue ce bug\", \"debug ça\", \"analyse le bug\"). Ne propose jamais de fix immédiat — chaque phase s'arrête et attend une validation explicite avant de passer à la suiva attach-review-to-prneolabhqAdd line-specific review comments to pull requests using GitHub CLI API kaizenneolabhqUse when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.load-pr-commentsneolabhqUse to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix.resolve-fixed-pr-commentsneolabhqVerify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.review-local-changesneolabhqReview your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, when nothing has been pushed yet.review-prneolabhqReview an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working tree.root-cause-tracingneolabhqUse when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior kotlin-concurrency-expertnew-silvermoonKotlin Coroutines review and remediation for Android. Use when asked to review concurrency usage, fix coroutine-related bugs, improve thread safety, or resolve lifecycle issues in Kotlin/Android code.feature-devnoteditGuided feature development with codebase understanding and architecture focus. Use for implementing features systematically: explore → clarify → design → implement → test → review.dotnet-csharpnovotnyllcBaseline C# skill loaded for every .NET code path. Guides language patterns (records, pattern matching, primary constructors, C# 8-15), coding standards, async/await, DI, LINQ, serialization, domain modeling, concurrency, Roslyn analyzers, globalization, native interop (P/Invoke, LibraryImport, ComWrappers), WASM interop (JSImport/JSExport), and type design. Spans 25 topics. Do not use for ASP.NET endpoint architecture, UI framework patterns, or CI/CD guidance.finding-duplicate-functionsobraUse when auditing a codebase for semantic duplication - functions that do the same thing but have different names or implementations. Especially useful for LLM-generated codebases where new functions are often created rather than reusing existing ones.Code Review ReceptionobraReceive and act on code review feedback with technical rigor, not performative agreement or blind implementation Defense-in-Depth ValidationobraValidate at every layer data passes through to make bugs impossible Requesting Code ReviewobraDispatch code-reviewer subagent to review implementation against plan or requirements before proceeding Simplification CascadesobraFind one insight that eliminates multiple components - "if this is true, we don't need X, Y, or Z Systematic DebuggingobraFour-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.lighthouseonnokhGoogle Lighthouse CLI reference for auditing web performance, accessibility, SEO, and best practices. Use this skill when users need to analyze website performance, run audits, generate reports, or integrate Lighthouse into their workflow.codegraphonsager-aiPre-indexed code knowledge graph (MCP, SQLite + tree-sitter) for faster, lower-token exploration of brownfield codebases. Use when starting work on a repo larger than ~500 files or when the task involves cross-file traversal — "where is X used", "what calls Y", "what breaks if I change Z", "trace flow from A to B", "explain this subsystem". Skip for single-file edits or sessions shorter than the cold-start cost. Triggers include "codegraph", "code graph", "index this repo", "where is X defined",code-reviewopenaiRun a final code review on a pull request netsuite-suitescript-upgradeoracleSuiteScript 1.0, 2.0, and 2.x to 2.1 migration assistant. Analyzes, converts, explains, and validates script upgrades. Covers 125+ API mappings, 34 object conversions, 13 unmapped API workarounds, all script type entry point changes, SuiteScript 2.0/2.x to 2.1 upgrade guidance, and 16 categories of breaking behavioral changes. Essential for modernizing legacy SuiteScript codebases.conformetry-validateorganizzoliniRun a conformetry conformance check and act on what it reports. Use when a conformetry-validate target fails; when a composite lint run reports conformance differences; when a report names a missing file, a missing declaration, a missing comment, an ambiguous instance, or an unmatched instance; when deciding whether to edit an instance or regenerate it; or before claiming generated code is finished. Covers both the Nx plugin and the conformetry command-line host.reviewowainlewisUses a fresh agent to review an implementation change without editing it. Checks behavior, security, regressions, complexity, tests, docs, and missing proof. Use for code, PR, diff, security, second-opinion, or pre-merge reviews.ast-grep-findparcadeiAST-based code search and refactoring via ast-grep MCP dead-codeparcadeiFind unused functions and dead code in the codebase exploreparcadeiMeta-skill for internal codebase exploration at varying depths (quick/deep/architecture)modular-codeparcadeiModular Code Organization opc-architectureparcadeiOPC Architecture Understanding qlty-checkparcadeiCode quality checks, formatting, and metrics via qlty CLI qlty-during-developmentparcadeiQLTY During Development refactorparcadeiCode refactoring workflow - analyze → plan → implement → review → validate reference-sdkparcadeiCheck reference SDK implementations using btca ask reviewparcadeiComprehensive code review workflow - parallel specialized reviews → synthesis tldr-codeparcadeiToken-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.tldr-deepparcadeiFull 5-layer analysis of a specific function. Use when debugging or deeply understanding code.validate-agentparcadeiValidation agent that validates plan tech choices against current best practices command-patternpatternsdevTeaches the command pattern for decoupling task execution from invocation. Use when you need undo/redo functionality, queued operations, or want to decouple the object that invokes an operation from the one that performs it.flyweight-patternpatternsdevTeaches the flyweight pattern for memory optimization. Use when your application creates large numbers of similar objects and memory consumption is a concern.module-patternpatternsdevTeaches the module pattern for code organization and encapsulation. Use when structuring JavaScript into reusable, maintainable pieces with clear public and private boundaries.observer-patternpatternsdevTeaches the observer pattern for event-driven communication. Use when you need decoupled publish/subscribe behavior where multiple parts of your system react to state changes or events.