Coding & Dev Tools

Modernize deprecated MATLAB functions and patterns. Use when check_matlab_code or checkcode reports "not recommended" or "to be removed" warnings, when migrating legacy code, or when replacing deprecated APIs (trainNetwork, csvread, xlsread, datenum, eval, subplot, guide, optimset, wavread, svmtrain, uicontrol) with current equivalents.

Generate and maintain llms.txt files for AI discoverability. Scans repos to create curated content maps that help AI answer engines surface your project accurately. Implements the llms.txt specification from Answer.AI.

Manage public/private repository pairs. Verify parity, detect drift, run sync scripts, and validate no sensitive data leaks to the public repo. Use for projects that maintain separate dev and public repositories.

Generate changelog entries and GitHub releases from git history. Categorizes commits into features, fixes, breaking changes, and docs. Supports conventional commits, PR-based grouping, and semantic versioning. Creates formatted CHANGELOG.md entries and GitHub releases.

A/B and multivariate testing methodology. Design experiments, calculate sample sizes, determine statistical significance, avoid common pitfalls, and interpret results. Platform-agnostic framework applicable to landing pages, emails, ads, pricing, and product features. Use when the user asks about A/B testing, split testing, experiment design, statistical significance, or conversion experiments.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Configure PHP ecosystem tooling, dependency management, and static analysis. Use when managing Composer dependencies, running PHPStan, or configuring PHP build tools.

Guides quality-first TDD for new behavior, bug fixes, and test changes. Selects the smallest test layer, proves a distinct regression risk, and runs bounded RED-GREEN-REFACTOR verification.

Dart static analysis, linting, formatting, and code-generation standards. Use only for analysis_options.yaml, build_runner, dart format, DCM, lefthook, or analyze/format CI failures; defer Dart language, null-safety, Flutter tests, and generic CI questions.

Run an AI-assisted PR code review using multi-layer lenses with confidence scoring.

Configure Hilt dependency injection with proper scoping, modules, and constructor injection in Android. Use when changing the production Hilt graph; defer test overrides, Room wiring, navigation-specific scopes, and generic DI explanations to their specific skills.

SwiftUI navigation and deep linking using NavigationStack and Universal Links. Use when implementing NavigationStack or Universal Links deep linking in iOS.

Modern Java 21+ language standards including Records, Pattern Matching, and Virtual Threads. Use for Java language constructs or Java-to-Java upgrades; defer Kotlin, tests, formatting/build tools, CompletableFuture, builder patterns, and isolated null-handling questions.

Implement Angular SSR with hydration, TransferState caching, and per-route render modes. Use when configuring Angular Universal SSR, client hydration, static prerendering, or preventing double-fetching.

Profile and optimize iOS apps with Instruments, memory management, and rendering techniques. Use when profiling iOS apps with Instruments or optimizing memory and rendering.

Implement concurrency and non-blocking I/O in modern PHP. Use when implementing concurrent requests, async processing, or non-blocking I/O in PHP.

Configure SPM packages, SwiftLint, and build settings for Swift projects. Use when managing Swift packages with SPM, configuring build settings, or enforcing Swift code quality.

Draft user-facing release notes, store changelogs, and internal publish summaries.

Apply MVVM, Coordinators, and Clean Architecture (VIP/VIPER) in iOS apps. Use when applying MVVM, Coordinators, or VIP/VIPER architecture in iOS apps.

Implement String Catalogs, L10n workflows, and asset management for iOS. Use when adding multi-language support using iOS String Catalogs or L10n workflows.

Implement BullMQ job workflows in NestJS. Use when building queue processors, redis-throttler, Upstash limits, idle polling, stalled jobs, and retention policies.

Apply Optionals, Protocols, Extensions, and Type Safety patterns in Swift. Use when working with Swift Optionals, Protocols, Extensions, or type-safe APIs.

Build typed reactive forms with strict FormGroup typing, custom validators, and nonNullable controls in Angular. Use when implementing typed reactive forms, custom validators, or form control patterns.

Standards for structured logging and observability in Golang. Use when adding structured logging or tracing to Go services.

Write unit tests with table-driven patterns and interface mocking in Go. Use when writing Go unit tests, table-driven tests, or using mock interfaces.

Push notifications for iOS using UserNotifications framework and APNS. Use when integrating APNS push notifications in iOS applications.

Implement UIKit navigation, Auto Layout, and Apple Human Interface Guidelines in iOS. Use when implementing UIKit navigation, Auto Layout constraints, or HIG compliance.

Implement multi-level caching, invalidation patterns, and stampede protection in NestJS. Use when adding Redis caching layers, configuring cache-manager interceptors, implementing stale-while-revalidate, or preventing cache stampedes in NestJS services.

Write Unit and E2E tests with Jest, mocking strategies, and database isolation in NestJS. Use when writing NestJS unit tests, E2E tests with supertest, or mock providers.

Test Python services with pytest, async coverage, monkeypatch, and boundary-focused fakes. Use when writing Python tests, fixtures, async tests, regression tests, or dependency-isolated verification.

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system knowledge document, or both.

Core idioms, style guides, and best practices for writing idiomatic Go code. Use when writing Go code following official style guides and idiomatic patterns.

Write PHP following PSR coding standards, SOLID principles, and code-quality guidelines. Use for PHP style, design, refactoring, naming, and guard clauses—not Composer/PSR-4 project configuration.

Perform an HTTP GET request and return the response body

Retrieve a value by key from the Custodian KV store