Review code for proper DI patterns using DryIoc. Ensures no static singletons, validates constructor injection and service lifetimes.
Manage deprecation and migration of old systems, APIs, or features. Use when removing legacy code, sunsetting features, consolidating duplicate implementations, or planning the…
Remove historical cruft from design docs. Use when docs accumulate outdated content, after major refactorings, or when preparing for releases.
Use when Java design, refactoring, or implementation tradeoffs should be evaluated with Kent Beck's simple design rules, including passes the tests, reveals intention, has no…
Verify code implementation aligns with design specifications. Use after implementing features, during code reviews, or when refactoring to ensure architectural compliance.
Use when a complex or risky code change should be split into Kent Beck's two-step method by first making the change easy through behavior-preserving preparatory refactoring, then…
Guides designing, reviewing, and refactoring modules for depth — maximizing functionality hidden behind minimal interfaces.
Use when reviewing uncommitted or staged git changes before commit. Trigger on: 帮我 commit, 我要 commit, commit 一下, 准备提交, pre-commit, 提交前检查, 看下这次修改, commit 前看一下, I want to commit,…
Revue de code structurée avec détection de bugs, suggestions d'amélioration et bonnes pratiques. À utiliser quand l'utilisateur colle du code et demande un avis, une revue ou des…
Use proactively before writing any code, fixing bugs, designing features, refactoring, or making any code changes in nekonote. Must be invoked before implementation begins.
[WHAT] บังคับ TDD cycle (red → green → refactor) + quality gate (format/lint/type/complexity/naming/test/doc) ก่อน hand-off production code.
Delegate code tasks to OpenAI Codex CLI using markdown file handoff pattern. Write instructions to TASK.md, Codex reads and executes, outputs to OUTPUT.md.
Default development lead for the AIM monorepo. Orchestrates agent teams for any development task — feature implementation, bug fixes, refactoring, and cross-system changes.
Pre-wrap quality gate. Runs /simplify on the working-tree diff, re-runs commands.test, and reports results. Suggests /code-review:code-review when installed.
Analyzes codebase against standards and generates refactoring tasks for ring:dev-cycle.
Refactor safely without changing behavior - small steps behind a test net Use when the user explicitly invokes $dev-refactor-code or asks for this dev refactor-code workflow.
AUTO-ACTIVATE when working in flow-state-refactor worktree or refactoring large components. MANDATORY port 5550 for refactor worktree.
AUTO-ACTIVATE when working in flow-state-refactor worktree or refactoring large components. MANDATORY port 5550 for refactor worktree.
Use when a Rust source change must be implemented, ported, or refactored across APIs, crates, services, CLIs, async, persistence, unsafe or FFI boundaries, tests, or docs; owns…
Review and audit code quality, architecture, and implementation. Verify code meets design specs, find bugs, identify improvements, and create change/bug/improve backlogs.
Developer tools for The Fold - protocols (extensible dispatch), protocol bundles, refactoring toolkit (rename, move, dead code), and template DSL.
General principles for exploring, developing, editing, and refactoring code. Use for codebase analysis, implementation tasks, and code quality improvements.
Review pull requests or audit repositories for correctness, security, performance, test risk, architecture, dependencies, developer experience, documentation, and grounded product…
Use when implementing, debugging, refactoring, or reviewing code — enforces the think → analyze → verify → execute workflow — even when the user just says 'implement X' without…
Hands-free pipeline for any coding task — bug fix, feature, refactor, debug, modify, PR review. Free-form goal or formal spec input.
Compares two tables or query results and diagnoses exactly how they differ — row counts, key set differences, per-column value mismatches — for migration and refactor validation.
Compare two implementations of the same thing — a port (R↔Python↔Stata), a reimplementation, a replication package, a refactor, or a new version against the old — so that…
Audit Python classes and OOP code for structural anti-patterns, naming inconsistencies, and data modeling issues.
Use when user describes a business requirement spanning 2+ domains. TRIGGER when: requirement involves 2+ domain keywords defined in project CLAUDE.md routing table, user asks…
Execute TDD implementation from task list following RED-GREEN-REFACTOR cycle with mandatory tests, stub detection, and quality gates.
Identify, quantify, and prioritize technical debt in the codebase. Activate when user mentions "tech debt", "code quality", "technical debt", "code smells", "refactor candidates",…
Use whenever a rewrite, redesign, or refactor would remove, replace, or overwrite copy or visuals that are already in place — a tuned headline, a converting landing page, a hero,…
Conventions for writing or editing bash CLI scripts in ~/dotfiles/bin/ — argument parsing, validation, error format, file structure.
Use a repo-root `.editorconfig` to configure free .NET analyzer and style rules. Use when a .NET repo needs rule severity, code-style options, section layout, or analyzer…
Review .NET changes for bugs, regressions, architectural drift, missing tests, incorrect async or disposal behavior, and platform-specific pitfalls before you approve or merge…
Use free built-in .NET maintainability analyzers and code metrics configuration to find overly complex methods and coupled code.
Use the open-source free `QuickDup` clone detector for .NET repositories. Use when a repo needs duplicate C# code discovery, structural clone detection, DRY refactoring…
Use when reviewing PRs/diffs/branches/documents for .NET quality, correctness, performance, security, data access, messaging, and observability.
Use when you need CRAP score and coverage risk analysis to find high-risk code before refactoring or release.
Don't Repeat Yourself (DRY) and Never Reinvent the Wheel (NRtW) - core b00t principles. Use existing libraries, leverage Rust via PyO3 instead of duplicating logic in Python, and…
Use when user asks to "remove duplicates", "DRY up code", "extract common logic", "consolidate repeated code", or when /dry scan finds duplicates.
Guides systematic code refactoring following the DRY (Don't Repeat Yourself) principle. Use when user asks to eliminate code duplication, refactor repetitive code, apply DRY…
Use when reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality gates)…
Orchestrate a parallel multi-agent build with mandatory cross-review across Claude and Codex. Splits a multi-component coding task into ~equal Claude and Codex subtasks, runs them…
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and — from…
Third-party Claude Code token/context/code-review tools. Use when choosing or recommending an external tool to reduce token usage, manage context, or review large codebases…
Use when analyzing the Reactive Agents codebase for architectural improvements, abstraction opportunities, composability gaps, or Effect-TS engineering quality — before proposing…
Use when explaining, debugging, refactoring, or teaching Effect-TS and functional TypeScript.
Analyzes and refactors Go code using Effective Go principles. Use when refactoring Go code, identifying anti-patterns, improving Go idioms, or applying Go best practices.
Use BEFORE generating, refactoring, reviewing, or debugging code. Trigger phrases include "write a function/script/class for X", "review this code/diff/PR", "refactor this",…
Index a codebase's structure (folders, files, symbols) into Browzer's workspace graph via `browzer init` + `browzer workspace index`.
Audible code-quality reactions for code reading, review, refactoring, debugging, and repository exploration.
Use when the user asks to create a CodeTour .tour file — persona-targeted, step-by-step walkthroughs that link to real files and line numbers.
How to approach a coding task like a senior engineer — classify it (fix / refactor / feature / review / explore / migrate), map blast radius before editing, and self-review both…
Applies Chesterton's Fence, Occam's Razor, the Peter Principle, and Dunning-Kruger to technical decisions.
Identify, categorize, and prioritize technical debt. Trigger with "tech debt", "technical debt audit", "what should we refactor", "code health", or when the user asks abo — from…
Use when modernizing legacy Entity Framework data layers to EF Core with help for model mapping, DbContext refactors, phased cutovers, and migration risk review.
Apply the Explore → Plan → Code → Commit workflow for tasks like implementing features, fixing bugs, refactors, or adding integrations.
ERNE — Comprehensive code review combining code quality and performance analysis
ERNE — Create native modules with sequential native-bridge-builder then code-reviewer agents