Best refactoring skills, page 11

Preserves existing code comments (line, block, JSDoc, region markers) when editing files; does not delete or collapse comments for brevity unless the user asked to remove or update them.

zkldi/Tachi

Levantar SonarQube con Docker, analizar el código y proponer mejoras.

686f6c61/alfred-dev

Forge (锻造坊) — Engineering & architecture deliberation room. An agent skill from geekjourneyx/agora.

geekjourneyx/agora

Language-agnostic coding principles for maintainability, readability, and quality.

shinpr/claude-code-workflows

Transform an AI agent into a disciplined software development partner with strong judgment, transparent decisions, proportionate verification, and craftsmanship.

shareAI-lab/lab-skills

Run cargo-mutants for changed coop logic and keep .cargo/mutants.toml synchronized.

trailofbits/coop

This skill should be used when creating, refreshing, or validating a repository AGENTS.md so it stays concise, current, and grounded in repository evidence.

alchemiststudiosDOTai/harness-engineering

Stress-tests a fuzzy or vague feature idea before any PRD, spec, or ticket is written.

opsmill/infrahub

Test-driven development for factory builders. An agent skill from DanMcInerney/architect-loop.

DanMcInerney/architect-loop

A skill your agent uses when multiple workflows duplicate the same operational logic, when deciding what belongs in actions vs shared services, or when refactoring repeated operational blocks across…

vvedantb/eva

Trace TypeScript exports, imports, and re-exports in codexhost before refactoring interfaces or deleting code.

BytePioneer-AI/codex-host

Define backend data modeling standards for Python services. An agent skill from AUTO-MAS-Project/AUTO-MAS.

AUTO-MAS-Project/AUTO-MAS

Restructure code while keeping observable behavior identical, and prove it with difference testing.

tola-rs/tola-ssg

Detects duplicate boilerplate, copy-paste tests, and structural maintainability issues across .NET test suites.

dotnet/skills

Pushes the agent toward the smallest working solution on coding tasks by climbing a ladder from skipping the work to reuse, standard library, native features and one-liners.

diegosouzapw/OmniRoute

React performance optimization guidelines. An agent skill from poteto/noodle.

poteto/noodle

Checks cyclomatic complexity, function and file length, parameter count, nesting depth and naming conventions against fixed thresholds, with a bundled Node.js script and hotspot integration.

telagod/code-abyss

Runs a user-invoked, swarm-style audit of a whole codebase for SOLID and DRY violations, code smells, complexity, dead code and pattern consistency, with a prioritized report.

dralgorhythm/claude-agentic-framework

Searches a codebase for the existing module that already owns a behavior before any new code is written, so a feature request edits that owner instead of shipping a second implementation.

codewhale-hq/Codewhale

Implements settings-style form pages using SettingsFormManager, SettingsFieldConfig, and SettingsFormRowBuilder.

singleton-altman/MoviePilotLite

Given a bug report (GitHub issue, Jira ticket, file, or pasted text), find its root cause and decide per symptom whether it is a one-off or one instance of a pattern worth fixing at the root, then…

BuilderIO/agent-native

Expertise in LLVM tooling development including Clang plugins, LLDB debugger extensions, Clangd/LSP, and LibTooling.

aftermathlabs/llvm-msvc

Implement and review Java code changes for Micronaut framework repositories using maintainer standards, including JSpecify null-safety conventions.

micronaut-projects/micronaut-openapi

A skill your agent uses when changing Dapper-FluentMap production code, public contracts, project files, PackageIds, package metadata, dependencies, or related tests.

rodri-oliveira-dev/Dapper-FluentMap

DESIGN a non-trivial codebase change (Harbor / MarinSkyRL / vLLM / OT-Agent / LLaMA-Factory) as a dependency-ordered STAGED PLAN before writing code — a feature port, a multi-step fix with parity…

open-thoughts/OpenThoughts-Agent

Review code for refactorability — surface concrete, prioritized refactoring opportunities grounded in Martin Fowler's smell catalog and SOLID, augmented with static analysis tools (gocyclo…

meain/dotfiles

Writes and reviews modern JavaScript: ES2023+ syntax, async/await, ESM modules, Node.js and browser APIs, with linting, leak checks and Jest tests.

Jeffallan/claude-skills

Plans incremental migrations of aging systems with the strangler fig pattern, using dependency maps, rollback plans, characterization tests and gradual traffic shifts.

Jeffallan/claude-skills

Replaces raw offsets and anonymous fields in a TH08 C++ source reconstruction with evidence-backed names and types, without changing accepted bytes or playable behavior.

N0zoM1z0/th08

ALWAYS use this skill when writing or refactoring code. An agent skill from ed3dai/ed3d-plugins.

ed3dai/ed3d-plugins

Axone contract structure and Abstract SDK patterns. An agent skill from axone-protocol/contracts.

axone-protocol/contracts

Comprehensive post-change review of all modified files. An agent skill from Ivy-Interactive/Ivy-Tendril.

Ivy-Interactive/Ivy-Tendril

Refactor complex case statements and deeply nested code using appropriate strategies.

kitchen-engineer42/pdf2skills

Update project documentation after code changes. An agent skill from peterkrueck/Claude-Code-Development-Kit.

peterkrueck/Claude-Code-Development-Kit

Create a new plan document in kb/plans/ for the opentraces project.

JayFarei/opentraces

A skill your agent uses when writing or refactoring core Elixir — pattern matching, case/cond/with, pipes, {:ok, }/{:error, } contracts.

j-morgan6/elixir-phoenix-guide

Hands coding work such as codebase questions, bug fixes, refactors and PR reviews to the Qwen Code CLI, driven through acpx instead of scraped terminal sessions.

QwenLM/qwen-code

Reviews your uncommitted diff with three parallel passes for reuse, quality and efficiency, then applies the straightforward cleanups before a pull request.

QwenLM/qwen-code

Analisa padrões de qualidade de código e detecta code smells, complexidade elevada e duplicação.

glaucia86/repocheckai

Compatibility entry for vBook extension creation, repair, testing, auditing, refactoring, building, and installation.

Darkrai9x/vbook-extensions

Tailwind CSS v4 usage guide and v3-to-v4 differences. An agent skill from mastra-ai/mastra.

mastra-ai/mastra

Format, clean up, and style-check changed files, matching the project's CI style gate.

ROCm/FlyDSL

Plan architecture improvements and refactoring for a codebase: scan for deepening opportunities (shallow modules, leaky seams, low-leverage interfaces), present candidates as a markdown report with…

TwiTech-LAB/devchain

Structure Django business logic as plain services that receive their dependencies via constructor injection, and wire them through an svcs registry so they can be resolved anywhere — views, Celery…

dvf/opinionated-django

Concrete code-quality thresholds and anti-patterns: 120-char lines, max 20 cyclomatic complexity, max 4 nesting levels, max 50 lines per function, no magic numbers, no global state, composition over…

Goldziher/ai-rulez

Refactoring rules for Handsontable code: SOLID applied to plugins, Law of Demeter fixes, performance patterns and strict protection of backward compatibility.

handsontable/handsontable

A skill your agent uses when writing Dart code, reviewing for style, refactoring naming, adding doc comments, structuring imports, or enforcing type annotations.

evanca/flutter-ai-rules

重构 CombatSolver 的 Search、Runtime 会话、UI snapshot、无人测试编排或 mirror registry 职责边界时使用；目标是迁移所有权和依赖，同时保持战斗语义、路线政策与协议行为不变。

Torch1230/CombatSolver