Best refactoring skills, page 12

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

ayoubben18/ab-method

Sets up Android Gradle convention plugins in a build-logic composite build, including the version catalog wiring and shared configuration that are easy to get wrong.

rcosteira79/android-skills

A skill your agent uses for Go changes in Neva: authoring, refactoring, debugging, or review.

nevalang/neva

Project stylistic refactoring rules for Bun/TypeScript CLI. An agent skill from nklisch/claude-code-modes.

nklisch/claude-code-modes

Produce a professional, code-grounded refactor or implementation design report from identified technical problems, product gaps, review findings, architecture concerns, or frontend-backend contract…

penwyp/ClaudePreference

Review a git diff or explicit file scope for reuse, code quality, efficiency, clarity, and standards issues, then optionally apply safe Codex-driven fixes.

Dimillian/Skills

Decompose OpenFoot Manager code by responsibility when a quality gate is red, a reviewer requests a split or a refactor is authorized.

openfootmanager/openfootmanager

A skill your agent uses to perform a comprehensive code quality and architecture review of the current project or repository, identifying code smells, architectural debt, performance bottlenecks…

paiml/aprender

A skill your agent uses when writing, fixing, editing, or refactoring Python tests.

ertugrul-dmr/clean-code-skills

Speculative code editing session — simulate changes in memory before touching disk.

blackwell-systems/agent-lsp

Frontend-specific code review criteria, component anti-patterns, hooks quality, rendering correctness, accessibility and performance spot-checks, and module organization issues.

TheSoftwareHouse/copilot-collections

Assess whether completed engine code changes should be reflected in Doc/EngineCodeMap.

tangziwen/CubeMiniGame

Безопасный рефакторинг маленькими шагами без изменения поведения.

justxor/claude-code-pro-course

Post-refactor clean-code check after recent refactors or a few merged PRs.

akitaonrails/my-skills

Clean up code with lightweight clarity improvements. An agent skill from jrkerns/pylinac.

jrkerns/pylinac

Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings shaped as refactor proposals /squid-refactor can consume directly.

iusztinpaul/squid

Orchestrate a 3-agent PR code review debate using Claude Code Teams.

NomaDamas/AutoRAG-Research

Enforces coding best practices: deep-read before modify, LSP-first navigation, TDD red-green-refactor, minimal changes, self-review, verification.

KaimingWan/oh-my-kiro

Refactor and verify website timer/time-entry surfaces on the reused local runtime.

CorrectRoadH/OpenTickly

Query SonarCloud API for code quality data. An agent skill from agentculture/culture.

agentculture/culture

Expert code simplification and refactoring specialist that autonomously enhances code clarity, consistency, and maintainability while preserving exact functionality.

chendongqi/OPB-Skills

Combine React's official "You Might Not Need an Effect" guidance with this project's stricter no direct useEffect stance.

waynesutton/markdown-site

[omh] Messy or AI-generated code to clean up: delete AI-generated slop, dead code, and duplication while observable behavior stays identical.

rlaope/oh-my-hermes

Cleans up AI-generated code that works but is bloated or repetitive, locking behavior with tests first and deleting before adding, with a reviewer-only mode.

Yeachan-Heo/oh-my-claudecode

Periodic survey that walks a repo's module graph and reports ranked candidates for deepening, without changing any code itself.

Yeachan-Heo/oh-my-claudecode

A skill your agent uses to keep Jetpack Compose state alive across HotSwan hot reloads by understanding the three escalating tiers Compose HotSwan uses (tier 1 targeted recomposition, tier 2…

rosuH/EasyWatermark

A skill your agent uses to teach Claude exactly which Kotlin and Compose changes hot-reload under Compose HotSwan and which trigger a full incremental rebuild fallback.

rosuH/EasyWatermark

Manage per-feature living documents that capture decisions, constraints, and reasoning across AI sessions during active development.

techygarg/lattice

Conventions for writing empirical finance R code with data.table, fixest, arrow, and ggplot2.

aspi6246/Claude-Code-Skills-for-Academics

Delegate coding tasks to Codex, Claude Code, or Pi agents via background host sessions.

trpc-group/trpc-agent-go

Drive OpenAI's Codex CLI (codex exec) as a non-interactive coding sub-agent from inside Claude Code.

kortix-ai/suna

[production-grade internal] Implements backend services, APIs, and business logic — builds features, fixes bugs, refactors code from specs.

nagisanzenin/production-grade

Refactor error handling to use smarterr. An agent skill from hashicorp/terraform-provider-aws.

hashicorp/terraform-provider-aws

Surfaces architectural friction in real code — shallow modules, tight coupling, untested seams — and proposes deepening refactors using Ousterhout's deep-module principle (small interface hiding a…

assafkip/kipi-system

Decompose large tasks across parallel agents — use for migrations, multi-file refactors, or batch work

nyldn/claude-octopus

Structured decision-making framework for technical proposals and trade-off analysis.

Tommy-yw/RunbookHermes

This skill should be used after visual-acceptance-review has generated fix-tasks.json.

Jason904/ui-skill-lab

Structures Lean 4 proofs and library design along Mathlib conventions, from stating theorems to refactoring long tactic proofs and fixing slow or timing-out ones.

trailofbits/skills

Specialized code quality evaluator for the Evaluate-Loop. An agent skill from Ibrahim-3d/orchestrator-supaconductor.

Ibrahim-3d/orchestrator-supaconductor

Investigates unfamiliar codebases before changing them, makes small targeted edits and records what it learns in a .notebook/ folder for later sessions.

tech-leads-club/agent-skills

Runs a five-step analysis of a monolith: size components, find shared domain logic, flatten hierarchy, measure coupling and group components into candidate domains.

tech-leads-club/agent-skills

Runs deterministic byte-parity and paired performance campaigns for Dynamo offline KV-aware replay across native-G1 vLLM and SGLang configurations, including forced scheduler-pressure and…

ai-dynamo/dynamo

A skill your agent uses when building or refactoring Angular applications — choosing between signals, RxJS, and NgRx for state, configuring routing with guards and lazy loading, optimizing change…

kid-sid/claude-spellbook

Automatically document all development work and code modifications in a structured workthrough format.

bear2u/my-skills

Refactor a Vue page or component from Vuetify to semantic HTML5 + Schema.org microdata + Stylus element selectors.

scott-fryxell/brayness

Analyzes code changes from an architectural perspective for pattern compliance and design integrity.

udecode/plate

Workflow orchestration for complex coding tasks. An agent skill from brianlovin/agent-config.

brianlovin/agent-config

Frontend building block catalog — typed patterns for components, hooks, queries, mutations, stores, and models.

bartstc/vite-ts-react-template