Best refactoring skills, page 9

A skill your agent uses when modifying existing code that lacks tests and you need to document its actual current behavior before making changes -- the legacy code dilemma where you need tests to…

citypaul/.dotfiles

Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket…

JuliusBrussee/caveman

Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading.

cursor/plugins

Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.

openclaw/openclaw

Migrate a Flutter project that already uses an older vexana (4.x or 5.x) to vexana 6.x — bumps the dependency, rewrites removed imports and immutable-model mutations, and flags call sites whose…

VB10/vexana

Review C++ changes for string parameter and call-site efficiency conventions (std::stringview, std::string&&, const std::string&, const char, and TransparentStringMap lookup).

tetherto/qvac

Project health audit and health check — architecture, performance, tests, dependencies, code quality.

oliver-kriska/claude-elixir-phoenix

Architecture rules for cmux's move to Swift Packages: acyclic whole-domain packages, minimal public API, group folders, Xcode project wiring and Swift 6 concurrency.

manaflow-ai/cmux

Apply Whispering service-boundary patterns for UI-free capabilities, explicit inputs, Result fallibility, Live objects, lifecycle factories, and platform variants.

EpicenterHQ/epicenter

Guide for continuous improvement, error proofing, and standardization.

davila7/claude-code-templates

Moves logic out of Astro frontmatter into tested helper modules under shared/lib, with rules for naming, typing, deterministic demo data and sibling test files.

tabler/tabler

Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo.

affaan-m/ECC

A skill your agent uses when writing, debugging, or refactoring code that imports "pinia", the Vue 3 store library.

skilld-dev/vue-ecosystem-skills

Generate, scaffold, or refactor code so it embodies FIASSE v1.0.4 SSEM qualities by default — 10 attributes, Transparency and Least-Astonishment principles, ASVS-aligned controls, defensive boundary…

OWASP/secure-agent-playbook

A skill your agent uses for frontend work in webapp (React/TypeScript, UI implementation, tests, and refactors).

streamband/hydra-srt

Evaluates and carries out non-trivial software changes from first principles: ground the problem, name real consumers, choose the smallest sufficient solution and require evidence.

bytedance/deer-flow

Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules.

sanity-io/sanity

Audit broad Luxury Yacht systems or cross-cutting concerns for structural simplification, hardening, optimization, or refactoring; use for app-wide reviews and phased structural plans, not branch…

luxury-yacht/app

Automatically scans the TizenFX codebase on a rotating schedule to discover .NET 8 / C 12+ refactoring targets and register them as GitHub Issues.

Samsung/TizenFX

Maintain the Prism codebase: measure cyclomatic complexity, refactor hotspots, and enforce the anti-slop type discipline.

irfndi/prism-liquidity-agent

Remove AI-generated code slop and clean up code style. An agent skill from sanity-io/sanity.

sanity-io/sanity

Rules for writing and editing unit tests in the Console (console/src//.spec.ts[x]).

synnaxlabs/synnax

Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform.

caliber-ai-org/ai-setup

Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees.

rohitg00/pro-workflow

Systematic planning for medium-to-large tasks. An agent skill from poteto/noodle.

poteto/noodle

Refactors code safely in projects indexed by trace-mcp: assess risk, find candidates, check impact and rename symbols across every file without missing a reference.

nikolai-vysotskyi/trace-mcp

Keeps truST's architecture simple and well separated, and runs the automated architecture checks.

johannesPettersson80/trust-platform

Read, write and compile-check CODESYS code in this project without opening the GUI, by driving CODESYS headlessly through its ScriptEngine.

MichielVanwelsenaere/HomeAutomation.CoDeSys3

实现新功能或功能改造。不用于纯 bug 修复（cs-issue）、行为等价重构（cs-refactor）、大需求拆解（cs-epic）。

codestable/CodeStable

Build or refactor a Tool-channel provider (PagerDuty, Opsgenie, future incident/alerting tools) to be endpoint-routed: per-subscriber secrets encrypted on the channel endpoint resource, a stateless…

novuhq/novu

Commit local changes as a baseline, hop into a lightweight review worktree, run a thermo-nuclear code quality review scoped to ONLY that commit, commit the resulting refactor as a separate follow-up…

novuhq/novu

Odoo 18 development reference for Python models and ORM (search, domain, readgroup, compute fields), XML/CSV data and views, OWL/JS client code, QWeb reports, security (ACL, record rules, groups)…

unclecatvn/agent-skills

Reviews a code change for correctness, security, maintainability, architecture, performance, and verification gaps, or performs a local code-smell review.

hylarucoder/hai-stack

Prevent scope creep when a plan or implementation starts absorbing adjacent fixes, speculative compatibility work, migrations, or unrelated refactors.

tiramisulabs/seyfert

Review or self-check a change to the Static Web Server (SWS) project before it is called done — correctness, invariants, API design, concurrency, maintainability, and an SWS-specific review checklist.

static-web-server/static-web-server

Apply Robert C. Martin-inspired clean code rules when improving readability, naming, function design, responsibilities, or testable everyday code.

ciembor/agent-rules-books

Convert a legacy handwritten-Cypher Cartography sync (load / cleanup JSON jobs) into the modern declarative data model (load(), GraphJob.fromnodeschema()).

cartography-cncf/cartography

Styling and layout guide for Saleor Apps using modern macaw-ui and @saleor/apps-ui-next.

saleor/apps

A skill your agent uses whenever the user wants the Zova frontend path in this Cabloy repo: create or extend pages, components, api or model beans, route/query/params work, metadata refresh…

cabloy/cabloy

Removes AI-generated code smells from branch changes or an explicit file list behind regression tests.

code-yeongyu/oh-my-openagent

Find and fix technical debt including duplicated code, dead code, outdated patterns, and code smells.

meleantonio/ChernyCode

Rules for continuing or remodeling a prior CraftBot building script: treat the inherited model as a found object, audit it against the brief, and track every change.

lukapiskorec/craftbot

Compresses a TypeScript or Swift repository into one symbol-map text file sized for an LLM context window, for refactor planning and architecture recon.

steipete/agent-scripts

End-to-end workflow for agent-driven changes that add or modify behavior in the toolkit packages.

OfficeDev/microsoft-365-agents-toolkit

Reorganize NemoClaw documentation pages, navigation, or content ownership while preserving published routes.

NVIDIA/NemoClaw

Autonomous iteration loops for .NET development: build-fix, test-fix, refactor, and scaffold loops.

Resgrid/Core

Expert guidance on Swift Concurrency best practices, patterns, and implementation.

AFK-surf/OpenBridge

Delegate coding tasks to Claude Code (Anthropic's CLI agent).

RedWoodOG/Hermes-Desktop