Refactoring

A skill your agent uses when the user wants multi-agent division of labor for research-led work and the lead should stay on the critical path while 1-2 bounded sidecars handle low-coupling tasks.

cnfjlhj/ai-collab-playbook

Corrective cleanup of AI-generated code — removes LLM-specific patterns while preserving behavior.

tmdgusya/engineering-discipline

Refactor high-complexity React components in Dify frontend. An agent skill from Ohh-889/skyroc.

Ohh-889/skyroc

Scans the code a spec touches for its shallowest module, then proposes a refactor that hides more behind a smaller interface without changing behavior.

JuliusBrussee/cavekit

Code refactoring expert for improving code quality, readability, maintainability, and performance.

yennanliu/CS_basics

Guides writing or reviewing point-free, first-match-wins case lists in fp-go v2 Go code instead of switch statements and if-else chains.

IBM/fp-go

Enumerates Go declarations and signatures from the syntax tree, then proposes small, mechanically safe refactors with file and line citations.

pilinux/gorest

Invoke before committing user-facing JET changes such as features, bug fixes, compatibility changes, or deprecations.

aviatesk/JET.jl

Removes a Warp feature flag once it is stable for everyone, deleting the definition, the Cargo entries and every conditional check.

warpdotdev/warp

Refactoring MCP Tools for Better LLM Integration and Usability

adeze/raindrop-mcp

Migrates a direct command call in Ruby Git's Git::Lib to a Git::Commands class, as part of a Strangler Fig redesign, with a plan, legacy tests and a pull request.

ruby-git/ruby-git

Use BEFORE roadmap or specify to get the idea OUT OF YOUR HEAD and onto disk — a Socratic interview that surfaces hidden assumptions, names tradeoffs, exposes imprecisions and proposes fresh angles…

genkovich/sdd

A skill your agent uses when scanning source code for bugs, anti-patterns, code smells, or quality issues in a codebase, or when running a proof-driven bug hunt that must find, prove, fix, and…

WrongStack/WrongStack

Mandatory coding discipline rules that prevent common AI coding anti-patterns.

luoling8192/ai-coding-principles

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles.

meshery/meshery-operator

A skill your agent uses when writing, reviewing, or refactoring TypeScript

mrzmyr/pixy-mood-tracker-app

Orchestrate multi-track parallel feature development with subagents and git worktrees.

flyxl/datazen

Plan and execute large refactor or rewrite efforts efficiently with parallel multi-agent analysis and implementation.

Dimillian/Skills

Implement, change, build, fix, refactor, migrate, or apply accepted review findings in the Happier repositories with canonical-owner discovery, scope-preserving solution economy, TDD, efficient…

happier-dev/happier

Worker brief for implementing one pre-assigned feature in the senpi todotools built-in extension, with strict scope, typing, testing and git-safety rules.

code-yeongyu/senpi

A skill your agent uses when a dd-trace-js change introduces or substantially changes a class hierarchy, module boundary, shared helper layer, public API, or duplicated behavior across multiple types.

DataDog/dd-trace-js

This skill should be used when writing, reviewing, or refactoring Python code.

fcakyon/claude-codex-settings

Pick open GitHub issues in the Axelix monorepo that are suitable for unpaid volunteer contributors working in their spare time.

axelixlabs/axelix

Refactor Session Sniffer code to improve structure, readability, duplication, and maintainability while preserving existing behavior.

BUZZARDGTA/Session-Sniffer

OpenTeams-only workflow skill. An agent skill from openteams-lab/openteams.

openteams-lab/openteams

Provide an expert codebase review for this repository. An agent skill from jtenniswood/esphome-media-player.

jtenniswood/esphome-media-player

Multi-agent orchestration for complex tasks. An agent skill from numman-ali/n-skills.

numman-ali/n-skills

A skill your agent uses when asked to restructure a layered monolith (Core/Infrastructure/Web style) into a modular monolith, extract modules or bounded contexts, or plan a feature-based…

DevBetterCom/DevBetterWeb

Use this when the user wants to refactor the codebase, clean up code, reduce duplication, or says 'refactor' / 'new refactor'.

dcodesdev/LetterSpace

Rewrite messy or AI-generated crawler code into clean, production-ready style that follows the zavod best practices.

opensanctions/opensanctions

Surgical code fixer for Bug Hunter. An agent skill from codexstar69/bug-hunter.

codexstar69/bug-hunter

TypeScript engineering guidelines based on Google's style guide.

rishighan/threetwo

Aggressive token, context, and cost optimization mode for AI coding agents (Claude Code, Antigravity, Cursor, etc.).

kipperacademy/skillpper

Odoo 17 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

A skill your agent uses when generating UI for a specific scenario (mobile/PC/官网/管理端/营销页/文档/金融/原生/3D), when refactoring an existing HTML/Vue/React project to a unified design system, when extracting…

jiushiwon/wg-skills

Perform a comprehensive DRY (Don't Repeat Yourself) code review on a codebase.

espennilsen/pi

Invoke before committing user-facing changes (new features, bug fixes, behavior changes) to update CHANGELOG.md.

aviatesk/JETLS.jl

End-to-end, phase-gated SDLC for AI coding agents: relentless design interview → reviewed spec → dependency-graphed task board → safe-wave TDD execution → verification → converge.

maddhruv/absolute

Explore packages/, layout, and .agents/ for architectural friction (coupling, shallow packages, missing boundaries) and file or recommend agent issues under docs/issues/.

Apocrathia/home-assistant-config

Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue.

fossasia/eventyay-interpretation

对 Aaalice NAI Launcher 的大型文件拆分型重构执行多子代理等价性闭环。当任务目标是把大型业务文件按职责拆分、同时保持功能、交互与布局不变时自动使用；不用于普通重构、功能开发、单点 Bug 修复或常规代码审查。

Aaalice233/Aaalice_NAI_Launcher

Work inside the Databuddy monorepo for internal implementation, debugging, review, and refactoring.

databuddy-analytics/Databuddy

Orchestrate parallel Claude Code worker swarms with protocol-based behavioral governance.

cj-vana/claude-swarm

Shows how to compose Go functions with fp-go v2 Pipe and Flow: point-free pipelines, predicates, the reader monad, do-notation and tests for pipelines.

IBM/fp-go

Guides systematic code refactoring following the DRY (Don't Repeat Yourself) principle.

YYH211/Claude-meta-skill

Audit and improve repository code milestone by milestone for correctness, clarity, local reasoning, DRY design, explicit state modeling, panic resistance, and trustworthy TypeScript boundaries.

pmndrs/glyph

Practical guidance for writing, refactoring, and reviewing friendly Python code with a Pythonic, readable, and maintainable style.

PsiACE/skills

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