Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Refactor

ASecurity

Analyzes code for smells and structural issues, proposes a safe refactoring plan, and executes it with test verification. Use when code is hard to read, maintain, or extend.

7 stars
0 votes
0 copies
1 views
Added 5/28/2026
ai-agentsgobashrefactoringgitapi

Works with

api

Security Analysis

A100/100

Scanned 5/28/2026

$npx -y skills add viknesh20-20/claude-code-tool-kit --skill refactor --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Refactor?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Refactor
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/viknesh20-20-refactor/badge)](https://www.skillsdirectory.com/skills/viknesh20-20-refactor)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: refactor
description: "Analyzes code for smells and structural issues, proposes a safe refactoring plan, and executes it with test verification. Use when code is hard to read, maintain, or extend."
argument-hint: "[file, function, or module to refactor]"
allowed-tools: Read, Grep, Glob, Bash, Edit, Write
---

# Safe Code Refactoring

## Context
!`git status --short 2>/dev/null`
!`git stash list 2>/dev/null`

---

## Refactoring Process

### Step 1: Analyze — Identify Code Smells
Read the target code and identify issues from this list:

- **Long Method/Function** (>40 lines): Extract smaller, focused functions
- **Deep Nesting** (>3 levels): Use early returns, guard clauses, or extract methods
- **Code Duplication**: Extract shared logic into reusable functions
- **God Class/Module**: Split into focused, single-responsibility modules
- **Feature Envy**: Move logic to the class/module that owns the data
- **Primitive Obsession**: Replace related primitives with a proper type/struct/class
- **Long Parameter List** (>4 params): Use an options/config object or builder pattern
- **Dead Code**: Remove unused functions, imports, variables, and commented-out code
- **Magic Numbers/Strings**: Extract into named constants
- **Inconsistent Naming**: Align with project conventions
- **Missing Abstractions**: Introduce interfaces/traits where concrete types are overused
- **Tight Coupling**: Introduce dependency injection or interface boundaries

### Step 2: Plan — Define the Refactoring Strategy
For each identified issue:
1. Name the specific refactoring technique (Extract Method, Move Function, Introduce Parameter Object, etc.)
2. Describe the before and after state
3. Assess the risk (High/Medium/Low) — does it touch public API? Does it cross module boundaries?
4. List affected files

**Present the plan to the user before executing.**

### Step 3: Verify — Check for Existing Tests
- Find all tests that cover the code being refactored
- Run them to establish a green baseline
- If no tests exist, flag this as a risk and recommend writing tests first

### Step 4: Execute — Apply Changes
- Make one refactoring change at a time
- After each change, verify:
  - The code still compiles/parses
  - Existing tests still pass
  - No new linting errors
- If a change breaks something, revert it immediately

### Step 5: Validate — Final Checks
- Run the full test suite for the affected area
- Verify no regressions via `git diff`
- Ensure the refactored code is actually simpler/cleaner than before
- If it isn't, consider reverting — refactoring should reduce complexity, not just move it

---

## Rules
- **Never change behavior** — refactoring is about structure, not features
- **Never skip tests** — if tests don't exist, say so and suggest writing them first
- **Small steps** — one technique per commit if possible
- **Respect scope** — don't refactor code outside the requested area
- **Keep the diff minimal** — don't reformat untouched code

Attribution

viknesh20-20viknesh20-20
View sourceSee grades on GitHubMore from viknesh20-20 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →