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

Refactoring

ASecurity

Restructure existing code without changing what it does — when asked to clean up, simplify, split a big file or function, remove duplication, or "make this nicer". Not for fixing bugs or adding features.

2 stars
0 votes
0 copies
1 views
Added 10/3/2026
ai-agentsrefactoring

Security Analysis

A100/100

Scanned 10/3/2026

$npx -y skills add ivanvp91/TRCode --skill refactoring --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Refactoring?

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

Security grade badge for Refactoring
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ivanvp91-refactoring/badge)](https://www.skillsdirectory.com/skills/ivanvp91-refactoring)

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: refactoring
description: Restructure existing code without changing what it does — when asked to clean up, simplify, split a big file or function, remove duplication, or "make this nicer". Not for fixing bugs or adding features.
description_ru: Переустроить существующий код, не меняя поведения — когда просят почистить, упростить, разделить большой файл или функцию, убрать дублирование, «сделать аккуратнее». Не для починки багов и не для новых возможностей.
triggers: рефактор, рефакторинг, refactor, refactoring, почисти, почистить, cleanup, clean up, упрости, упростить, simplify, дублирование, duplication, разбей файл, tech debt, техдолг, отрефактори, зарефактори
---

# Refactoring

## 1. Establish the safety net first
- Find the tests that cover the code. Run them and record that they pass *before* you touch anything.
- No tests? Say so, and either write a characterisation test for the current behaviour first, or keep the change small enough to verify by reading.

## 2. Understand the current shape
Read every caller of what you are about to move (`grep` the symbol). A refactor that looks local is usually not: default arguments, re-exports, dynamic access by string, and tests all reach in.

## 3. Pick the smallest useful move
In order of payoff:
1. **Delete** — dead code, unused parameters, commented-out blocks, redundant branches.
2. **Name** — a magic number, a boolean parameter, a `data2` variable.
3. **Extract** — pull a coherent block into a function with one job; not "the middle 20 lines".
4. **Deduplicate** — but only when the copies really are the same rule, not two rules that coincide today.
5. **Reshape** — flatten nesting, early returns, invert a condition.

## 4. One transformation per step
Make the change, run the tests, move on. A pile of simultaneous edits is not a refactor, it is a rewrite with no way back.

## 5. Match the codebase, not your taste
Follow the naming, file layout, error handling and comment density that already exist here. A refactor that introduces a new style is a net loss even if the style is better in the abstract.

## What not to do
- Do not change behaviour, error messages or public signatures unless explicitly asked. If you find a bug on the way, report it separately — do not fix it silently inside the refactor.
- Do not add abstraction for a second case that does not exist yet.
- Do not reformat whole files; it buries the real change in the diff.
- Do not "improve" comments into noise. Delete comments that lie; keep the ones explaining *why*.

## Answer format
- What changed, grouped by intent (deleted / renamed / extracted / moved).
- Confirmation that behaviour is identical, and how you know (tests run, output compared).
- Anything you deliberately left alone and why.

Attribution

ivanvp91ivanvp91
View sourceSee grades on GitHubMore from ivanvp91 →
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', ...

698431 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 →