Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/thangbuiq-refactoring
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/refactoring
What's inside
- Skill name
refactoring- Description
- Safely restructure code without changing behaviour. Use for cleaning up duplication, long functions, poor naming, tangled dependencies or preparing code for a new feature.
- License
- MIT
- Metadata
- source: first-party
- Instructions
- 11 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Refactoring 1. **Secure a safety net** – ensure tests cover the behaviour you will touch; add characterization tests if they don't. Run them green first. 1. **One transformation at a time**: rename, extract function/class, inline, move, replace conditionals with polymorphism/lookup, introduce parameter object, remove dead code. 1. **Run tests after every step**; commit in small steps so each is revertable. 1. **Keep behaviour and public APIs stable** unless explicitly asked; separate refactor commits from feature/fix commits. 1. Follow the codebase's conventions; don't introduce new patterns or dependencies just because. Signals worth fixing: duplication (3+ copies), functions doing several things, deep nesting, boolean-flag parameters, primitive obsession, shotgun surgery. Stop when the code is clear enough for the task at hand; don't gold-plate.
From thangbuiq/universal-ai-agent-kit, MIT.
More from thangbuiq/universal-ai-agent-kit
- 0.565score
git-workflow
thangbuiq
Branching, Conventional Commit messages and pull request practices.
SkillAFreshness: AClaude Code +9 - 0.559score
commit-with-precommit
thangbuiq
Commit in repos that use prek or pre-commit.
SkillAFreshness: AClaude Code +9 - 0.559score
documentation
thangbuiq
Write or update READMEs, API docs, docstrings, ADRs and changelogs.
SkillAFreshness: AClaude Code +9 - 0.544score
mcp-builder
thangbuiq
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
SkillAFreshness: AClaude Code +9 - 0.541score
webapp-testing
thangbuiq
Toolkit for interacting with and testing local web applications using Playwright.
SkillAFreshness: AClaude Code +9 - 0.539score
receiving-code-review
thangbuiq
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires…
SkillAFreshness: AClaude Code +9 - 0.538score
requesting-code-review
thangbuiq
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
SkillAFreshness: AClaude Code +9 - 0.538score
writing-plans
thangbuiq
Use when you have a spec or requirements for a multi-step task, before touching code
SkillAFreshness: AClaude Code +9 - 0.538score
systematic-debugging
thangbuiq
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
SkillAFreshness: AClaude Code +9 - 0.536score
frontend-design
thangbuiq
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one.
SkillAFreshness: AClaude Code +9 - 0.534score
subagent-driven-development
thangbuiq
Use when executing implementation plans with independent tasks in the current session
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 17, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from thangbuiq
- 0.565score
git-workflow
thangbuiq
Branching, Conventional Commit messages and pull request practices.
SkillAFreshness: AClaude Code +9 - 0.559score
commit-with-precommit
thangbuiq
Commit in repos that use prek or pre-commit.
SkillAFreshness: AClaude Code +9 - 0.559score
documentation
thangbuiq
Write or update READMEs, API docs, docstrings, ADRs and changelogs.
SkillAFreshness: AClaude Code +9 - 0.544score
mcp-builder
thangbuiq
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
SkillAFreshness: AClaude Code +9 - 0.541score
webapp-testing
thangbuiq
Toolkit for interacting with and testing local web applications using Playwright.
SkillAFreshness: AClaude Code +9 - 0.539score
receiving-code-review
thangbuiq
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires…
SkillAFreshness: AClaude Code +9
Cite this page
refactoring skill. Agent Mart. https://agentmart.dev/skills/thangbuiq-refactoring (last updated 2026-10-24)