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/franciscsimon-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
Use cases: productivity
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
- Safe refactoring workflow using Chain of Small Steps. Restructures code without changing behavior, with tests between each step. Use when code needs cleanup or restructuring.
- License
- MIT
- Instructions
- 36 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Refactoring ## Workflow 1. **Verify tests pass before starting** ```bash npm test ``` If tests fail, fix them first. Never refactor without a green baseline. 2. **Identify the smell** — duplication, long method, feature envy, god class, etc. 3. **Plan small steps** — each step must be one atomic change that keeps tests green 4. **Execute one step at a time** - Make one change - Run tests: `npm test` - If green: commit with `refactor: <what changed>` - If red: revert immediately 5. **Repeat** until the smell is gone 6. **Final check** ```bash npm test git diff --stat HEAD~N # Review total changes ``` ## Rules - Never change behavior. Tests must pass at every step. - Never add features during refactoring. - If a test breaks, the refactoring introduced a bug — revert. - One commit per refactoring step.
From franciscsimon/harness, MIT.
More from franciscsimon/harness
- 0.432score
debugging
franciscsimon
Systematic debugging workflow using Approved Logs pattern.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
code-review
franciscsimon
Structured code review workflow.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
context-management
franciscsimon
Manage AI context health — prevent context rot, extract knowledge before compaction, compose reference docs.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
performance-optimization
franciscsimon
Profile and optimize performance bottlenecks.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
architecture-review
franciscsimon
Review and document system architecture.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
migration
franciscsimon
Dependency upgrade and API migration workflow.
SkillDFreshness: D★ 1Claude Code +9 - 0.429score
security-audit
franciscsimon
Security vulnerability audit following OWASP Top 10.
SkillDFreshness: D★ 1Claude Code +9 - 0.424score
knowledge-extraction
franciscsimon
Extract reusable knowledge from a session — decisions, gotchas, patterns discovered.
SkillDFreshness: D★ 1Claude Code +9 - 0.402score
test-writing
franciscsimon
Systematic test writing workflow.
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Mar 16, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/franciscsimon/harness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from franciscsimon
- 0.432score
debugging
franciscsimon
Systematic debugging workflow using Approved Logs pattern.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
code-review
franciscsimon
Structured code review workflow.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
context-management
franciscsimon
Manage AI context health — prevent context rot, extract knowledge before compaction, compose reference docs.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
performance-optimization
franciscsimon
Profile and optimize performance bottlenecks.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
architecture-review
franciscsimon
Review and document system architecture.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
migration
franciscsimon
Dependency upgrade and API migration workflow.
SkillDFreshness: D★ 1Claude Code +9
Cite this page
refactoring skill. Agent Mart. https://agentmart.dev/skills/franciscsimon-refactoring (last updated 2026-10-24)