refactor
Invoke IMMEDIATELY via script when user requests refactoring analysis, technical debt review, or code quality improvement.
Skill by gcharang
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/gcharang-refactor
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/refactor
What's inside
- Skill name
refactor- Description
- Invoke IMMEDIATELY via script when user requests refactoring analysis, technical debt review, or code quality improvement. Do NOT explore first - the script orchestrates exploration.
- License
- MIT
- Instructions
- 26 lines in SKILL.md · view on GitHub
Files (3)
- CLAUDE.md
- README.md
- SKILL.md
SKILL.md (first lines)
# Refactor Run the script before exploring and follow its output; it orchestrates the exploration. ## Invocation <invoke working-dir=".claude/skills/scripts" cmd="uv run python -m skills.refactor.refactor --step 1 --n 10" /> | Argument | Required | Description | | -------- | -------- | --------------------------------------------- | | `--step` | Yes | Current step (starts at 1) | | `--n` | No | Number of categories to explore (default: 10) | ## Determining N (category count) Default: N = 10 Adjust based on user request scope: - SMALL (single file, specific concern, "quick look"): N = 5 - MEDIUM (directory, module, standard analysis): N = 10 - LARGE (entire codebase, "thorough", "comprehensive"): N = 25 Step 1 picks a mode from the request. In design, code, or both mode the script samples N targets at random from the categories in conventions/code-quality/; in custom mode it selects categories from the problem statement and ignores N.
From gcharang/claude-config, MIT.
More from gcharang/claude-config
- 0.570score
prompt-engineer
gcharang
Invoke IMMEDIATELY via script when user requests prompt optimization.
SkillAFreshness: AClaude Code +9 - 0.565score
incoherence
gcharang
Detect and resolve incoherence across documentation, code and specs.
SkillAFreshness: AClaude Code +9 - 0.560score
cc-history
gcharang
Query Claude Code conversation history (JSONL transcripts under ~/.claude/projects/) with shell and jq.
SkillAFreshness: AClaude Code +9 - 0.559score
deepthink
gcharang
Invoke IMMEDIATELY via script when user requests structured reasoning for open-ended analytical questions.
SkillAFreshness: AClaude Code +9 - 0.559score
codebase-analysis
gcharang
Invoke IMMEDIATELY via script when user requests codebase understanding, architecture comprehension, or repository orientation.
SkillAFreshness: AClaude Code +9 - 0.559score
problem-analysis
gcharang
Invoke IMMEDIATELY via script when user requests problem analysis or root cause investigation.
SkillAFreshness: AClaude Code +9 - 0.556score
decision-critic
gcharang
Invoke IMMEDIATELY via script to stress-test decisions and reasoning.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 22, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/gcharang/claude-config
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from gcharang
- 0.570score
prompt-engineer
gcharang
Invoke IMMEDIATELY via script when user requests prompt optimization.
SkillAFreshness: AClaude Code +9 - 0.565score
incoherence
gcharang
Detect and resolve incoherence across documentation, code and specs.
SkillAFreshness: AClaude Code +9 - 0.560score
cc-history
gcharang
Query Claude Code conversation history (JSONL transcripts under ~/.claude/projects/) with shell and jq.
SkillAFreshness: AClaude Code +9 - 0.559score
deepthink
gcharang
Invoke IMMEDIATELY via script when user requests structured reasoning for open-ended analytical questions.
SkillAFreshness: AClaude Code +9 - 0.559score
codebase-analysis
gcharang
Invoke IMMEDIATELY via script when user requests codebase understanding, architecture comprehension, or repository orientation.
SkillAFreshness: AClaude Code +9 - 0.559score
problem-analysis
gcharang
Invoke IMMEDIATELY via script when user requests problem analysis or root cause investigation.
SkillAFreshness: AClaude Code +9
Cite this page
refactor skill. Agent Mart. https://agentmart.dev/skills/gcharang-refactor (last updated 2026-10-24)