sc-improve
Skill19 starsChanged 8 months agoMITView on GitHub
Apply systematic improvements to code quality, performance, maintainability, and cleanup. Use when refactoring code, optimizing performance, removing dead code, or improving project structure.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- kreighmitchell/SuperClaudeword for word, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 1
- kreighmitchell/SuperClaude★ 4100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository37 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-data-engineerSkill
- agent-fullstack-developerSkill
- agent-kubernetes-specialistSkill
- agent-ml-engineerSkill
- agent-performance-engineerSkill
- agent-react-specialistSkill
- agent-security-engineerSkill
- agent-technical-writerSkill
- ask-multiSkill
- askSkill
- learned-skills-indexSkill
- sc-analyzeSkill
- sc-brainstormSkill
- sc-buildSkill
- sc-cicd-setupSkill
- sc-code-reviewSkill
- sc-designSkill
- sc-documentSkill
- sc-e2eSkill
- sc-estimateSkill
- sc-evaluateSkill
- sc-explainSkill
- sc-gitSkill
- sc-implementSkill
- sc-log-fixSkill
- sc-mcpSkill
- sc-pr-checkSkill
- sc-pr-fixSkill
- sc-principlesSkill
- sc-pushSkill
- sc-readmeSkill
- sc-researchSkill
- sc-tddSkill
- sc-testSkill
- sc-workflowSkill
- sc-worktreeSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Validate: - Ensure functionality preservation
- Distinctive: line 130
Run tests to verify functionality preservation
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Code Improvement & Cleanup Skill
Systematic improvements with multi-persona expertise and safety validation.
Quick Start
# Quality improvement
/sc:improve src/ --type quality --safe
# Performance optimization
/sc:improve api-endpoints --type performance
# Dead code cleanup
/sc:improve src/ --cleanup --type code --safe
# Import optimization
/sc:improve --cleanup --type importsBehavioral Flow
- Analyze - Examine codebase for improvement opportunities
- Plan - Choose approach and activate relevant personas
- Execute - Apply systematic improvements
- Validate - Ensure functionality preservation
- Document - Generate improvement summary
Flags
| Flag | Type | Default | Description |
--type | string | quality | quality, performance, maintainability, style, principles, code, imports, files, all |
--cleanup | bool | false | Enable cleanup mode |
--safe | bool | true | Conservative with safety validation |
--aggressive | bool | false | Thorough cleanup (use with caution) |
--preview | bool | false | Show changes without applying |
--interactive | bool | false | Guided decision mode |
Personas Activated
- architect - Structure and design improvements
- performance - Optimization expertise
- quality - Code quality and maintainability
- security - Security pattern application
- code-warden - KISS and Purity enforcement (with --type principles)
MCP Integration
PAL MCP (Validation & Analysis)
| Tool | When to Use | Purpose |
mcp__pal__consensus | Complex refactors | Multi-model validation before major changes |
mcp__pal__codereview | Quality assessment | Review improvement quality and safety |
mcp__pal__thinkdeep | Architecture changes | Deep analysis of structural improvements |
mcp__pal__precommit | Before commit | Validate all changes preserve functionality |
mcp__pal__debug | Regression issues | Root cause analysis if improvements break things |
mcp__pal__challenge | Aggressive mode | Critical evaluation of aggressive cleanup decisions |
PAL Usage Patterns
# Consensus for major refactor
mcp__pal__consensus(
models=[
{"model": "gpt-5.2", "stance": "for"},
{"model": "gemini-3-pro", "stance": "against"}
],
step="Evaluate: Should we extract this into a separate module?"
)
# Review after improvements
mcp__pal__codereview(
review_type="full",
step="Reviewing code improvements",
findings="Quality, maintainability, backwards compatibility",
relevant_files=["/src/refactored/module.py"]
)
# Pre-commit validation
mcp__pal__precommit(
path="/path/to/repo",
step="Validating refactoring changes",
confidence="high"
)Rube MCP (Automation & Tracking)
| Tool | When to Use | Purpose |
mcp__rube__RUBE_SEARCH_TOOLS | External tools | Find linters, formatters, analyzers |
mcp__rube__RUBE_MULTI_EXECUTE_TOOL | Notifications | Update tickets, notify team |
mcp__rube__RUBE_CREATE_UPDATE_RECIPE | Reusable workflows | Save improvement patterns |
Rube Usage Patterns
# Notify team of improvements
mcp__rube__RUBE_MULTI_EXECUTE_TOOL(tools=[
{"tool_slug": "SLACK_SEND_MESSAGE", "arguments": {
"channel": "#refactoring",
"text": "Completed: Dead code cleanup removed 500 lines"
}},
{"tool_slug": "JIRA_UPDATE_ISSUE", "arguments": {
"issue_key": "TECH-456",
"status": "Done"
}}
])
# Create improvement report in Notion
mcp__rube__RUBE_MULTI_EXECUTE_TOOL(tools=[
{"tool_slug": "NOTION_CREATE_PAGE", "arguments": {
"title": "Refactoring Report - Q4 2025",
"content": "## Summary\n- Lines removed: 500\n- Complexity reduced: 25%"
}}
])Evidence Requirements
This skill requires evidence. You MUST:
- Show before/after code comparisons
- Run tests to verify functionality preservation
- Report metrics (lines removed, complexity reduction)
Improvement Types
Quality (--type quality)
- Technical debt reduction
- Code structure improvements
- Readability enhancements
Performance (--type performance)
- Bottleneck resolution
- Algorithm optimization
- Resource efficiency
Maintainability (--type maintainability)
- Complexity reduction
- Documentation improvements
- Modular restructuring
Style (--type style)
- Formatting consistency
- Naming conventions
- Pattern alignment
Principles (--type principles)
- KISS compliance improvements (reduce complexity, extract methods)
- Purity enforcement (separate I/O from logic)
- Guard clause refactoring (reduce nesting)
- Functional core extraction (move I/O to shell layer)
Validators:
# Run KISS validation
python .claude/skills/sc-principles/scripts/validate_kiss.py --scope-root . --json
# Run Purity validation
python .claude/skills/sc-principles/scripts/validate_purity.py --scope-root . --jsonCleanup Mode (--cleanup)
Code Cleanup (--type code)
- Dead code detection and removal
- Unused variable elimination
- Unreachable code removal
Import Cleanup (--type imports)
- Unused import removal
- Import organization
- Dependency optimization
File Cleanup (--type files)
- Empty file removal
- Orphaned file detection
- Structure optimization
Full Cleanup (--type all)
- Comprehensive cleanup
- All categories combined
- Multi-persona coordination
Safety Modes
Safe Mode (--safe)
- Conservative changes only
- Automatic safety validation
- Preserves all functionality
Aggressive Mode (--aggressive)
- Thorough cleanup
- Framework-aware patterns
- Requires careful review
Examples
Safe Quality Improvement
/sc:improve src/ --type quality --safe
# Technical debt reduction with safety validationPerformance Optimization
/sc:improve api-endpoints --type performance --interactive
# Guided optimization with profiling analysisDead Code Cleanup
/sc:improve src/ --cleanup --type code --safe
# Remove unused code with dependency validationPreview Changes
/sc:improve --cleanup --type imports --preview
# Show what would be removed without executingTool Coordination
- Read/Grep/Glob - Code analysis
- Edit/MultiEdit - Safe modifications
- TodoWrite - Progress tracking
- Task - Large-scale improvement delegation
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

