Token导航 LogoToken导航TokenDH.com
研究检索执行命令github未标认证来源可访问clear审计未展示

sc-improve提高

Agent Skill

sc-improve 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

636

周安装

26

GitHub Stars

公开资料未说明

下载量

206
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:sc-improve(提高)
来源仓库:https://github.com/tony363/superclaude
仓库路径:skills/sc-improve
安装命令:
npx skills add tony363/superclaude --skill "sc-improve"
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

AgentSkills.tonpx skills
npx skills add tony363/superclaude --skill "sc-improve"

简介

sc-improve 用于查找、检索和筛选相关信息, 适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。

  • 可结合来源仓库、安装命令和原始 README 继续核验具体用法。
  • 安装前建议确认权限范围、维护状态, 以及是否会触发联网、命令执行或文件读写。

SKILL.md

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 imports

Behavioral Flow

  1. Analyze - Examine codebase for improvement opportunities
  2. Plan - Choose approach and activate relevant personas
  3. Execute - Apply systematic improvements
  4. Validate - Ensure functionality preservation
  5. Document - Generate improvement summary

Flags

FlagTypeDefaultDescription
--typestringqualityquality, performance, maintainability, style, principles, code, imports, files, all
--cleanupboolfalseEnable cleanup mode
--safebooltrueConservative with safety validation
--aggressiveboolfalseThorough cleanup (use with caution)
--previewboolfalseShow changes without applying
--interactiveboolfalseGuided 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)

ToolWhen to UsePurpose
mcp__pal__consensusComplex refactorsMulti-model validation before major changes
mcp__pal__codereviewQuality assessmentReview improvement quality and safety
mcp__pal__thinkdeepArchitecture changesDeep analysis of structural improvements
mcp__pal__precommitBefore commitValidate all changes preserve functionality
mcp__pal__debugRegression issuesRoot cause analysis if improvements break things
mcp__pal__challengeAggressive modeCritical 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)

ToolWhen to UsePurpose
mcp__rube__RUBE_SEARCH_TOOLSExternal toolsFind linters, formatters, analyzers
mcp__rube__RUBE_MULTI_EXECUTE_TOOLNotificationsUpdate tickets, notify team
mcp__rube__RUBE_CREATE_UPDATE_RECIPEReusable workflowsSave 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 . --json

Cleanup 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 validation

Performance Optimization

/sc:improve api-endpoints --type performance --interactive
# Guided optimization with profiling analysis

Dead Code Cleanup

/sc:improve src/ --cleanup --type code --safe
# Remove unused code with dependency validation

Preview Changes

/sc:improve --cleanup --type imports --preview
# Show what would be removed without executing

Tool Coordination

  • Read/Grep/Glob - Code analysis
  • Edit/MultiEdit - Safe modifications
  • TodoWrite - Progress tracking
  • Task - Large-scale improvement delegation

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

27.16%
按下载量换算56

Claude Code

22.92%
按下载量换算47

windsurf

17.64%
按下载量换算36

trae

13.38%
按下载量换算28

OpenCode

8.39%
按下载量换算17

Cursor

3.57%
按下载量换算7

安全审计

暂无安全审计结果可展示。

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add tony363/superclaude --skill "sc-improve" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills