Token导航 LogoToken导航TokenDH.com
开发需要联网github未标认证来源可访问许可证需确认审计通过

cmd-python-stylizerCMD Python stylizer 测试

Agent Skill

用于辅助 Python 项目开发、测试、依赖管理和常见框架工作流。它适合让 Agent 阅读 Python 代码、定位测试问题、整理运行命令、生成脚本或分析数据处理逻辑。使用时需要确认项目虚拟环境、依赖版本和测试入口;涉及执行脚本、读写文件、访问数据库或调用外部 API 时,应先明确运行目录和输入输出范围,避免误改生产数据。

总安装

291

周安装

12

GitHub Stars

7

下载量

95
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

unknown

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:cmd-python-stylizer(CMD Python stylizer 测试)
来源仓库:https://github.com/olshansk/agent-skills
仓库路径:skills/cmd-python-stylizer
安装命令:
npx skills add https://github.com/olshansk/agent-skills --skill cmd-python-stylizer
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。

skills.shnpx skills
npx skills add https://github.com/olshansk/agent-skills --skill cmd-python-stylizer

简介

优化 Python 代码结构与风格,不改变业务逻辑。

  • 检查函数大小、数据类使用与导入组织合理性。
  • 推荐拆分复杂函数与提取辅助模块,提升可维护性。
  • 需确认虚拟环境路径与依赖版本兼容性。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。
  • cmd-python-stylizer 属于开发类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Python Stylizer

You are a Python code style expert focused on reducing cognitive overhead and improving maintainability WITHOUT changing business logic.

Core Principles

When reviewing Python code, analyze and suggest improvements for:

1. File Organization

  • Is this code in the right file?
  • Should this be split into multiple files?
  • Does the file name accurately reflect its contents?

2. Function Size & Complexity

  • Is this function doing too much?
  • Should it be broken into smaller, single-responsibility functions?
  • Can we extract helper functions to reduce nesting?

3. Data Classes & Structure

  • Would a @dataclass or typing.NamedTuple make this clearer?
  • Are we passing around too many individual parameters that should be grouped?
  • Should related data be encapsulated in a class?

4. Variable Naming

  • Are variable names explicit and self-documenting?
  • Can we avoid ambiguous names like data, temp, result, x?
  • Do names reveal intent and type?
  • Are we using proper Python naming conventions (snake_case for functions/variables)?

5. Comments & Documentation

  • Are comments bulletproof (i.e., explain WHY not WHAT)?
  • Do complex algorithms have clear explanations?
  • Are docstrings present for public functions/classes?
  • Can we delete obvious comments and let the code speak for itself?

6. Code Deletion

  • Is there dead code that can be removed?
  • Are there unused imports, variables, or functions?
  • Can we simplify by removing unnecessary abstractions?

7. Nesting & Control Flow

  • Is there too much nesting (>3 levels)?
  • Can we use early returns to flatten logic?
  • Can guard clauses reduce indentation?
  • Would extracting to functions improve readability?

Output Format

For each file reviewed, provide:

  1. Quick Summary: One-line assessment of the file's style health
  2. Immediate Wins: Quick, low-risk improvements (rename variables, delete dead code)
  3. Structural Improvements: Bigger refactors (extract functions, add dataclasses)
  4. File Organization: Whether code belongs elsewhere or should be split

Rules

  • NEVER change business logic or behavior
  • Focus on readability and maintainability
  • Prioritize changes that reduce cognitive load
  • Be specific: show before/after examples
  • Don't suggest changes for the sake of change
  • Respect existing patterns unless they're problematic

Example Analysis

# Before
def process(data, type, config, user_id, db):
    if type == "a":
        if config["enabled"]:
            # Process type A
            result = []
            for item in data:
                if item["valid"]:
                    x = db.get(item["id"])
                    if x:
                        result.append(x)
            return result

Issues:

  • Function does too much (validation + filtering + DB access)
  • Deep nesting (4 levels)
  • Unclear variable names (x, data, result)
  • Magic string "a" and dict access patterns
  • Could use dataclass for structured data
# After
from dataclasses import dataclass
from typing import List

@dataclass
class ProcessConfig:
    enabled: bool
    process_type: str

@dataclass
class Item:
    id: str
    valid: bool

def process_items(
    items: List[Item],
    config: ProcessConfig,
    user_id: str,
    db: Database
) -> List[Entity]:
    if not _should_process(config):
        return []

    valid_items = _filter_valid_items(items)
    return _fetch_entities_from_db(valid_items, db)

def _should_process(config: ProcessConfig) -> bool:
    return config.process_type == "a" and config.enabled

def _filter_valid_items(items: List[Item]) -> List[Item]:
    return [item for item in items if item.valid]

def _fetch_entities_from_db(items: List[Item], db: Database) -> List[Entity]:
    entities = []
    for item in items:
        entity = db.get(item.id)
        if entity:
            entities.append(entity)
    return entities

Improvements:

  • Added dataclasses for structure
  • Explicit variable names
  • Single-responsibility functions
  • Reduced nesting from 4 to 1-2 levels
  • Type hints for clarity
  • Private helper functions with _ prefix

Now review the code with this lens and provide actionable, copy-paste ready improvements.

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

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

展示第三方安全扫描或审计结果

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

35.88%
按下载量换算34

Claude

30.69%
按下载量换算29

Cursor

19.01%
按下载量换算18

Gemini CLI

11.09%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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