Desktop Cleanup Playbook

为桌面文件生成整理方案、分类规则和阶段性清理计划，先分析再行动。；use for desktop, cleanup, organization workflows；do not use for 自动删除桌面文件, 越权访问系统目录.

Security Scan

The skill’s files, runtime instructions, and single Python helper are coherent with a read-only 'directory audit' desktop-cleanup purpose and do not request unrelated credentials or perform network operations.

Purpose & Capability

Name and description describe generating desktop organization plans; the included spec.json and scripts/run.py implement a directory_audit mode that reads a provided directory or input and produces structured, read-only reports. Requested binary (python3) is appropriate and proportional.

Instruction Scope

SKILL.md explicitly instructs the agent to analyze first and not to delete or access system directories. The script likewise performs read-only scanning and pattern checks. Note: these are advisory controls — nothing enforces the 'no deletion / no overreach' rule if a user or other code runs commands outside the skill (but the skill itself does not perform deletions or remote calls).

Install Mechanism

No install spec; it's instruction-only with a local Python script that uses only the standard library. No downloads or package installs are required.

Credentials

The skill declares no environment variables, no credentials, and no config paths. Its behavior (reading files from a provided path) is consistent with the stated purpose.

Persistence & Privilege

always is false and the skill is user-invocable; it does not request elevated or persistent privileges and does not modify other skills or system-wide settings.

Assessment

This skill appears to do what it says: read a directory (or an input file) and produce a read-only desktop-cleanup plan. Before running: 1) don’t point it at system root or directories containing sensitive private keys/credentials; run it on a copy or limited test directory first; 2) prefer --dry-run or run without an output path to inspect results before writing files; 3) review scripts/run.py yourself (it’s short and uses only the standard library) if you have extra caution; 4) the 'no deletion / no overreach' rule is advisory — the skill won’t delete files, but other tools or manual actions could, so review any follow-up execution steps carefully.

桌面整理作战手册

你是什么

你是“桌面整理作战手册”这个独立 Skill，负责：为桌面文件生成整理方案、分类规则和阶段性清理计划，先分析再行动。

Routing

适合使用的情况

• 给我桌面整理方案
• 先分析不要直接动文件
• 输入通常包含：桌面目录路径
• 优先产出：现状概览、分类建议、确认清单

不适合使用的情况

• 不要自动删除桌面文件
• 不要越权访问系统目录
• 如果用户想直接执行外部系统写入、发送、删除、发布、变更配置，先明确边界，再只给审阅版内容或 dry-run 方案。

工作规则

1. 先把用户提供的信息重组成任务书，再输出结构化结果。
2. 缺信息时，优先显式列出“待确认项”，而不是直接编造。
3. 默认先给“可审阅草案”，再给“可执行清单”。
4. 遇到高风险、隐私、权限或合规问题，必须加上边界说明。
5. 如运行环境允许 shell / exec，可使用：
   • python3 "{baseDir}/scripts/run.py" --input <输入文件> --output <输出文件>
6. 如当前环境不能执行脚本，仍要基于 {baseDir}/resources/template.md 与 {baseDir}/resources/spec.json 的结构直接产出文本。

标准输出结构

请尽量按以下结构组织结果：

• 现状概览
• 分类建议
• 短期清理
• 长期规则
• 误删风险
• 确认清单

本地资源

• 规范文件：{baseDir}/resources/spec.json
• 输出模板：{baseDir}/resources/template.md
• 示例输入输出：{baseDir}/examples/
• 冒烟测试：{baseDir}/tests/smoke-test.md

安全边界

• 默认只输出方案和预案。
• 默认只读、可审计、可回滚。
• 不执行高风险命令，不隐藏依赖，不伪造事实或结果。