电脑清理大师

v1.0.0

扫描并识别计算机中的重复文件,提供智能整理建议;当用户需要清理重复文件、释放磁盘空间或整理照片库时使用

0· 99·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for ludiansheng/duplicate-file-cleaner.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "电脑清理大师" (ludiansheng/duplicate-file-cleaner) from ClawHub.
Skill page: https://clawhub.ai/ludiansheng/duplicate-file-cleaner
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install ludiansheng/duplicate-file-cleaner

ClawHub CLI

Package manager switcher

npx clawhub@latest install duplicate-file-cleaner
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the included files: a Python scanner script (scripts/duplicate_scanner.py) that hashes files and produces a JSON report and the docs describe using that script. No unrelated credentials, binaries, or external services are requested.
Instruction Scope
SKILL.md instructs the agent to run the included scanner and to analyze the generated report. It also describes generating deletion scripts and optionally executing deletions. That behavior is consistent with a cleaner tool but is inherently destructive if performed without user confirmation. The instructions recommend backups and user confirmation, but they also give the agent discretion to assist in executing deletes — review/confirm before any deletion.
Install Mechanism
No install spec; the skill is instruction-plus-script and relies on Python standard library. No downloads, package managers, or external installers are invoked.
Credentials
The skill requests no environment variables, credentials, or config paths. The files and docs only operate on filesystem paths provided by the user, which is proportional to its purpose.
Persistence & Privilege
always:false and no install behavior means the skill does not demand permanent presence. The platform default allows autonomous invocation; combined with the skill's capability to generate/execute deletion scripts, this means an autonomous agent could delete files if granted permission — the skill itself does not persist or request elevated privileges.
Assessment
This skill appears to do what it says: it scans directories, hashes files to find exact duplicates, and can produce deletion scripts. Before running it: 1) Always back up important data. 2) Run scans with --output to save and inspect the JSON report before any deletions. 3) Restrict scans to non-system, limited directories (e.g., ~/Pictures or ~/Downloads) for initial runs. 4) If the agent proposes a deletion script, review it line-by-line and consider running a dry-run version (move files to a backup folder rather than permanently deleting). 5) Note SKILL.md shows an absolute example path (/workspace/projects/...), while README examples use scripts/duplicate_scanner.py — ensure you call the correct path in your environment. 6) If you will allow autonomous agent actions, grant that capability only if you trust the agent and are comfortable with it performing file operations; otherwise require explicit confirmation for delete actions.

Like a lobster shell, security has layers — review code before you run it.

latestvk975xp4jw4n9fp92tnwfczmckn84fkhc
99downloads
0stars
1versions
Updated 2w ago
v1.0.0
MIT-0

重复文件整理工具

任务目标

  • 本 Skill 用于:扫描指定目录,识别完全相同的重复文件,生成结构化报告并提供整理建议
  • 能力包含:文件内容哈希比对、重复文件分组、智能删除建议、磁盘空间分析
  • 触发条件:用户提到"重复文件"、"清理磁盘"、"整理照片"、"释放空间"等需求

操作步骤

1. 准备阶段

  • 确定要扫描的目录路径(用户需提供完整路径或相对路径)
  • 确认是否需要限制文件类型(如仅扫描图片)
  • 建议用户在操作前备份重要数据

2. 扫描阶段

  • 调用 scripts/duplicate_scanner.py 执行扫描:
    python /workspace/projects/duplicate-file-cleaner/scripts/duplicate_scanner.py \
      --directory <扫描目录> \
      --output <报告文件.json> \
      --min-size 1024 \
      --extensions jpg,png,pdf,mp4
    
  • 参数说明:
    • --directory:必填,要扫描的目录
    • --output:可选,输出报告文件路径(默认输出到终端)
    • --min-size:可选,最小文件大小(字节),默认 1024(1KB)
    • --extensions:可选,文件扩展名过滤,逗号分隔(如 jpg,png,gif)

3. 分析阶段

  • 智能体解读扫描报告,提供以下建议:
    • 识别重复文件的数量和类型分布
    • 计算可释放的磁盘空间
    • 基于文件路径和修改时间推荐保留策略
    • 生成删除清单(标注高风险文件)

4. 整理阶段

  • 根据智能体建议,用户可选择:
    • 自动删除:智能体生成批量删除脚本
    • 手动确认:逐个确认每个重复文件组的处理方式
    • 备份后删除:先将重复文件移动到备份目录
  • 智能体协助执行删除操作或生成操作脚本

资源索引

注意事项

  • ⚠️ 在删除文件前,建议用户先备份重要数据
  • ⚠️ 脚本仅检测文件内容完全相同的文件,不检测视觉相似的图片
  • ⚠️ 对于系统目录(如 Windows/Program Files),建议谨慎操作
  • 建议优先处理用户目录(如 Documents、Pictures、Downloads)
  • 智能体会基于文件路径和修改时间提供保留建议,但最终决策由用户确认

使用示例

示例1:扫描照片库

# 扫描照片目录,仅查找图片文件
python scripts/duplicate_scanner.py \
  --directory ~/Pictures \
  --output report.json \
  --min-size 10240 \
  --extensions jpg,png,heic

智能体分析后建议保留拍摄时间最早的版本。

示例2:全盘扫描

# 扫描整个用户目录,查找所有类型的重复文件
python scripts/duplicate_scanner.py \
  --directory ~ \
  --output report.json \
  --min-size 1024

智能体会提示可能需要较长时间,并建议优先处理大文件。

示例3:清理下载目录

# 扫描下载目录,查找大于100KB的重复文件
python scripts/duplicate_scanner.py \
  --directory ~/Downloads \
  --output report.json \
  --min-size 102400

智能体会识别重复下载的资源文件,推荐删除多余副本。

Comments

Loading comments...