OpnForm：实践指南
2026-09-12 3466078
2026-08-23 0
文件系统管理是一项综合技能，旨在为 AI 智能体提供对本地和远程文件系统的高级控制。作为 Openclaw Skills 生态系统的核心组件，它支持复杂的递归目录遍历、基于模式的过滤和深度内容搜索等操作。此工具专为需要自动化处理大量文件工作流的开发人员构建，允许智能体智能地导航项目结构、分析磁盘使用情况并管理资产，无需人工干预。通过与其他 Openclaw Skills 无缝集成，它提供了一种安全且结构化的方式来处理大规模数据。
下载入口:https://github.com/openclaw/skills/tree/main/skills/gtrusler/clawdbot-filesystem
从源直接安装技能的最快方式。
npx clawhub@latest install clawdbot-filesystem
将技能文件夹复制到以下位置之一
全局模式~/.openclaw/skills/
工作区
/skills/ 优先级：工作区 > 本地 > 内置
将此提示词复制到 OpenClaw 即可自动安装。
请帮我使用 Clawhub 安装 clawdbot-filesystem。如果尚未安装 Clawhub，请先安装（npm i -g clawhub）。
# 通过 ClawdHub 安装
clawdhub install filesystem
# 或克隆到您的技能目录中
cd ~/.clawdbot/skills
git clone https://github.com/gtrusler/clawdbot-filesystem
# 设置执行权限
chmod +x filesystem/filesystem
编辑 config.json 文件以定义默认行为：
{
"defaultPath": "./",
"excludePatterns": ["node_modules", ".git"],
"outputFormat": "table"
}
该技能通过本地 JSON 文件管理配置，并产生结构化输出供智能体使用。
| 属性 | 描述 |
|---|---|
defaultPath |
设置所有相对路径操作的基准目录。 |
excludePatterns |
定义扫描期间要忽略的目录或文件列表。 |
maxDepth |
控制递归目录遍历的深度以节省资源。 |
outputFormat |
确定结果以表格、JSON 还是纯列表形式返回。 |
name: filesystem
description: Advanced filesystem operations - listing, searching, batch processing, and directory analysis for Clawdbot
homepage: https://github.com/gtrusler/clawdbot-filesystem
metadata: {"clawdbot":{"emoji":"??","requires":{"bins":["node"]}}}
Advanced filesystem operations for AI agents. Comprehensive file and directory operations with intelligent filtering, searching, and batch processing capabilities.
# List files with filtering
filesystem list --path ./src --recursive --filter "*.js"
# Search for content
filesystem search --pattern "TODO" --path ./src --content
# Batch copy with safety
filesystem copy --pattern "*.log" --to ./backup/ --dry-run
# Show directory tree
filesystem tree --path ./ --depth 3
# Analyze directory structure
filesystem analyze --path ./logs --stats
filesystem listAdvanced file and directory listing with filtering options.
Options:
--path, -p - Target directory (default: current)--recursive, -r - Include subdirectories--filter, -f - Filter files by pattern--details, -d - Show detailed information--sort, -s - Sort by name|size|date--format - Output format: table|json|listfilesystem searchSearch files by name patterns or content.
Options:
--pattern - Search pattern (glob or regex)--path, -p - Search directory--content, -c - Search file contents--context - Show context lines--include - Include file patterns--exclude - Exclude file patternsfilesystem copyBatch copy files with pattern matching and safety checks.
Options:
--pattern - Source file pattern--to - Destination directory--dry-run - Preview without executing--overwrite - Allow file overwrites--preserve - Preserve timestamps and permissionsfilesystem treeDisplay directory structure as a tree.
Options:
--path, -p - Root directory--depth, -d - Maximum depth--dirs-only - Show directories only--size - Include file sizes--no-color - Disable colored outputfilesystem analyzeAnalyze directory structure and generate statistics.
Options:
--path, -p - Target directory--stats - Show detailed statistics--types - Analyze file types--sizes - Show size distribution--largest - Show N largest files# Clone or install the skill
cd ~/.clawdbot/skills
git clone
# Or install via ClawdHub
clawdhub install filesystem
# Make executable
chmod +x filesystem/filesystem
Customize behavior via config.json:
{
"defaultPath": "./",
"maxDepth": 10,
"defaultFilters": ["*"],
"excludePatterns": ["node_modules", ".git", ".DS_Store"],
"outputFormat": "table",
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"sizeFormat": "human",
"colorOutput": true
}
# Find all JavaScript files in src
filesystem list --path ./src --recursive --filter "*.js" --details
# Search for TODO comments
filesystem search --pattern "TODO|FIXME" --path ./src --content --context 2
# Copy all logs to backup
filesystem copy --pattern "*.log" --to ./backup/logs/ --preserve
# Analyze project structure
filesystem tree --path ./ --depth 2 --size
# Find large files
filesystem analyze --path /var/log --sizes --largest 10
# List recent files
filesystem list --path /tmp --sort date --details
# Clean old temp files
filesystem list --path /tmp --filter "*.tmp" --older-than 7d
Works seamlessly with other Clawdbot tools:
Stay informed about the latest Clawdbot skills and filesystem tools:
Get early access to new skills and improvements by following @LexpertAI for:
MIT License - Free for personal and commercial use.
Remember: Great filesystem management starts with the right tools. This skill provides comprehensive operations while maintaining safety and performance.