filesystem
Advanced filesystem operations - listing, searching, batch processing, and directory analysis for Clawdbot
git clone --depth 1 https://github.com/opensquilla/opensquilla /tmp/filesystem && cp -r /tmp/filesystem/src/opensquilla/skills/bundled/filesystem ~/.claude/skills/filesystemSKILL.md
# 📁 Filesystem Management
Advanced filesystem operations for AI agents. Comprehensive file and directory operations with intelligent filtering, searching, and batch processing capabilities.
## OpenSquilla Compatibility Contract
When invoked from OpenSquilla, use the host-provided filesystem tools in the
current workspace. Do not install `clawdbot-filesystem`, do not call ClawHub,
and do not assume a standalone `filesystem` binary exists.
For `AwesomeWebpageMetaSkill` local packaging:
- Use only the `config.awesome_webpage.output_dir` supplied by the caller.
- Create or verify exactly:
- `project/index.html`
- `project/style.css`
- `project/script.js`
- `project/assets/images`
- `project/assets/audio`
- `project/assets/video`
- Keep all paths inside the current OpenSquilla workspace or the supplied
output directory.
- If generation did not produce files, return `PACKAGING_BLOCKED` with the
missing paths; do not try to discover unrelated config files.
## Features
### 📋 **Smart File Listing**
- **Advanced Filtering** - Filter by file types, patterns, size, and date
- **Recursive Traversal** - Deep directory scanning with depth control
- **Rich Formatting** - Table, tree, and JSON output formats
- **Sort Options** - By name, size, date, or type
### 🔍 **Powerful Search**
- **Pattern Matching** - Glob patterns and regex support
- **Content Search** - Full-text search within files
- **Multi-criteria** - Combine filename and content searches
- **Context Display** - Show matching lines with context
### 🔄 **Batch Operations**
- **Safe Copying** - Pattern-based file copying with validation
- **Dry Run Mode** - Preview operations before execution
- **Progress Tracking** - Real-time operation progress
- **Error Handling** - Graceful failure recovery
### 🌳 **Directory Analysis**
- **Tree Visualization** - ASCII tree structure display
- **Statistics** - File counts, size distribution, type analysis
- **Space Analysis** - Identify large files and directories
- **Performance Metrics** - Operation timing and optimization
## Quick Start
```bash
# 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
```
## Command Reference
### `filesystem list`
Advanced file and directory listing with filtering options.
**Options:**
- `--path, -p <dir>` - Target directory (default: current)
- `--recursive, -r` - Include subdirectories
- `--filter, -f <pattern>` - Filter files by pattern
- `--details, -d` - Show detailed information
- `--sort, -s <field>` - Sort by name|size|date
- `--format <type>` - Output format: table|json|list
### `filesystem search`
Search files by name patterns or content.
**Options:**
- `--pattern <pattern>` - Search pattern (glob or regex)
- `--path, -p <dir>` - Search directory
- `--content, -c` - Search file contents
- `--context <lines>` - Show context lines
- `--include <pattern>` - Include file patterns
- `--exclude <pattern>` - Exclude file patterns
### `filesystem copy`
Batch copy files with pattern matching and safety checks.
**Options:**
- `--pattern <glob>` - Source file pattern
- `--to <dir>` - Destination directory
- `--dry-run` - Preview without executing
- `--overwrite` - Allow file overwrites
- `--preserve` - Preserve timestamps and permissions
### `filesystem tree`
Display directory structure as a tree.
**Options:**
- `--path, -p <dir>` - Root directory
- `--depth, -d <num>` - Maximum depth
- `--dirs-only` - Show directories only
- `--size` - Include file sizes
- `--no-color` - Disable colored output
### `filesystem analyze`
Analyze directory structure and generate statistics.
**Options:**
- `--path, -p <dir>` - Target directory
- `--stats` - Show detailed statistics
- `--types` - Analyze file types
- `--sizes` - Show size distribution
- `--largest <num>` - Show N largest files
## Installation
```bash
# Clone or install the skill
cd ~/.clawdbot/skills
git clone <filesystem-skill-repo>
# Or install via ClawdHub
clawdhub install filesystem
# Make executable
chmod +x filesystem/filesystem
```
## Configuration
Customize behavior via `config.json`:
```json
{
"defaultPath": "./",
"maxDepth": 10,
"defaultFilters": ["*"],
"excludePatterns": ["node_modules", ".git", ".DS_Store"],
"outputFormat": "table",
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"sizeFormat": "human",
"colorOutput": true
}
```
## Examples
### Development Workflow
```bash
# 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
```
### System Administration
```bash
# 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
```
## Safety Features
- **Path Validation** - Prevents directory traversal attacks
- **Permission Checks** - Verifies read/write access before operations
- **Dry Run Mode** - Preview destructive operations
- **Backup Prompts** - Suggests backups before overwrites
- **Error Recovery** - Graceful handling of permission errors
## Integration
Works seamlessly with other Clawdbot tools:
- **Security Skill** - Validates all filesystem operations
- **Git Operations** - Respects .gitignore patterns
- **Backup Tools** - Integrates with backup workflows
- **Log Analysis** - Perfect for log file management
## Updates & Community
**Stay informed aboutSubmit audio or video for multilingual dubbing, poll status, and download dubbed audio. Use when the user asks for dubbing, 多语言配音, 视频翻译配音, 译制片, or wants a source clip dubbed into another language.
Generate a structured short-video shooting script from a topic. Emits a strict, machine-parseable shot list (3 shots by default) with image prompt + video prompt + voiceover + on-screen text per shot. Trigger when the user asks for a video script, 分镜, 短视频文案, AI视频, 短剧脚本, or wants visual prompts ready for image/video generation.
Use when the user asks to schedule recurring tasks, one-off reminders, timers, or cron-style jobs through the OpenSquilla cron tool.
Multi-round research with explicit methodology, evidence tracking, and citation-tagged synthesis. Trigger on 'deep dive', 'research report', 'literature review', 'investigate X across sources', 'multi-round investigation'. Distinct from the `summarize` skill, which is a single-pass condensation; this skill maintains a state file across iterations, tracks coverage, and produces a long-form report with per-claim citations. Three execution stages: plan (scope into sub-questions), iterate (record evidence per round), compile (synthesize report). The skill itself does not fetch the web — it tells the host agent which fetches to perform via OpenSquilla's existing web tools, and records what comes back.
Read, edit, or create Microsoft Word `.docx` files. Trigger this skill whenever the user mentions a Word document, .docx file, contract, report, brief, memo, or asks to extract text, modify an existing doc, generate one from a brief, or audit tracked changes. Three execution paths: text-and-structure extraction, in-place edit-by-run (preserves styles), and create-from-scratch with python-docx. Falls back to OOXML unzip-and-patch for layout work python-docx cannot reach.
Capture the current git diff (staged, working-tree, or staged file list) as text. Direct shell call for workflows that need repository diffs without an LLM agent loop.
GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.
Query the per-turn DecisionEntry log for skill co-occurrence patterns, meta-skill usage stats, and the router fixture corpus. Returns a JSON summary suitable for downstream LLM consumption. Used by meta-skill-creator's harvest step but also useful standalone for 'which skills did I use most this week?'