An intelligent file management system that implements semantic headers and a SQLite database to organize, tag, and validate project assets.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ghostcatalog
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install ghostcatalog using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Ghost Catalog?
Ghost Catalog is a robust technical skill designed to bring structural integrity to any codebase through the Ghost Catalog semantic file header system (SOM-XXX-NNNN-vX.X.X). By embedding structured metadata directly into the first 20 lines of a file, it enables developers and AI agents to maintain a searchable, validated, and highly organized workspace. As part of the Openclaw Skills ecosystem, this tool automates the discovery of untagged files and ensures every asset is properly categorized and versioned.
The skill operates by bridging the gap between raw files and a structured SQLite database. It supports a wide array of programming languages and file formats, adapting its comment syntax to match the environment. Whether you are onboarding to a legacy project or starting a new build, Ghost Catalog provides the visibility needed to manage complex file systems with ease.
Ghost Catalog Use Cases
- Discovering and identifying untagged files within a large or unfamiliar codebase.
- Onboarding to a new project by generating a comprehensive semantic catalog of all assets.
- Maintaining organizational compliance through automated header validation and duplicate ID detection.
- Searching for specific project files by category, custom tags, or the specific agent that modified them.
- Generating detailed markdown compliance reports for project stakeholders and documentation.
How Ghost Catalog Works
- The agent performs a workspace scan, applying layered ignore logic from .ghost_ignore and .gitignore to filter out dependencies and build artifacts.
- Each file is checked for the presence of a SOM header within the first 20 lines to determine its current catalog status.
- The system parses existing headers to update the local SQLite database or flags files as untagged if no header is found.
- Users can invoke tagging commands to automatically generate and prepend headers based on file extension and category sequence numbers.
- The database synchronizes metadata including checksums, categories, and agent IDs to provide a persistent record of the workspace state.
- Validation routines run to ensure that file IDs, versions, and filenames remain consistent across the entire project.
Ghost Catalog Setup
To begin using this skill within Openclaw Skills, ensure your workspace is ready for local database storage. The skill will automatically initialize the SQLite database at data/ghost-catalog.db upon its first run.
# Trigger an initial scan to identify untagged files
/ghost-catalog scan
# Tag a specific directory or file pattern
/ghost-catalog tag src/components/
# Validate existing headers for compliance
/ghost-catalog validate
Ghost Catalog Data Schema & Taxonomy
The Ghost Catalog organizes data using a relational SQLite schema and a specific header taxonomy.
Database Tables
| Table | Description |
|---|---|
file_catalog |
Stores primary metadata including file_id, path, category, and version. |
file_tags |
Maps specific files to searchable keywords and tags. |
agent_registry |
Records the identity and activity of AI agents interacting with the files. |
SOM File ID Format
Files are identified using the schema SOM-XXX-NNNN-vX.X.X, where:
SOM: The constant namespace.XXX: A 3-letter category code (e.g., SCR for Script, DOC for Document).NNNN: A 4-digit sequential identifier.vX.X.X: The semantic version of the file.
Ghost Catalog Advanced Features
- Smart comment adaptation for Python, JavaScript, HTML, CSS, SQL, and Markdown file types.
- Multi-agent tracking using unique agent IDs to see which model performed specific updates.
- Fuzzy search capabilities across name, description, and metadata fields for rapid file discovery.
- Integrated sequence management that ensures unique file IDs are generated globally per category.
- Layered exclusion system that respects both standard git ignores and custom catalog-specific filters.
SKILL.md
Loading
Related Openclaw Skills
Ghost Catalog
Ghost Catalog provides a semantic file header system and SQLite database to scan, tag, and organize files within any workspace for better discoverability and compliance.
Lobster Trap
A shared digital whiteboard for synchronized management of notes, code snippets, and key labels via API.
OpenDex API Skill
A high-performance interface for retrieving Solana market data and community-driven token insights.
Multi Search Engine Integration
A comprehensive search integration providing access to 17 global and Chinese search engines without the need for API keys.
Improve Skill: The Meta-Skill
A meta-skill designed to evaluate and optimize other skills by identifying gaps in logic, codebase fit, and output quality.
ClawMeter
A self-hosted dashboard for monitoring OpenClaw API spending and token usage with real-time budget alerts.
Featured*
