ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Why use this skill?
Manage structured agent memory with the Ontology skill. Create, query, and link entities for robust knowledge graphs and composable skills.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/oswalpalash/ontologyWhat This Skill Does
The Ontology skill provides a robust mechanism for agents to manage structured knowledge. It functions as a typed knowledge graph, allowing for the creation, querying, and linking of entities such as People, Projects, Tasks, Events, and Documents. This skill is designed to build a verifiable graph of information, enforcing constraints on data types and relationships to ensure data integrity. It's particularly useful for maintaining agent memory, enabling composable skills by providing a shared state, and facilitating complex planning by modeling actions as graph transformations. The skill supports CRUD operations on entities, dependency analysis, and cross-skill data access, making it a foundational tool for intelligent agent behavior.
Installation
To install the Ontology skill, use the following command:
clawhub install openclaw/skills/skills/oswalpalash/ontology
This command will fetch the skill from the source repository, which is openclaw/skills.
Use Cases
This skill is ideal for scenarios requiring structured data management and inter-entity relationships:
- Persistent Memory: Store and retrieve information about people, projects, tasks, events, documents, and more.
- Project Management: Track projects, their associated tasks, deadlines, owners, and dependencies.
- Relationship Mapping: Link related entities, such as associating a document with a project or a person with a task.
- Dependency Tracking: Visualize and query what tasks or projects depend on a specific entity, or what an entity depends on.
- Complex Planning: Model multi-step actions as transformations within the knowledge graph.
- Shared State: Provide a common data layer for multiple skills to interact with.
- Data Validation: Ensure data consistency through predefined type constraints and schema.
Example Prompts
- "Remember that Alice is working on the 'Website Redesign' project and her email is [email protected]."
- "What are all the open tasks assigned to Bob?"
- "Link the 'Project Proposal Document' to the 'Website Redesign' project."
Tips & Limitations
- Data Persistence: By default, the ontology data is stored in
memory/ontology/graph.jsonl. For larger or more complex graphs, consider migrating to a SQLite backend for better performance. - Append-Only Operations: When modifying existing ontology data or schema, always append or merge changes rather than overwriting files. This preserves historical data and prevents accidental data loss.
- Schema Definition: Define custom entity types and constraints in
memory/ontology/schema.yaml. - Command-Line Interface: The skill offers a CLI for creating, querying, relating, and validating entities. See the skill's documentation for detailed command usage.
- Complexity: While powerful, managing very large and highly interconnected graphs can become complex. Plan your schema and relationships carefully.
- Secret Management: Avoid storing sensitive information like passwords directly. Use
Credentialentities withsecret_refto reference secure storage.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-oswalpalash-ontology": {
"enabled": true,
"auto_update": true
}
}
}