Ontology

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...

Security Scan

The skill is mostly a local, file-backed ontology (consistent with its description) but has several internal inconsistencies (Node vs Python, differing default paths, metadata mismatches) and writes append-only data to disk — review before use.

Purpose & Capability

The skill's declared purpose (typed knowledge graph / agent memory) matches the included Python tool and SKILL.md workflows. However skill.yaml claims Node compatibility (node >=18.0.0) while the provided implementation is a Python script (scripts/ontology.py). The SKILL.md uses memory/ontology/graph.jsonl as the default storage path but skill.yaml's ONTOLOGY_PATH default is '~/clawd/ontology' — inconsistent defaults that could cause confusion. Metadata owner IDs/homepage also differ across files. These mismatches are not clearly malicious but are incoherent and warrant clarification.

Instruction Scope

Runtime instructions restrict operations to local graph files (create/query/relate/validate) and emphasize append-only history and a schema that forbids storing secrets directly (Credential.secret_ref). The instructions and script operate on local files (memory/ontology/graph.jsonl and memory/ontology/schema.yaml) and do not instruct network calls or access to unrelated system files. Caution: append-only logs preserve history, so any sensitive data written into entities will remain on disk; the skill explicitly calls out not storing secrets directly but relies on users/other skills to follow that.

Install Mechanism

No install spec is provided (instruction-only), and there are no downloads or package installs. The single bundled script is a plain Python CLI. This is low-install risk.

Credentials

The skill declares no required environment variables or credentials. The only config is an ONTOLOGY_PATH in skill.yaml (a storage path). The code does not require or reference external secrets or cloud credentials. This is proportionate to its stated purpose.

Persistence & Privilege

always is false and the skill is user-invocable; it does normal local storage of its own data and does not request persistent privileges or modify other skills' configs. The append-only storage model gives it persistent local data — ordinary for this functionality.

What to consider before installing

This skill implements a local, append-only ontology stored on disk and the bundled Python CLI mostly matches the documentation. Before installing or enabling it: (1) Verify which storage path the agent will actually use (SKILL.md uses memory/ontology; skill.yaml sets ~/clawd/ontology) and adjust to a safe directory you control. (2) Confirm your environment runs Python (the implementation is Python) — skill.yaml's Node requirement is incorrect and should be clarified with the author. (3) Do not store secrets directly in the graph — the schema enforces secret_ref, but other skills or users might accidentally write sensitive values; treat the graph files as potentially sensitive and restrict file permissions. (4) Inspect the full scripts/ontology.py (particularly the truncated schema-loading/validation code) for any network I/O before granting broad access. (5) If you need cross-skill sharing, require skills to declare exact read/write contracts per the Skill Contract. These inconsistencies look like sloppy packaging rather than overtly malicious behavior, but confirm the above points before trusting the skill with sensitive data.

A typed vocabulary + constraint system for representing knowledge as a verifiable graph.

Core Concept

Everything is an entity with a type, properties, and relations to other entities. Every mutation is validated against type constraints before committing.

Entity: { id, type, properties, relations, created, updated }
Relation: { from_id, relation_type, to_id, properties }

When to Use

Trigger	Action
"Remember that..."	Create/update entity
"What do I know about X?"	Query graph
"Link X to Y"	Create relation
"Show all tasks for project Z"	Graph traversal
"What depends on X?"	Dependency query
Planning multi-step work	Model as graph transformations
Skill needs shared state	Read/write ontology objects

Core Types

# Agents & People
Person: { name, email?, phone?, notes? }
Organization: { name, type?, members[] }

# Work
Project: { name, status, goals[], owner? }
Task: { title, status, due?, priority?, assignee?, blockers[] }
Goal: { description, target_date?, metrics[] }

# Time & Place
Event: { title, start, end?, location?, attendees[], recurrence? }
Location: { name, address?, coordinates? }

# Information
Document: { title, path?, url?, summary? }
Message: { content, sender, recipients[], thread? }
Thread: { subject, participants[], messages[] }
Note: { content, tags[], refs[] }

# Resources
Account: { service, username, credential_ref? }
Device: { name, type, identifiers[] }
Credential: { service, secret_ref }  # Never store secrets directly

# Meta
Action: { type, target, timestamp, outcome? }
Policy: { scope, rule, enforcement }

Storage

Default: memory/ontology/graph.jsonl

{"op":"create","entity":{"id":"p_001","type":"Person","properties":{"name":"Alice"}}}
{"op":"create","entity":{"id":"proj_001","type":"Project","properties":{"name":"Website Redesign","status":"active"}}}
{"op":"relate","from":"proj_001","rel":"has_owner","to":"p_001"}

Query via scripts or direct file ops. For complex graphs, migrate to SQLite.

Append-Only Rule

When working with existing ontology data or schema, append/merge changes instead of overwriting files. This preserves history and avoids clobbering prior definitions.

Workflows

Create Entity

python3 scripts/ontology.py create --type Person --props '{"name":"Alice","email":"[e-mail]"}'

Query

python3 scripts/ontology.py query --type Task --where '{"status":"open"}'
python3 scripts/ontology.py get --id task_001
python3 scripts/ontology.py related --id proj_001 --rel has_task

Link Entities

python3 scripts/ontology.py relate --from proj_001 --rel has_task --to task_001

Validate

python3 scripts/ontology.py validate  # Check all constraints

Constraints

Define in memory/ontology/schema.yaml:

types:
  Task:
    required: [title, status]
    status_enum: [open, in_progress, blocked, done]
  
  Event:
    required: [title, start]
    validate: "end >= start if end exists"

  Credential:
    required: [service, secret_ref]
    forbidden_properties: [password, secret, token]  # Force indirection

relations:
  has_owner:
    from_types: [Project, Task]
    to_types: [Person]
    cardinality: many_to_one
  
  blocks:
    from_types: [Task]
    to_types: [Task]
    acyclic: true  # No circular dependencies

Skill Contract

Skills that use ontology should declare:

# In SKILL.md frontmatter or header
ontology:
  reads: [Task, Project, Person]
  writes: [Task, Action]
  preconditions:
    - "Task.assignee must exist"
  postconditions:
    - "Created Task has status=open"

Planning as Graph Transformation

Model multi-step plans as a sequence of graph operations:

Plan: "Schedule team meeting and create follow-up tasks"

1. CREATE Event { title: "Team Sync", attendees: [p_001, p_002] }
2. RELATE Event -> has_project -> proj_001
3. CREATE Task { title: "Prepare agenda", assignee: p_001 }
4. RELATE Task -> for_event -> event_001
5. CREATE Task { title: "Send summary", assignee: p_001, blockers: [task_001] }

Each step is validated before execution. Rollback on constraint violation.

Integration Patterns

With Causal Inference

Log ontology mutations as causal actions:

# When creating/updating entities, also log to causal action log
action = {
    "action": "create_entity",
    "domain": "ontology", 
    "context": {"type": "Task", "project": "proj_001"},
    "outcome": "created"
}

Cross-Skill Communication

# Email skill creates commitment
commitment = ontology.create("Commitment", {
    "source_message": msg_id,
    "description": "Send report by Friday",
    "due": "2026-01-31"
})

# Task skill picks it up
tasks = ontology.query("Commitment", {"status": "pending"})
for c in tasks:
    ontology.create("Task", {
        "title": c.description,
        "due": c.due,
        "source": c.id
    })

Quick Start

# Initialize ontology storage
mkdir -p memory/ontology
touch memory/ontology/graph.jsonl

# Create schema (optional but recommended)
python3 scripts/ontology.py schema-append --data '{
  "types": {
    "Task": { "required": ["title", "status"] },
    "Project": { "required": ["name"] },
    "Person": { "required": ["name"] }
  }
}'

# Start using
python3 scripts/ontology.py create --type Person --props '{"name":"Alice"}'
python3 scripts/ontology.py list --type Person

References

• references/schema.md — Full type definitions and constraint patterns
• references/queries.md — Query language and traversal examples

Instruction Scope

Runtime instructions operate on local files (memory/ontology/graph.jsonl and memory/ontology/schema.yaml) and provide CLI usage for create/query/relate/validate; this is within scope. The skill reads/writes workspace files and will create the memory/ontology directory when used. Validation includes property/enum/forbidden checks, relation type/cardinality validation, acyclicity for relations marked acyclic: true, and Event end >= start checks; other higher-level constraints may still be documentation-only unless implemented in code.