← Back to Skills Marketplace
Ontology Mapper
by
datadrivenconstruction
· GitHub ↗
· v2.1.0
1330
Downloads
0
Stars
13
Active Installs
2
Versions
Install in OpenClaw
/install ontology-mapper
Description
Map construction data to standard ontologies. Create semantic mappings between different data schemas
Usage Guidance
This skill appears to do what it says: map construction data to ontologies using Python and reading user-provided files. Before installing or invoking it, only give it the files you want processed (avoid sending system or credential files), confirm the homepage/owner if provenance matters, and prefer manual review of any exported mappings before sharing them externally. Because the package requests filesystem access in its metadata, treat that as the main risk vector: restrict inputs to project data and do not expose secrets.
Capability Analysis
Type: OpenClaw Skill
Name: ontology-mapper
Version: 2.1.0
The skill's Python code in SKILL.md is benign, performing ontology mapping without any direct file system, network, or shell interactions. However, the `claw.json` manifest requests `filesystem` permission. While the `instructions.md` implicitly justifies this permission by mentioning handling 'file paths' for input and offering 'export to Excel/CSV/JSON' for output (implying the agent will perform file I/O around the skill's core logic), this broad permission represents a significant attack surface. If the AI agent were vulnerable to prompt injection, this permission could be abused to read or write arbitrary files, classifying it as a vulnerability and thus 'suspicious' rather than 'benign'.
Capability Assessment
Purpose & Capability
Name/description (ontology mapping) align with the declared requirements: python3 is required and the SKILL.md contains Python-based mapping classes and logic. Requesting filesystem access in claw.json is reasonable for reading user-supplied CSV/Excel/JSON files.
Instruction Scope
instructions.md and SKILL.md focus on processing data the user supplies and producing mapping reports. The skill documentation explicitly constrains operations to user-provided data, but the claw.json grants generic filesystem permission—this is required for file-based inputs but means the skill could read files if misused. No instructions were found that direct the agent to read unrelated system files or environment secrets.
Install Mechanism
There is no install spec and no code files to write/execute on install (instruction-only). This minimizes installation risk. The only runtime requirement is python3, which matches the provided code examples.
Credentials
The skill declares no required environment variables or credentials. That is proportional to the described task of local data mapping. No evidence in the provided files of attempts to access unrelated credentials or external services.
Persistence & Privilege
always is false (normal) and disable-model-invocation is false (normal autonomous invocation). claw.json includes a broad 'filesystem' permission which is appropriate for reading input files but is a sensitive permission—users should avoid supplying sensitive system files. The skill does not request persistent system-wide privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ontology-mapper - After installation, invoke the skill by name or use
/ontology-mapper - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.1.0
- Added detailed documentation and class definitions to SKILL.md, outlining ontology types, mapping confidence, relation types, and data classes for semantic mapping.
- Included Python code examples for ontology mapping, loading standard construction ontologies (IFC, COBie, Uniclass, MasterFormat) using DDC methodology.
- Enhanced transparency of mapping logic and data structures for improved adoption and developer understanding.
- Improved quick start section to guide users on how to leverage the mapping capability.
v1.0.0
Ontology Mapper 1.0.0 — Initial release.
- Introduces semantic mapping functionality for construction data using standard ontologies (IFC, COBie, Uniclass, OmniClass, etc.).
- Provides structured classes for ontology concepts, mapping relations, and mapping confidence.
- Supports generation of mapping reports, including mapping coverage and recommendations.
- Enables creation and management of semantic relationships between different data schemas for improved interoperability.
- Based on the DDC methodology (Chapter 2.2) and referenced in "Open Data Dominance".
Metadata
Frequently Asked Questions
What is Ontology Mapper?
Map construction data to standard ontologies. Create semantic mappings between different data schemas. It is an AI Agent Skill for Claude Code / OpenClaw, with 1330 downloads so far.
How do I install Ontology Mapper?
Run "/install ontology-mapper" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Ontology Mapper free?
Yes, Ontology Mapper is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Ontology Mapper support?
Ontology Mapper is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux, win32).
Who created Ontology Mapper?
It is built and maintained by datadrivenconstruction (@datadrivenconstruction); the current version is v2.1.0.
More Skills