name: ontology-mapper description: > Map materials science terms, crystal structures, and sample descriptions to standardized ontology classes and properties — resolve natural-language concepts to ontology entries with confidence scores, translate Bravais lattice types, space groups, and lattice constants into ontology-compliant annotations, and produce full sample metadata from structured descriptions. Supports any ontology in ontology_registry.json (CMSO, ASMO, etc.). Use when annotating simulation inputs with FAIR metadata, translating "BCC iron" or "FCC copper" into formal ontology terms, preparing machine- readable sample descriptions, or bridging between lab vocabulary and ontology vocabulary, even if the user only says "what CMSO terms describe my material" or "annotate this sample for me." allowed-tools: Read, Grep, Glob metadata: author: HeshamFS version: "1.1.0" security_tier: low security_reviewed: true tested_with: - claude-code - gemini-cli - vs-code-copilot eval_cases: 2 last_reviewed: "2026-03-26"

Ontology Mapper

Goal

Translate real-world materials science descriptions into standardized ontology annotations. Given terms like "FCC copper" or structured data like {"material": "iron", "structure": "BCC", "lattice_a": 2.87}, produce the corresponding ontology classes and properties for any registered ontology.

Requirements

• Python 3.8+
• No external dependencies (Python standard library only)
• Requires ontology-explorer's summary JSON and ontology_registry.json
• Per-ontology mapping config (<name>_mappings.json) for ontology-specific synonyms and labels

Inputs to Gather

Decision Guidance

What do you need to map?
├── A concept or term to find its ontology class
│   └── concept_mapper.py --ontology <name> --term "<term>"
├── Crystal structure parameters to ontology terms
│   └── crystal_mapper.py --ontology <name> --bravais <type> --space-group <N> --a <val>
├── A full sample description to ontology annotations
│   └── sample_annotator.py --ontology <name> --sample '<json>'
└── Multiple terms at once
    └── concept_mapper.py --ontology <name> --terms "term1,term2,term3"

Script Outputs (JSON Fields)

Workflow

1. If the user provides natural-language terms, use concept_mapper.py to find matching ontology classes.
2. If the user describes crystal structure parameters, use crystal_mapper.py to map them and validate constraints.
3. For a complete sample description, use sample_annotator.py to produce full ontology annotations.
4. Review any validation warnings (e.g., lattice parameter mismatches for the crystal system).
5. Check unmapped_fields and suggested_properties for completeness.

Conversational Workflow Example

User: I'm setting up an MD simulation of BCC iron with lattice parameter 2.87 angstroms.
      What CMSO terms should I use?

Agent: Let me map your iron sample to CMSO ontology terms.

[Runs: sample_annotator.py --ontology cmso --sample '{"material":"iron","structure":"BCC","lattice_a":2.87,"space_group":229}' --json]

Your BCC iron simulation maps to these CMSO annotations:

- **Sample**: Atomic Scale Sample (subclass of Computational Sample)
- **Material**: Crystalline Material
- **Unit Cell**: Bravais lattice = "cI" (body-centered cubic)
- **Space Group**: number = 229 (Im-3m)
- **Lattice**: a = 2.87 Å
- **Element**: Fe

Suggested additions:
- Number of atoms in the simulation cell
- Simulation cell vectors and angles

CLI Examples

# Map a single concept
python3 skills/ontology/ontology-mapper/scripts/concept_mapper.py \
  --ontology cmso --term "space group" --json

# Map multiple terms
python3 skills/ontology/ontology-mapper/scripts/concept_mapper.py \
  --ontology cmso --terms "FCC,copper,lattice constant" --json

# Map crystal parameters (with ontology-specific labels)
python3 skills/ontology/ontology-mapper/scripts/crystal_mapper.py \
  --ontology cmso --bravais FCC --space-group 225 --a 3.615 --json

# Map crystal parameters (generic labels, no ontology specified)
python3 skills/ontology/ontology-mapper/scripts/crystal_mapper.py \
  --bravais FCC --space-group 225 --a 3.615 --json

# Annotate a full sample
python3 skills/ontology/ontology-mapper/scripts/sample_annotator.py \
  --ontology cmso \
  --sample '{"material":"copper","structure":"FCC","space_group":225,"lattice_a":3.615}' \
  --json

Adding a New Ontology

To support a new ontology (e.g., ASMO), create a <name>_mappings.json in references/:

{
  "ontology": "asmo",
  "synonyms": { "simulation method": "Simulation Method", ... },
  "property_synonyms": { "timestep": "has timestep", ... },
  "material_type_rules": { "keyword_rules": [...], "default": "Material" },
  "sample_schema": { "sample_class": "Simulation", ... },
  "crystal_output": { "base_classes": [...], "property_map": {...} },
  "annotation_routing": { "unit_cell_indicators": [...], ... }
}

Then add "mappings_file": "asmo_mappings.json" to the ontology's entry in ontology_registry.json. No code changes needed.

Error Handling

Interpretation Guidance

• Confidence scores: 1.0 = exact match, 0.9 = synonym match, 0.7 = substring match, 0.5 = description match
• Validation warnings: indicate potential mistakes (e.g., specifying a!=b for cubic). These are warnings, not errors — the mapping still proceeds.
• Unmapped fields: input keys that the annotator doesn't recognize. These may need manual mapping.
• Suggested properties: additional ontology properties that would make the annotation more complete.

Security

Input Validation

• --ontology is validated against registered ontology names in ontology_registry.json (fixed allowlist)
• --term and --terms are length-limited and used only for substring matching against pre-processed synonym tables (never interpolated into code)
• --bravais is validated against a fixed set of recognized lattice type symbols
• --space-group is validated as an integer between 1 and 230
• Lattice parameters (--a, --b, --c, --alpha, --beta, --gamma) are validated as finite positive numbers
• --sample JSON is parsed with json.loads() and validated as a non-empty dict; keys and values are type-checked

File Access

• Scripts read pre-processed JSON files from the references/ directory: ontology_registry.json, *_mappings.json, *_summary.json, crystal_systems.json, element_data.json (all read-only)
• No scripts write to the filesystem; all output goes to stdout
• No network access is required

Tool Restrictions

• Read: Used to inspect script source, reference files, and ontology data
• Grep: Used to search reference files for mapping patterns or ontology terms
• Glob: Used to locate reference files and ontology data
• Notably, this skill has no Bash or Write access, giving it the lowest attack surface of all skills

Safety Measures

• No eval(), exec(), or dynamic code generation
• No subprocess calls of any kind; all logic runs within Python scripts invoked by the agent
• No file writes; the skill is purely read-only and analytical
• Minimal tool surface (Read, Grep, Glob only) means the agent cannot execute arbitrary commands or modify the filesystem

Limitations

• Concept mapping uses string matching and a per-ontology synonym table; it does not understand arbitrary natural language
• Crystal system validation checks basic constraints only (not all crystallographic rules)
• The element resolver recognizes common element names and symbols but may miss unusual spellings
• Bravais lattice aliases cover common usage (FCC, BCC, HCP) but not all crystallographic notation variants

References

• Mapping Patterns — common mapping examples
• Crystal Systems — crystal system definitions and Bravais lattices
• Element Data — periodic table data
• CMSO Mappings — CMSO-specific synonym tables and annotation config
• CMSO Guide — CMSO ontology overview

Version History