Validate material sample annotations against ontology constraints — check that class names and property names exist in the ontology, verify domain and range consistency for object property relationships, assess annotation completeness (required, recommended, and optional properties), and flag unknown or misspelled terms. Use when verifying that CMSO or other ontology annotations are correct before publishing, checking whether all required properties are present for a class like Crystal Structure or Unit Cell, auditing relationship triples between instances, or catching annotation errors early in a FAIR data workflow, even if the user only says "is my annotation correct" or "what am I missing."
インストール
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Validate material sample annotations against ontology constraints — check that class names and property names exist in the ontology, verify domain and range consistency for object property relationships, assess annotation completeness (required, recommended, and optional properties), and flag unknown or misspelled terms. Use when verifying that CMSO or other ontology annotations are correct before publishing, checking whether all required properties are present for a class like Crystal Structure or Unit Cell, auditing relationship triples between instances, or catching annotation errors early in a FAIR data workflow, even if the user only says "is my annotation correct" or "what am I missing."
allowed-tools
Read, Bash
metadata
{"author":"HeshamFS","version":"1.2.2","security_tier":"high","security_reviewed":true,"tested_with":["claude-code"],"last_evaluated":"2026-06-24","eval_cases":5,"last_reviewed":"2026-06-23","standards":["CMSO — Computational Material Sample Ontology v0.0.1 (OCDO, purls.helmholtz-metadaten.de/cmso/)","ASMO — Atomistic Simulation Methods Ontology (OCDO)","W3C OWL 2 / RDFS domain, range, and rdfs:subClassOf semantics","FAIR Guiding Principles (Wilkinson et al. 2016)"]}
Ontology Validator
Goal
Validate that material sample annotations comply with ontology constraints: correct class names, valid properties, consistent domain/range relationships, and required fields present.
Requirements
Python 3.10+
No external dependencies (Python standard library only)
Requires ontology-explorer's cmso_summary.json and ontology_registry.json
What do you need to validate?
├── An annotation (classes and properties are correct)
│ └── schema_checker.py --ontology cmso --annotation '<json>'
├── Completeness of a class annotation
│ └── completeness_checker.py --ontology cmso --class <name> --provided <props>
└── Object property relationships
└── relationship_checker.py --ontology cmso --relationships '<json>'
Script Outputs (JSON Fields)
Script
Key Outputs
scripts/schema_checker.py
results.valid, results.errors (each unknown_class/unknown_property error carries a suggestions array of nearest matches), results.warnings, results.class_valid, results.properties_valid
After mapping a sample with ontology-mapper, pass the annotations to schema_checker.py to verify correctness.
For a specific class, use completeness_checker.py to see what required/recommended properties are missing.
When building relationships between instances, use relationship_checker.py to ensure domain/range consistency.
Conversational Workflow Example
User: I annotated my sample as CrystalStructure with properties hasUnitCell and hasBasis.
Is this correct and complete?
Agent: Let me both validate the annotation and check its completeness.
[Runs: schema_checker.py --ontology cmso --annotation
'{"class":"Crystal Structure","properties":{"has unit cell":true,"has basis":true}}' --json]
[Runs: completeness_checker.py --ontology cmso --class "Crystal Structure"
--provided "has unit cell,has basis" --json]
From schema_checker.py (results.warnings):
- has unit cell: valid for Crystal Structure
- has basis: domain_mismatch warning — its domain is "Unit Cell", not
Crystal Structure (so this property belongs on the Unit Cell instance)
From completeness_checker.py (results, completeness_score = 0.5):
- **required_missing**: has space group
So: add "has space group" to the Crystal Structure annotation, and move
"has basis" onto the Unit Cell annotation. (The domain insight comes from
schema_checker.py's warnings; completeness_checker.py only reports the
missing required "has space group".)
Apply the nearest-match suggestions from the error, or use ontology-explorer to find the correct name
Property 'X' not found ... (did you mean 'Y'?)
Invalid/misspelled property name
Apply the nearest-match suggestions from the error, or use property_lookup.py to search
Annotation must be a dict
Wrong input format
Provide valid JSON dict
Relationships must be a non-empty list
Wrong input format
Provide JSON array of relationship dicts
Interpretation Guidance
Errors indicate definite problems (unknown class/property, range mismatch)
Warnings indicate potential issues (domain mismatch — may be intentional for subclasses)
Completeness score: 0.0-1.0 ratio of provided vs. total tracked
properties. It weights required, recommended, and optional properties
equally, so a moderate score (e.g. 0.5-0.67) can coexist with missing
required properties. ALWAYS check required_missing first: a non-empty
required_missing means the annotation is invalid regardless of the score.
required_missing: must fix for valid annotation
recommended_missing: should fix for quality
unrecognized: may indicate typos or properties from a different ontology
Verification checklist
Ran schema_checker.py --json and recorded results.valid; confirmed results.errors is an empty array (a valid:true with any unknown_class/unknown_property error cannot occur, but confirm the array length is 0 rather than trusting the boolean alone).
For every domain_mismatch entry in results.warnings, recorded the property, its reported domain, and the class it was applied to, then made an explicit keep-or-move decision (warnings are not auto-fixed and may be intentional for a subclass).
Ran completeness_checker.py --json and confirmed results.required_missing is empty BEFORE quoting completeness_score — a non-empty required_missing means the annotation is invalid no matter how high the score is.
Recorded the exact completeness_score together with the required_missing, recommended_missing, and optional_missing lists (do not paraphrase the score as "complete" while any required item is missing).
For each unknown class/property error, recorded the suggestions[0] value and confirmed the corrected name actually exists in the ontology (re-ran the checker, or checked via ontology-explorer) rather than assuming the top suggestion is right.
Ran relationship_checker.py --json for every subject-property-object triple and confirmed each per-triple results.results[i].valid is true; recorded any results.errors strings naming the offending domain or range.
Confirmed the --ontology used (e.g. cmso, asmo) matches the ontology the annotation was authored against — a class can be "unknown" simply because the wrong constraints/summary file was loaded.
Common pitfalls & rationalizations
Tempting shortcut
Why it's wrong / what to do
"completeness_score is 0.67, so the annotation is basically complete."
The score weights required, recommended, and optional tiers equally, so a high score can still hide a missing required property. Check required_missing first; a non-empty list means invalid regardless of score.
"schema_checker returned only warnings, no errors, so I'll ignore them."
domain_mismatch warnings flag a property attached to a class that is not (a subclass of) its domain — often the property belongs on a different instance. Record each warning and decide explicitly; don't auto-dismiss.
"The class name didn't match but the validator gave a suggestion, so I'll just use it."
suggestions come from stdlib difflib fuzzy matching (cutoff 0.6) and can be wrong or empty. Verify the suggested name exists in the ontology before applying it.
"Two of the three relationships passed, so the triples are fine."
results.valid is the AND over all triples; you must inspect each results.results[i] and its errors. A single failing domain/range check invalidates the relationship set.
"It returned valid:true, so the annotation is semantically correct."
The checker only verifies class/property existence and domain/range against a manually curated constraints file. It does not check data types, cardinality, or value plausibility — valid:true is necessary, not sufficient.
"Property exists in the ontology, so it applies to my class."
Existence is checked against the full property set; domain applicability is a separate subclass-aware check. A real property can still trigger a domain_mismatch warning on the wrong class.
"I'll trust the bare class name; substrings are close enough."
Domain/subclass matching is exact-equality plus parent traversal, NOT substring containment. Material is not credited with Crystalline Material properties; use the precise ontology class name.
Security
Input Validation
--ontology is validated against registered ontology names in ontology_registry.json (fixed allowlist)
--annotation JSON is parsed with json.loads() and validated as a dict with required class and properties keys
--class names are validated against known classes in the ontology summary; unknown classes produce clear errors
--provided property names are validated as comma-separated strings and matched against known properties
--relationships JSON is parsed and validated as a non-empty list of dicts, each requiring subject_class, property, and object_class keys
Size/length caps reject abusive input (exit code 2): raw JSON inputs and annotation files are capped at 1,000,000 bytes; at most 1000 annotations/relationships/provided properties per call; each class or property name is capped at 500 characters. Class and property names must be strings.
File Access
Scripts read pre-processed JSON files from the references/ directory: ontology_registry.json, cmso_summary.json, cmso_constraints.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 constraint data
Bash: Used to execute the three Python validation scripts (schema_checker.py, completeness_checker.py, relationship_checker.py) with explicit argument lists
Safety Measures
No eval(), exec(), or dynamic code generation
All subprocess calls use explicit argument lists (no shell=True)
JSON input parsing uses json.loads() only (no pickle, no YAML with unsafe loaders)
Validation logic operates on pre-loaded in-memory data structures; no dynamic file discovery or traversal
Limitations
Constraints file is manually curated, not derived from OWL axioms
Does not validate data types (e.g., whether a value is actually a float vs string)
Does not validate cardinality (e.g., exactly one space group per structure)
Subclass checking uses simple parent traversal, not full OWL reasoning
