Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →datadrivenconstruction/input-validation
Validate construction data inputs before processing: cost estimates, schedules, BIM data, field reports. Catch errors early with domain-specific rules.
Passed 22 of 22 test cases with the skill, and 12 of 22 without it.
and 14 more in the full report
10 fixed12 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
In a site schedule, Crane_01 is assigned to Task 1 with 60% allocation and Task 2 with 50% allocation on overlapping dates. What issue severity is added to the validation result?
| Checked | Without skill | With skill |
|---|---|---|
| The combined allocation exceeding 100% triggers a ValidationSeverity WARNING. | Missed | Passed |
The instructions your model reads when the skill loads.
Validate incoming construction data before processing to catch errors early. Domain-specific validation rules for estimates, schedules, BIM exports, and field data.
from dataclasses import dataclass, field
from typing import List, Dict, Any, Callable, Optional
from enum import Enum
import re
from datetime import datetime
class ValidationSeverity(Enum):
ERROR = "error" # Must fix, blocks processing
WARNING = "warning" # Should review, allows processing
INFO = "info" # FYI, no action needed
@dataclass
class ValidationIssue:
field: str
message: str
severity: ValidationSeverity
value: Any = None
suggestion: str = None
@dataclass
class ValidationResult:
is_valid: bool
issues: List[ValidationIssue] = field(default_factory=list)
def add_error(self, field: str, message: str, value: Any = None, suggestion: str = None):
self.issues.append(ValidationIssue(field, message, ValidationSeverity.ERROR, value, suggestion))
self.is_valid = False
def add_warning(self, field: str, message: str, value: Any = None, suggestion: str = None):
test cases passed, vs 12 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.