Extract, clean, and organize legacy construction data from archives. Migrate historical project data, cost records, and schedules into modern formats.
SkillScore82Maintained
Automatic
◆Data Engineer pack
Last verified 8/23/2026
What it changes
Passed 18 of 22 test cases with the skill, and 8 of 22 without it.
Without skill36%
With skill82%
Checks it passed that the model alone missed
Maps 'total_amount' to 'amount'.
Classifies the record set data type as 'cost'.
Uses a cost index value of 0.82 for year 2015.
and 7 more in the full report
10 fixed8 passed either way4 still failing0 broke
Pass-rate lift
+45 pp
Tokens
+167%
Agent turns
0%
Response time
-15%
Model gemini-3.6-flashMeasured 8/23/2026v118 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
When inspecting legacy spreadsheet columns containing 'total', 'budget', and 'price', what data classification type should be automatically assigned to the extracted record set?
What was checked, without and with the skill
Checked
Without skill
With skill
Classifies the record set data type as 'cost'.
Missed
Passed
case-06 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md418 linessingle file
Historical Data Manager for Construction
Overview
Manage legacy construction data from archives, old systems, and historical records. Extract, clean, normalize, and migrate data into modern formats for analysis and benchmarking.
Business Case
Construction companies accumulate decades of project data in various formats:
Paper records scanned to PDF
Legacy database exports (Access, dBase, FoxPro)
Old spreadsheet formats (Lotus 1-2-3, early Excel)
Proprietary software exports
Project closeout documentation
This skill helps extract value from historical data for:
Cost benchmarking and trending
Productivity analysis over time
Risk pattern identification
Estimating improvement
Technical Implementation
Historical Data Extractor
from dataclasses import dataclass, field
from typing import List, Dict, Any, Optional
from datetime import datetime
from pathlib import Path
import pandas as pd
import re
import json
@dataclass
class HistoricalRecord:
project_id: str
project_name: str
year: int
data_type: str # cost, schedule, labor, material
Validate construction data inputs before processing: cost estimates, schedules, BIM data, field reports. Catch errors early with domain-specific rules.