industryby datadrivenconstruction
Labor Allocation Manager
datadrivenconstruction/labor-allocation
Allocate and track labor resources across project activities. Balance workload, track attendance, and optimize crew assignments.
What it changes
Passed 20 of 23 test cases with the skill, and 13 of 23 without it.
Without skill57%
With skill87%
Checks it passed that the model alone missed
- Reports total labor cost as $2,750.
- Formats third assignment identifier as 'ASN-0003'.
- Identifies 'hvac' as the valid trade enum string for HVAC technicians.
and 6 more in the full report
7 fixed13 passed either way3 still failing0 broke
- Pass-rate lift
- +30 pp
- Tokens
- +228%
- Agent turns
- 0%
- Response time
- -8%
Model gemini-3.6-flashMeasured 8/23/2026v120 of 23 cases passed with skill
See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWhen creating a new assignment record in the system, how is the assignment identifier formatted for the 3rd assignment added?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Formats third assignment identifier as 'ASN-0003'. | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md436 linessingle file
Labor Allocation Manager
Business Case
Problem Statement
Labor management challenges:
- Assigning workers to activities
- Balancing workload
- Tracking attendance
- Optimizing productivity
Solution
Systematic labor allocation and tracking to optimize resource utilization and maintain project schedule.
Technical Implementation
import pandas as pd
from typing import Dict, Any, List, Optional
from dataclasses import dataclass, field
from datetime import date, timedelta
from enum import Enum
from collections import defaultdict
class Trade(Enum):
CARPENTER = "carpenter"
ELECTRICIAN = "electrician"
PLUMBER = "plumber"
CONCRETE = "concrete"
MASON = "mason"
IRONWORKER = "ironworker"
HVAC = "hvac"
PAINTER = "painter"
LABORER = "laborer"
OPERATOR = "operator"
FOREMAN = "foreman"
class WorkerStatus(Enum):
Track record
Benchmark
20 / 23
test cases passed, vs 13 / 23 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
Importeddatadrivenconstruction / ddc_skills_for_ai_agents_in_construction
1_DDC_Toolkit/Resource-Management/labor-allocation/SKILL.md
View on GitHub ↗License MITImported 8/3/2026Version v1