Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →datadrivenconstruction/multi-agent-estimation
Build multi-agent AI systems for construction estimation. Use CrewAI/LangGraph to orchestrate specialized agents: QTO agent, pricing agent, validation agent. Automate complex estimation workflows.
Passed 11 of 22 test cases with the skill, and 7 of 22 without it.
and 2 more in the full report
4 fixed7 passed either way11 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
What role title and primary goal should be assigned to the cost estimator agent in a construction AI crew?
| Checked | Without skill | With skill |
|---|---|---|
| Sets the role title to Cost Estimator. | Passed | Passed |
| Sets the goal to match extracted quantities to CWICR database and apply unit rates. | Missed | Passed |
The instructions your model reads when the skill loads.
In 2026, AI agents are moving from single-task assistants to orchestrated multi-agent systems. This skill enables building a crew of specialized AI agents that work together to automate construction estimation.
"Thanks to LLM nodes, you can simply ask ChatGPT, Claude, or any advanced AI assistant to generate n8n automation pipelines — whether for extracting tables from PDFs, validating parameters, or producing custom QTO tables — and get ready-to-run workflows in seconds." — Artem Boiko
┌─────────────────────────────────────────────────────────────────┐
│ MULTI-AGENT ESTIMATION │
├─────────────────────────────────────────────────────────────────┤
│ │
│ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ │
│ │ QTO │ │ Pricing │ │Validation│ │ Report │ │
│ │ Agent │──▶│ Agent │──▶│ Agent │──▶│ Agent │ │
│ └──────────┘ └──────────┘ └──────────┘ └──────────┘ │
│ │ │ │ │ │
│ ▼ ▼ ▼ ▼ │
│ Extract Match to Validate Generate │
│ quantities CWICR DB totals Excel/PDF │
│ │
└─────────────────────────────────────────────────────────────────┘
from crewai import Agent, Task, Crew
from langchain_openai import ChatOpenAI
# Initialize LLM
llm = ChatOpenAI(model="gpt-4o", temperature=0)
# QTO Agent - Extracts quantities from documents
qto_agent = Agent(
role="Quantity Takeoff Specialist",
goal="Extract accurate quantities from IFC models and PDF drawings",
test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.