Works with the AI Agents you already use
quantity takeoff checking
Validates quantity takeoff data, checks unit consistency, detects statistical outliers and anomalies, validates variance against expected values. Qualified estimator validates takeoffs. Decision support only.
$1.99
quantity takeoff checking
Example session with this skill installed
Validate this takeoff for Project Alpha: Item A1, 500 m2, Slab; Item A2, 550 m2, Slab; Item A3, 5200 m2, Slab (Drawing D-01). Tolerance 5%. Verify for outliers and unit consistency.
- Read your context and instructions
- Compiled the quantity takeoff checking
I have processed the takeoff data for Project Alpha using the validation script. The analysis identified one significant statistical outlier in the Slab category.
Quantity Takeoff Check Report
1. Summary
- Item Count: 3
- Completeness Rate: 100%
- Anomaly Count: 1
2. Category Statistics
| Category | Count | Sum | Min | Max | Mean | StdDev |
|---|---|---|---|---|---|---|
| Slab | 3 | 6,250.00 | 500.00 | 5,200.00 | 2,083.33 | 2,204.09 |
3. Unit Consistency
- Status: Consistent
- All items in the 'Slab' category use 'm2'. No mixed-unit issues detected.
4. Statistical Outliers
- Item A3: 5,200 m2 (Slab). Value is 1.41 standard deviations from the mean. Exceeds typical variance for this set.
5. Items Requiring Review
Item A3: Flagged for statistical anomaly. Verify if the quantity should be 520 m2 (potential decimal error) or if the scope change is valid for Drawing D-01.
6. Warnings
variance_check: Item A3 exceeds the default 5% variance threshold relative to the category mean.
7. Recommendations
- Analytical estimate — validation required: Inspect Item A3 on Drawing D-01 to confirm the 5,200 m2 measurement.
Analytical estimate — validation required: Recalculate category mean excluding Item A3 to establish a new baseline.
Next steps
- Review Drawing D-01 to verify the magnitude of Item A3.
- Update the takeoff with the corrected value if a decimal error is confirmed.
- Rerun the validation script to confirm the updated dataset passes all checks.
Connects securely to your tools. The creator never sees your data.
About this skill
Quantity takeoff errors lead to budget overruns and procurement delays. This skill validates takeoff data using deterministic scripts to identify unit inconsistencies, statistical outliers, and measurement anomalies before they reach the bid stage.
What it does
- Unit Validation checks for inconsistent Units of Measure (UoM) within the same category to prevent conversion errors.
- Statistical Auditing detects outliers using standard deviation and mean analysis to flag potential typos or decimal errors.
- Variance Testing compares measured quantities against expected values to highlight deviations exceeding defined tolerances.
- Completeness Metrics tracks drawing references and revision status to ensure no scope items are missing from the takeoff.
- Anomaly Flagging explicitly identifies negative quantities or data points requiring manual estimator review.
How it works
- Data Intake: The skill extracts quantity items, units, categories, and drawing references from your provided documents or text.
- Schema Generation: It constructs a structured
request.jsonfile following strict validation rules. - Execution: It runs a Python-based validation script (
run.py) to perform exact arithmetic and statistical checks. - Report Generation: It produces a standardized Markdown report summarizing category statistics, outliers, and items needing human review.
Frameworks & tools
This skill uses a Python 3 execution environment for deterministic processing. It relies on JSON schema validation for input integrity and implements standard statistical formulas for outlier detection.
Why this beats prompting it yourself
Generic LLM prompts often hallucinate arithmetic or overlook subtle unit mismatches in large tables. This skill uses a dedicated script for exact calculations, ensuring every flagged anomaly is based on deterministic logic rather than probabilistic guessing.
Use cases
- Auditing civil engineering takeoffs for unit consistency across multiple drawing sets.
- Identifying anomalous material quantities in MEP estimates before procurement.
- Verifying variance between current takeoff versions and historical project benchmarks.
- Generating documented QA reports for estimator peer reviews.
Known limitations
Does not perform OCR or BIM model extraction. It requires raw takeoff data as input and provides decision support rather than final legal approval.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Does not perform direct quantity extraction from drawings, OCR, or BIM integration. Requires structured or semi-structured takeoff data to function.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed today