Works with the AI Agents you already use
production yield analysis
Manual yield tracking often relies on disconnected spreadsheets, leading to inconsistent formulas and hidden quality costs.
$1.99
production yield analysis
Example session with this skill installed
Analyze batch records for the last two weeks. Batch B001: 1000 in, 950 out, 10 dimensional defects, 40 surface. Batch B002: 500 in, 480 out, 10 material, 10 assembly. Unit cost $50.
- Read your context and instructions
- Compiled the production yield analysis
Analysis complete for 2 batches. I have processed the yield metrics, defect Pareto distribution, and loss cost estimates based on a $50 unit cost.
Production Yield Analysis
1. Summary
- Batches analyzed: 2
- Total input: 1500 units
- Total output: 1430 units
- Overall yield: 95.33%
- Yield loss: 4.67%
- Total defects: 70
- Total loss cost: $3,500.00 (estimated)
2. Batch Results
| Batch ID | Product | Period | Input | Output | FPY % | Flags |
|---|---|---|---|---|---|---|
| B001 | Standard | Week 1 | 1000 | 950 | 95.00% | None |
| B002 | Standard | Week 2 | 500 | 480 | 96.00% | None |
3. Defect Pareto Analysis
| Category | Count | Contribution % | Cumulative % |
|---|---|---|---|
| Surface | 40 | 57.14% | 57.14% |
| Assembly | 10 | 14.29% | 71.43% |
| Dimensional | 10 | 14.29% | 85.72% |
| Material | 10 | 14.29% | 100.00% |
4. Yield Trends
| Product | From Period | To Period | From Yield | To Yield | Direction |
|---|---|---|---|---|---|
| Standard | Week 1 | Week 2 | 95.00% | 96.00% | Improving |
5. Interpretation Notes
- Surface defects represent over 50% of your losses; prioritize this category for root cause analysis.
- Yield is improving by 1.0% week-over-week.
- Loss cost estimate assumes all non-output units are scrapped.
Next steps
- Review the surface preparation process to address the top defect category.
- Provide rework data for B001 and B002 to calculate the Final Yield.
- Run a Process Capability Assessment if you need to determine if this yield is within control limits.
Connects securely to your tools. The creator never sees your data.
About this skill
Manual yield tracking often relies on disconnected spreadsheets, leading to inconsistent formulas and hidden quality costs. This skill standardizes production yield analysis by processing raw batch records into traceable metrics and prioritized defect data.
What it does
- Calculate yield metrics computes first-pass and final yield percentages using verified input and output quantities.
- Decompose losses breaks down production scrap and defects into standard categories like dimensional, material, and functional.
- Perform Pareto analysis ranks defect types by contribution to identify the primary drivers of yield loss.
- Track yield trends monitors performance across different periods and products to flag improving or declining stability.
- Estimate quality costs calculates scrap and rework costs using unit costs and configurable rework factors.
How it works
- Provide batch production data including IDs, products, periods, input quantities, and defect breakdowns.
- The agent builds a request JSON and executes the analysis script to process the manufacturing data.
- The system checks for data integrity issues, such as zero inputs or output quantities exceeding inputs.
- Review the generated report containing yield summaries, Pareto tables, and trend directions.
Frameworks & tools
This skill uses Python for data processing and logic execution. It relies on standard manufacturing yield formulas and Pareto distribution methods for quality control analysis.
Why this beats prompting it yourself
Prompting a standard LLM for math-heavy yield analysis often results in calculation errors or inconsistent definitions of first-pass yield. This skill uses a dedicated execution script to ensure every calculation is traceable, handles zero-input edge cases, and applies a rigid Pareto methodology that does not hallucinate trends.
Use cases
- Analyzing weekly batch performance to identify products with high scrap rates.
- Prioritizing quality improvement projects based on the top 80% of defect categories.
- Monitoring the impact of process changes by comparing yield trends between periods.
- Estimating the financial impact of rework versus scrap for budgeting.
Known limitations
Does not support OEE metrics, process capability analysis (Cp/Cpk), or detailed cost allocation. Yield is capped at 100 percent for measurement errors.
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 support OEE or Cp/Cpk analysis. Yield is capped at 100% in case of measurement errors. Requires batch_id and input_qty for all records.
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