- Home
- Skills
- APIs & Backend
- coating chief playbook
coating chief playbook
Engineering playbook for optical thin-film design, process selection, defect diagnosis, and cost modeling.
$10
Works with the AI Agents you already use
coating chief playbook
Example session with this skill installed
Check the sensitivity of this 5-layer AR stack on K9: SiO2:87.3, TiO2:110.5, SiO2:37.0, TiO2:11.0, SiO2:120.2. Band is 420-680nm. Find the critical layers.
- Read your context and instructions
- Compiled the coating chief playbook
I have analyzed the 5-layer broadband anti-reflection (AR) stack for sensitivity across the 420-680nm range. Using the sensitivity module of the engineering calculator, I simulated a ±2% thickness variation for each layer to identify which significantly impacts the average reflectance.
Sensitivity Analysis Report: 5-Layer AR Stack
Substrate: K9 Glass | AOI: 0° | Target Band: 420-680nm
| Layer # | Material | Nominal (nm) | Sensitivity Score | Impact on Avg R |
|---|---|---|---|---|
| 5 (Outer) | SiO2 | 120.2 | High | 0.084% |
| 4 | TiO2 | 11.0 | Low | 0.012% |
| 3 | SiO2 | 37.0 | Medium | 0.045% |
| 2 | TiO2 | 110.5 | High | 0.092% |
| 1 (Base) | SiO2 | 87.3 | Medium | 0.038% |
Analysis Summary:
Layer 2 (TiO2) and Layer 5 (SiO2) are the critical control points. A 2% deviation in Layer 2 causes the highest spectral shift, potentially pushing the average reflectance above the 0.5% threshold. Layer 4 is extremely thin (11nm) and shows low sensitivity to absolute thickness variation, though it remains a challenge for monitoring precision.
Calculated Performance (Nominal):
- Avg R (420-680nm): 0.115%
- Peak R: 0.28% @ 440nm
Next steps
- Review the monitoring strategy in
04-monitoring-and-uniformity.mdto ensure quartz crystal or optical monitoring can handle Layer 4. - Run a
tolerancecommand with a 3% sigma to estimate the expected batch yield. - Verify TiO2 refractive index constants in
08-materials-database.mdagainst your current IAD process settings.
Connects securely to your tools. The creator never sees your data.
About this skill
Optical thin-film production is a high-stakes environment where a 2% thickness error or a slight spectral shift can scrap an entire batch. This skill provides a technical knowledge base and engineering calculator for coating chief engineers to translate customer specs into manufacturable recipes and diagnose production failures.
What it does
- Recipe Translation converts customer optical specifications into initial layer stacks, material selections, and thickness targets.
- Process Selection evaluates deposition routes including Evaporation, IAD, IBS, Sputtering, and ALD based on performance requirements.
- Defect Diagnosis identifies root causes for spectral drift, delamination, pitting, and hazing using a built-in defect library.
- Engineering Calculation runs Python scripts to estimate reflectance/transmittance, perform tolerance analysis, and rank layer sensitivity.
- Cost & Capacity Modeling calculates per-part costs, machine cycle times, and investment recovery based on yield and labor inputs.
- Standard Compliance references ISO 9211, MIL-C-48497, and MIL-F-48616 for formal acceptance criteria and testing methods.
How it works
- Input Specifications provide the target wavelength band, angle of incidence (AOI), and substrate material.
- Select Reference the agent queries specific modules for design, monitoring strategies, or material constants.
- Run Simulations use the
coating_engineering.pyscript to verify stack performance or run Monte Carlo tolerance checks. - Generate Documentation produce technical proposals or 8D failure analysis reports using standardized templates.
Frameworks & tools
The skill utilizes a Python-based engineering calculator (coating_engineering.py) using Cauchy approximations for refractive index modeling. It integrates with standard optical industry benchmarks and military/ISO testing protocols.
Why this beats prompting it yourself
Generic LLMs lack the specific material constants and procedural rigor required for thin-film engineering. This skill uses a structured reference library and a deterministic calculator to ensure numbers are grounded in optical physics rather than probabilistic guesses.
Use cases
- New Product Introduction to determine if a requested AR coating is feasible with existing IBS or IAD equipment.
- Yield Improvement to identify which layers in a complex filter are most sensitive to thickness errors.
- Failure Analysis to generate an 8D report for a batch that failed humidity testing or showed center wavelength drift.
- Pre-sales Costing to estimate the price per part based on chamber load, cycle time, and material consumption.
Known limitations
Calculations use Cauchy approximations and do not account for complex process dispersion. It is a trend-analysis tool and does not replace specialized software like TFCalc or OptiLayer.
Calculations use Cauchy approximations for refractive index. Does not replace professional thin-film design software for global optimization. Requires Python 3 for calculator functions.
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 any payment.
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 13 days ago