Ald Process Controller
Othersald-process-controllerAld Process Controller is an Agent Skill for general use published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Atomic Layer Deposition skill for conformal thin film deposition with atomic-level thickness control
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/a5c-ai/babysitter/blob/HEAD/library/specializations/domains/science/nanotechnology/skills/ald-process-controller/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/ald-process-controller, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
ALD Process Controller
Purpose
The ALD Process Controller skill provides comprehensive atomic layer deposition process control, enabling conformal thin film growth with atomic-level precision through optimized pulse sequences and in-situ monitoring.
Capabilities
- Precursor pulse/purge optimization
- Growth per cycle (GPC) characterization
- Film uniformity mapping
- Conformality assessment
- In-situ monitoring integration
- Multi-component film design
Usage Guidelines
ALD Process Control
-
Saturation Studies
- Vary pulse times
- Identify saturation dose
- Optimize purge times
-
Process Window
- Determine ALD window
- Optimize temperature
- Monitor GPC stability
-
Film Quality
- Characterize uniformity
- Measure conformality
- Assess impurity levels
Process Integration
- Thin Film Deposition Process Optimization
- Nanodevice Integration Process Flow
Input Schema
{
"material": "string",
"precursor_a": "string",
"precursor_b": "string",
"target_thickness": "number (nm)",
"substrate": "string",
"temperature": "number (C)"
}
Output Schema
{
"optimized_recipe": {
"precursor_a_pulse": "number (s)",
"purge_a": "number (s)",
"precursor_b_pulse": "number (s)",
"purge_b": "number (s)"
},
"gpc": "number (Angstrom/cycle)",
"cycles_required": "number",
"uniformity": "number (%)",
"conformality": "number (% step coverage)"
}