Experiment Planner DOE

SkillMedia

Design of Experiments skill for systematic optimization of nanomaterial synthesis and processing

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Experiment Planner DOE skill

What this skill tells your AI

The instructions your AI receives, as published by a5c-ai/babysitter in library/specializations/domains/science/nanotechnology/skills/experiment-planner-doe/SKILL.md and read by ahel’s review.

Purpose

The Experiment Planner DOE skill provides systematic experimental design for nanomaterial synthesis and processing optimization, enabling efficient exploration of parameter space and robust process development.

Capabilities

  • Factorial design generation
  • Response surface methodology
  • Taguchi method implementation
  • ANOVA analysis
  • Optimization predictions
  • Robustness testing

Usage Guidelines

DOE Workflow

  1. Design Selection

    • Identify factors and levels
    • Choose appropriate design
    • Calculate required runs
  2. Execution Planning

    • Randomize run order
    • Include replicates
    • Plan blocking if needed
  3. Analysis

    • Perform ANOVA
    • Build response models
    • Optimize parameters

Process Integration

  • Nanoparticle Synthesis Protocol Development
  • Thin Film Deposition Process Optimization
  • Nanolithography Process Development

Input Schema

{
  "factors": [{
    "name": "string",
    "low": "number",
    "high": "number",
    "type": "continuous|categorical"
  }],
  "responses": ["string"],
  "design_type": "factorial|fractional|rsm|taguchi",
  "constraints": {
    "max_runs": "number",
    "blocking": "boolean"
  }
}

Output Schema

{
  "design": {
    "type": "string",
    "runs": "number",
    "run_table": [{
      "run": "number",
      "factors": {},
      "block": "number"
    }]
  },
  "analysis": {
    "anova_table": {},
    "significant_factors": ["string"],
    "r_squared": "number"
  },
  "optimization": {
    "optimal_settings": {},
    "predicted_response": "number",
    "confidence_interval": {"lower": "number", "upper": "number"}
  }
}

Signals

GitHub stars
2k
Forks
112
Last commit
Sep 2026
Advanced
Item type
skill
Key
experiment-planner-doe
Source
github.com/a5c-ai/babysitter