dp-state-designer

Assist in designing optimal DP states and transitions

509 stars

bya5c-ai

View on GitHub Installation ↓

Best use case

dp-state-designer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Assist in designing optimal DP states and transitions

Teams using dp-state-designer should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/dp-state-designer/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/specializations/algorithms-optimization/skills/dp-state-designer/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/dp-state-designer/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How dp-state-designer Compares

Feature / Agent	dp-state-designer	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Assist in designing optimal DP states and transitions

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# DP State Designer Skill

## Purpose

Assist in designing optimal dynamic programming states, transitions, and optimizations for complex DP problems.

## Capabilities

- Identify subproblem structure from problem description
- Suggest state representations (dimensions, parameters)
- Derive transition formulas
- Identify optimization opportunities (rolling array, bitmask compression)
- Generate state space complexity estimates
- Detect overlapping subproblems

## Target Processes

- dp-pattern-matching
- dp-state-optimization
- dp-transition-derivation
- advanced-dp-techniques

## DP Design Framework

1. **Subproblem Identification**: What smaller problems compose the solution?
2. **State Definition**: What parameters uniquely identify a subproblem?
3. **Transition Formula**: How do we combine subproblem solutions?
4. **Base Cases**: What are the trivial subproblems?
5. **Computation Order**: In what order should we solve subproblems?
6. **Space Optimization**: Can we reduce memory usage?

## Input Schema

```json
{
  "type": "object",
  "properties": {
    "problemDescription": { "type": "string" },
    "constraints": { "type": "object" },
    "examples": { "type": "array" },
    "requestType": {
      "type": "string",
      "enum": ["fullDesign", "stateOnly", "transitions", "optimize"]
    }
  },
  "required": ["problemDescription", "requestType"]
}
```

## Output Schema

```json
{
  "type": "object",
  "properties": {
    "success": { "type": "boolean" },
    "state": {
      "type": "object",
      "properties": {
        "definition": { "type": "string" },
        "parameters": { "type": "array" },
        "complexity": { "type": "string" }
      }
    },
    "transitions": { "type": "array" },
    "baseCases": { "type": "array" },
    "optimizations": { "type": "array" }
  },
  "required": ["success"]
}
```