OpenParable
Skip to content
← Back to skills

Dp Optimizer

Development
dp-optimizer

Dp Optimizer is an Agent Skill for development published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Apply advanced DP optimizations automatically

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. 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/algorithms-optimization/skills/dp-optimizer/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/dp-optimizer, 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.

DP Optimizer Skill

Purpose

Apply advanced dynamic programming optimizations to improve time and space complexity of DP solutions.

Capabilities

  • Convex hull trick detection and application
  • Divide and conquer optimization
  • Knuth optimization
  • Monotonic queue/deque optimization
  • Alien's trick / WQS binary search
  • Rolling array optimization
  • Bitmask compression

Target Processes

  • dp-state-optimization
  • advanced-dp-techniques
  • complexity-optimization

Optimization Techniques

Time Optimizations

  1. Convex Hull Trick: O(n^2) -> O(n log n) for certain recurrences
  2. Divide & Conquer: O(n^2 k) -> O(n k log n) when optimal j is monotonic
  3. Knuth Optimization: O(n^3) -> O(n^2) for certain interval DP
  4. Monotonic Queue: O(n*k) -> O(n) for sliding window DP

Space Optimizations

  1. Rolling Array: O(n*m) -> O(m) when only previous row needed
  2. Bitmask Compression: Reduce state space with bit manipulation

Input Schema

{
  "type": "object",
  "properties": {
    "dpCode": { "type": "string" },
    "stateDefinition": { "type": "string" },
    "transitions": { "type": "string" },
    "currentComplexity": { "type": "string" },
    "targetComplexity": { "type": "string" },
    "optimizationType": {
      "type": "string",
      "enum": ["auto", "convexHull", "divideConquer", "knuth", "monotonic", "space"]
    }
  },
  "required": ["dpCode", "optimizationType"]
}

Output Schema

{
  "type": "object",
  "properties": {
    "success": { "type": "boolean" },
    "optimizedCode": { "type": "string" },
    "optimizationApplied": { "type": "string" },
    "newComplexity": { "type": "string" },
    "explanation": { "type": "string" }
  },
  "required": ["success"]
}