skills.rest
hungrytech
hungrytechCOMMUNITY
Explore all skills by this author →
GitHub

numerical

Analyze, verify, and optimize numerical code in Python and Dart projects.

3|Updated Mar 30, 2026
Search Tags:#verification#analysis#memory#gpu#broadcasting#numeric
One-click install
npx skills add https://github.com/hungrytech/hungrytech-claude-skills --skill numerical
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: numerical
Source: https://github.com/hungrytech/hungrytech-claude-skills/tree/main/plugins/numerical/skills/numerical
Command: npx skills add https://github.com/hungrytech/hungrytech-claude-skills --skill numerical

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill automates end-to-end numerical analysis, verification, and optimization for Python and Dart projects, reducing manual debugging and performance tuning.

Core Features & Use Cases

  • Phase-driven workflow (Analyze → Verify → Optimize) with automatic context loading and phase-specific references.
  • Automatic project discovery and language/library detection, plus on-demand references and scripts for guided improvements.
  • Multiphase verification and optimization across numeric patterns (dtype, shape, precision, broadcasting, memory layout, and GPU usage) with policy-driven loops and reporting.

Quick Start

Run numerical on your Python or Dart project to automatically perform Analyze → Verify → Optimize across your numeric code.

Frequently Asked Questions about numerical

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check for precision risks and broadcasting errors in my Python numeric code?▼

To check for precision risks and broadcasting errors in Python numeric code, this skill automates numerical analysis by examining dtype usage, shape flows, and broadcasting patterns. It auto-detects your project's numeric libraries to guide hands-on improvements.

What is the best way to optimize memory layout and GPU potential for numerical computing?▼

The best way to optimize memory layout and GPU potential is through an automated Analyze, Verify, and Optimize workflow. This skill iteratively verifies and optimizes numeric patterns across your project, applying policy-driven loops to maximize performance.

Can I use this numerical verification and optimization workflow with Dart projects?▼

Yes, you can use this numerical verification and optimization workflow with Dart projects. The skill supports both Python and Dart, automatically discovering your project's language and loading phase-specific references and scripts for numeric improvements.

How does automated numerical verification handle different numeric libraries and tooling?▼

Automated numerical verification handles different libraries by auto-detecting the project's numeric libraries, language, and tooling. It then loads phase-specific references and scripts to guide multiphase verification across dtype, shape, and precision patterns.

Do I need to manually configure references and scripts for numerical analysis?▼

No, you do not need to manually configure references and scripts for numerical analysis. The skill features automatic context loading with phase-specific references, detecting your tooling to guide the Analyze, Verify, and Optimize phases automatically.

Related Skills

Explore More Software Engineering Skills→
trailofbitstrailofbits
6.5k

dimensional-analysis

Automate dimensional analysis and bug detection in numeric computation codebases.

Official
Advanced
flag3flag3
1

iterative-retrieval

Guide subagents through a 4-phase retrieval loop to refine information.

Community
Basic
gouravsingh311gouravsingh311

python-type-safety

Enforce static typing with annotations, generics, and protocols via mypy or pyright.

Community
Advanced
insightwavesmithinsightwavesmith

code-analyzer

Analyze code changes to identify those meeting evidence-shape-check criteria.

Community
Intermediate