prompt-analysis

Analyze AI prompting patterns and acceptance rates from a local SQLite database.

2.4k|260|Updated Jul 2, 2025
One-click install
npx skills add https://github.com/git-ai-project/git-ai --skill prompt-analysis-git-ai-project
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prompt-analysis
Source: https://github.com/git-ai-project/git-ai/tree/main/skills/prompt-analysis
Command: npx skills add https://github.com/git-ai-project/git-ai --skill prompt-analysis-git-ai-project

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps you understand and optimize how you interact with AI coding assistants by analyzing your prompting patterns, acceptance rates, and the effectiveness of your prompts.

Core Features & Use Cases

  • Analyze Prompt Performance: Track metrics like acceptance rate, lines accepted/overridden, and identify trends across different models and authors.
  • Categorize Prompt Usage: Classify prompts by work type (bug fix, feature, refactor, etc.) to understand where AI is most utilized.
  • Identify Reusable Patterns: Discover prompts that solved recurring problems, enabling you to save and reuse effective prompting strategies.
  • Diagnose Low Acceptance: Investigate why certain prompts lead to low code acceptance by analyzing conversation content and identifying reasons like vague requests or incorrect approaches.
  • Use Case: A developer wants to know which AI models yield the highest acceptance rates for their code, or why a particular set of prompts consistently requires significant human modification.

Quick Start

Analyze your AI prompt patterns by running the git-ai prompts command with appropriate flags to initialize the prompt database.

Frequently Asked Questions about prompt-analysis

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

FAQPage Schema
How do I analyze AI prompt acceptance rates to improve my coding workflow?

To analyze AI prompt acceptance rates, you query a local SQLite database populated by the git-ai tool to track metrics, categorize work types, and identify trends for optimizing AI-assisted coding workflows.

Why does my AI code generation prompt consistently result in low acceptance rates?

Low acceptance rates for AI code generation are diagnosed by analyzing conversation content to identify failure reasons like vague requests or incorrect approaches, helping you adjust your prompting strategy.

What is the best way to identify reusable AI prompts for recurring coding tasks?

The best way to identify reusable AI prompts is to analyze prompt performance patterns to discover which specific prompts successfully solved recurring problems, enabling you to save and reuse effective strategies.

Do I need a specific database setup to track developer productivity metrics with git-ai?

Yes, you need a local SQLite database named prompts.db populated by the git-ai tool to track developer productivity metrics and enable detailed diagnostics on prompt effectiveness.

Can I categorize AI prompt usage by work type like bug fixes and refactoring?

Yes, you can categorize AI prompt usage by work type such as bug fixes, features, or refactoring to understand exactly where AI assistance is most utilized in your development workflow.