prompt-analysis

🔍 Extract and analyze your Claude Code conversation history to discover usage patterns, generate insights, and create custom slash commands from your prompting style.

The sorta-descriptive Python script takes a text file of image descriptions generated by MidJourney and sorts them into nine columns in a CSV file.

A recipe for any AI agent to build a self-improving theory-of-mind model of its user from interaction logs (feedback precognition). What you mind is what you get.

Analyze how you use AI—this Next.js app scores your prompts for brain growth vs dependency using Gemini and local heuristics.

Private, local-only capture of Claude Code and Codex CLI conversation logs into SQLite, and an auditable analysis of which software guidelines one developer repeats most. Measured over 7,882 human prompts, with 100% test coverage.

Local Python analyzer for Claude session transcripts with token usage reports and prompt insights.

A new package designed to facilitate the extraction of structured insights from user prompts related to the domain of autonomous AI agents and their potential vulnerabilities. Given an input text desc

A prompt-engineering framework that analyzes naïve prompts using a six-component Prompt Composition Framework (C1–C6), computes a Prompt Quality Score (PQS), transforms prompts into fully structured versions, and compares prompt quality through deterministic evaluation and LLM execution.

MCP tool that analyzes your prompts — scores quality, reveals what AI inferred vs. missed, and tracks improvement over time. Works with Claude Desktop & Claude Code.

Cite Prob LLM analyzes how different LLMs cite and rank domains/URLs in response to structured prompts. The project builds citation audit datasets, computes feature-based metrics (presence, dominance, position, conversion, stability), and applies clustering/visualization methods to compare model behavior across scenarios.

Open-source prompt analyzer and optimizer for better AI interactions.

Human Character Generation from user prompts in blender using Natural Language Processing. It uses flask, spaCy and python.

prompt keyword matching analyzer

I Asked It to Forget, but It Didn't — A Case of Miscommunication Between AI and Humans

🧠 Analyze your AI interactions to boost understanding or reveal dependency with insight from prompts and chat history.