prompt-review

Analyze past agent dialogues to assess technical understanding, prompting patterns, and AI dependence.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/hirakawat-hmp/.claude --skill prompt-review-hirakawat-hmp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prompt-review
Source: https://github.com/hirakawat-hmp/.claude/tree/main/skills/prompt-review
Command: npx skills add https://github.com/hirakawat-hmp/.claude --skill prompt-review-hirakawat-hmp

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

このスキルは、ユーザーが「プロンプトをレビューして」「対話履歴を分析して」「理解度を診断して」"と依頼したとき、または /prompt-review で呼び出されたときに使用します。過去のAIエージェント対話履歴を読み取り、技術理解度・プロンプティングパターン・AI依存度を推定してレポートを生成します。レポートは日本語で reports/prompt-review-YYYY-MM-DD.md に書き出します。

Core Features & Use Cases

  • 過去の対話履歴の収集と統合、プロジェクト横断の分析を実行します。
  • 技術理解度マップ、プロンプティングパターン分析、AI依存度評価をレポートに統合します。
  • 指定された期間・プロジェクトフィルタに基づくデータ抽出と日本語レポート出力を自動化します。

Quick Start

scripts/collect.py を実行してデータを集め、出力を読み込んで日本語のレポートを生成してください。

Frequently Asked Questions about prompt-review

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

FAQPage Schema
How do I analyze past AI dialogue history to assess prompting patterns and AI dependence?

Analyzing past AI dialogue history for prompting patterns and AI dependence involves collecting and integrating past agent interactions across all projects, estimating technical understanding, and generating a Japanese review report. This Skill evaluates your dialogue history to visualize prompting patterns and AI dependence metrics.

Can I filter dialogue analysis by specific project and date range?

Filtering dialogue analysis by specific project and date range is supported by this Skill. It performs data extraction based on specified period and project filters, narrowing the technical understanding and AI dependence assessment to targeted project interactions before generating the localized report.

What is the best way to generate a prompt review report from agent conversation logs?

Generating a prompt review report from agent conversation logs is best achieved by running the included data collection script to aggregate past dialogues, then leveraging frontmatter configuration to guide the analysis. This produces a Japanese markdown report saved with a timestamp to your reports directory.

How does technical understanding estimation work in dialogue analysis?

Technical understanding estimation in dialogue analysis works by identifying and summarizing the user's past agent dialogues to assess prompting patterns and AI dependence levels. The Skill evaluates your interaction history across projects to map your technical comprehension and reliance on AI-generated responses.

Do I need any dependencies to run the prompt analysis and report generation script?

No external dependencies are required to run the prompt analysis and report generation script. The Skill operates autonomously with its bundled scripts and reference components, collecting dialogue data and producing the Japanese markdown report without requiring additional packages.

What format does the prompt review report use for output?

The prompt review report uses markdown format for output, specifically saved as a Japanese-language file named prompt-review-YYYY-MM-DD.md in the reports directory. This standardized markdown structure ensures the technical understanding, prompting patterns, and AI dependence analysis are documented readably.