Back to Details

conversation-analyzer

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Conversation Analyzer

对话分析器

Analyzes your Claude Code conversation history to identify patterns, common mistakes, and workflow improvement opportunities.
分析你的Claude Code对话历史，以识别使用模式、常见错误及工作流改进机会。

When to Use

适用场景

  • "analyze my conversations"
  • "review my Claude Code history"
  • "what patterns do you see in my usage"
  • "how can I improve my workflow"
  • "am I using Claude Code effectively"
  • "分析我的对话"
  • "查看我的Claude Code历史记录"
  • "你能从我的使用中发现什么模式"
  • "我该如何改进我的工作流"
  • "我是否在高效使用Claude Code"

What It Analyzes

分析内容

  1. Request type distribution (bug fixes, features, refactoring, queries, testing)
  2. Most active projects
  3. Common error keywords
  4. Time-of-day patterns
  5. Repetitive tasks (automation opportunities)
  6. Vague requests causing back-and-forth
  7. Complex tasks attempted without planning
  8. Recurring bugs/errors
  1. 请求类型分布（bug修复、功能开发、重构、查询、测试）
  2. 最活跃的项目
  3. 常见错误关键词
  4. 使用时段模式
  5. 重复性任务（自动化机会）
  6. 导致多轮沟通的模糊请求
  7. 未做规划就尝试的复杂任务
  8. 反复出现的bug/错误

Analysis Scope

分析范围

Default: Last 200 conversations for recency and relevance.
默认：最近200条对话，保证时效性和相关性。

Methodology

分析方法

1. Request Type Distribution

1. 请求类型分布

Categorizes by: bug fixes, feature additions, refactoring, information queries, testing, other.
按以下类别划分：bug修复、功能新增、重构、信息查询、测试、其他。

2. Project Activity

2. 项目活跃度

Tracks which projects consume most time, identifies project-specific patterns.
追踪占用时间最多的项目，识别项目特有的使用模式。

3. Time Patterns

3. 时间模式

Hour-of-day usage distribution, identifies peak productivity times.
按小时统计使用分布，识别生产力峰值时段。

4. Common Mistakes

4. 常见错误

  • Vague requests: Initial requests lacking context vs. acceptable follow-ups
  • Repeated fixes: Same issues occurring multiple times
  • Complex tasks: Multi-step requests without planning
  • Repetitive commands: Manual tasks that could be automated
  • 模糊请求：缺少上下文的初始请求，以及可接受的后续追问的对比
  • 重复修复：相同问题多次出现
  • 复杂任务：未做规划的多步骤请求
  • 重复命令：可被自动化的手动任务

5. Error Analysis

5. 错误分析

Frequency of error-related requests, common error keywords, recurring problems.
与错误相关的请求频率、常见错误关键词、反复出现的问题。

6. Automation Opportunities

6. 自动化机会

Identifies repeated exact requests, suggests skills, slash commands, or scripts.
识别重复出现的完全相同的请求，推荐skill、斜杠命令或脚本。

Output

输出内容

Structured report with:
  • Statistics: Request types, active projects, timing patterns
  • Patterns: Common tasks, repetitive commands, complexity indicators
  • Issues: Specific problems with examples
  • Recommendations: Prioritized, actionable improvements
结构化报告包含：
  • 统计数据：请求类型、活跃项目、时间模式
  • 使用模式：常见任务、重复命令、复杂度指标
  • 存在问题：带示例的具体问题
  • 优化建议：按优先级排序的可落地改进项

Tools Used

使用工具

  • Read: Load history file (
    ~/.claude/history.jsonl
    )
  • Write: Create analysis reports if requested
  • Bash: Execute Python analysis script
  • Direct analysis: Parse JSON programmatically
  • Read：加载历史文件（
    ~/.claude/history.jsonl
    ）
  • Write：按需生成分析报告
  • Bash：执行Python分析脚本
  • 直接分析：程序化解析JSON

Analysis Script

分析脚本

Uses 
scripts/analyze_history.py
for comprehensive analysis:
Capabilities:
  • Loads and parses 
    ~/.claude/history.jsonl
  • Analyzes patterns across multiple dimensions
  • Identifies common mistakes and inefficiencies
  • Generates actionable recommendations
  • Outputs detailed reports
Usage within skill: Runs automatically when user requests analysis.
Standalone usage:
bash
cd ~/.claude/plugins/*/productivity-skills/conversation-analyzer/scripts
python3 analyze_history.py
Outputs:
  • conversation_analysis.txt
    - Detailed pattern analysis
  • recommendations.txt
    - Specific improvement suggestions
使用
scripts/analyze_history.py
进行全面分析：
功能：
  • 加载并解析
    ~/.claude/history.jsonl
  • 多维度分析使用模式
  • 识别常见错误和低效操作
  • 生成可落地的改进建议
  • 输出详细报告
在skill中使用： 用户请求分析时自动运行。
独立使用：
bash
cd ~/.claude/plugins/*/productivity-skills/conversation-analyzer/scripts
python3 analyze_history.py
输出：
  • conversation_analysis.txt
    - 详细的模式分析报告
  • recommendations.txt
    - 具体的改进建议

Example Output

输出示例

Analyzed last 200 conversations:
- 60% general tasks, 15% bug fixes, 13% feature additions
- Project "ultramerge" dominates 58% of activity
- Same test-fixing request made 8 times
- 19 multi-step requests without planning
- Peak productivity: 13:00-15:00

Recommendations:
- Use test-fixing skill for recurring test failures
- Create project-specific utilities for ultramerge
- Use feature-planning skill for complex requests
- Add tests to prevent recurring bugs
- Schedule complex work during peak hours
Analyzed last 200 conversations:
- 60% general tasks, 15% bug fixes, 13% feature additions
- Project "ultramerge" dominates 58% of activity
- Same test-fixing request made 8 times
- 19 multi-step requests without planning
- Peak productivity: 13:00-15:00

Recommendations:
- Use test-fixing skill for recurring test failures
- Create project-specific utilities for ultramerge
- Use feature-planning skill for complex requests
- Add tests to prevent recurring bugs
- Schedule complex work during peak hours

Success Criteria

成功标准

  • User understands usage patterns
  • Concrete, actionable recommendations
  • Specific examples from history
  • Prioritized by impact (quick wins vs long-term)
  • User can immediately apply improvements
  • 用户理解自身的使用模式
  • 给出具体可落地的改进建议
  • 提供来自历史记录的具体示例
  • 按影响优先级排序（快速见效项 vs 长期改进项）
  • 用户可以立即应用改进方案

Integration

集成能力

  • feature-planning: Implement recommended improvements
  • test-fixing: Address recurring test failures
  • git-pushing: Commit workflow improvements
  • feature-planning：落地推荐的改进方案
  • test-fixing：解决反复出现的测试失败问题
  • git-pushing：提交工作流改进内容

Privacy Note

隐私说明

All analysis happens locally. Conversation history never leaves user's machine.
所有分析均在本地运行，对话历史永远不会离开用户的设备。