conversation-analyzer
npx machina-cli add skill mhattingpete/claude-skills-marketplace/conversation-analyzer --openclawConversation Analyzer
Analyzes your Claude Code conversation history to identify patterns, common mistakes, and workflow improvement opportunities.
When to Use
- "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"
What It Analyzes
- Request type distribution (bug fixes, features, refactoring, queries, testing)
- Most active projects
- Common error keywords
- Time-of-day patterns
- Repetitive tasks (automation opportunities)
- Vague requests causing back-and-forth
- Complex tasks attempted without planning
- Recurring bugs/errors
Analysis Scope
Default: Last 200 conversations for recency and relevance.
Methodology
1. Request Type Distribution
Categorizes by: bug fixes, feature additions, refactoring, information queries, testing, other.
2. Project Activity
Tracks which projects consume most time, identifies project-specific patterns.
3. Time Patterns
Hour-of-day usage distribution, identifies peak productivity times.
4. Common Mistakes
- 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
5. Error Analysis
Frequency of error-related requests, common error keywords, recurring problems.
6. Automation Opportunities
Identifies repeated exact requests, suggests skills, slash commands, or scripts.
Output
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
Tools Used
- Read: Load history file (
~/.claude/history.jsonl) - Write: Create analysis reports if requested
- Bash: Execute Python analysis script
- Direct analysis: Parse JSON programmatically
Analysis Script
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:
cd ~/.claude/plugins/*/productivity-skills/conversation-analyzer/scripts
python3 analyze_history.py
Outputs:
conversation_analysis.txt- Detailed pattern analysisrecommendations.txt- Specific improvement suggestions
Example Output
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
- User understands usage patterns
- Concrete, actionable recommendations
- Specific examples from history
- Prioritized by impact (quick wins vs long-term)
- User can immediately apply improvements
Integration
- feature-planning: Implement recommended improvements
- test-fixing: Address recurring test failures
- git-pushing: Commit workflow improvements
Privacy Note
All analysis happens locally. Conversation history never leaves user's machine.
Source
git clone https://github.com/mhattingpete/claude-skills-marketplace/blob/main/productivity-skills-plugin/skills/conversation-analyzer/SKILL.mdView on GitHub Overview
This skill analyzes your Claude Code conversation history to identify usage patterns, common mistakes, and workflow improvement opportunities. It surfaces concrete, actionable recommendations and automation opportunities to help you work more efficiently and follow best practices.
How This Skill Works
It loads the history from ~/.claude/history.jsonl and runs analyze_history.py to extract metrics across request types, projects, errors, and time patterns. It then outputs a structured report with statistics, patterns, issues, and recommendations that you can act on.
When to Use It
- 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
Quick Start
- Step 1: Run the analysis script to load your Claude history.
- Step 2: Open conversation_analysis.txt and recommendations.txt to review findings.
- Step 3: Implement top recommendations by adding automation or new skills and re-run later for measurement.
Best Practices
- Run analysis after major projects or sprints to surface patterns and automation opportunities.
- Prioritize recurring issues and create targeted automations or scripts (e.g., repetitive fixes, common errors).
- Clarify vague requests with context to reduce back-and-forth and improve future analyses.
- Use feature-planning and automation skills for complex, multi-step tasks identified by the analysis.
- Schedule tackling high-impact recommendations during your peak productivity window to maximize impact.
Example Use Cases
- Analyzed last 200 conversations and found 60% general tasks, 15% bug fixes, 13% feature additions, with ultramerge as the dominant project.
- Detected recurring test-fixing requests and routed them to the test-fixing skill for automation.
- Noted 19 multi-step requests without explicit planning and adopted a feature-planning workflow for those tasks.
- Identified a peak productivity window of 13:00-15:00 and rescheduled complex work there for better outcomes.
- Created project-specific utilities for ultramerge to reduce repetitive commands and streamline workflows.
