Initial commit
This commit is contained in:
Zhongwei Li
142
skills/code-auditor/SKILL.md
Normal file
142
skills/code-auditor/SKILL.md
Normal file
@@ -0,0 +1,142 @@
|
||||
---
|
||||
name: code-auditor
|
||||
description: Performs comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability. Use when user wants to audit code quality, identify technical debt, find security issues, assess test coverage, or get a codebase health check.
|
||||
---
|
||||
|
||||
# Code Auditor
|
||||
|
||||
Comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability.
|
||||
|
||||
## When to Use
|
||||
|
||||
- "audit the code"
|
||||
- "analyze code quality"
|
||||
- "check for issues"
|
||||
- "review the codebase"
|
||||
- "find technical debt"
|
||||
- "security audit"
|
||||
- "performance review"
|
||||
|
||||
## What It Analyzes
|
||||
|
||||
### 1. Architecture & Design
|
||||
- Overall structure and organization
|
||||
- Design patterns in use
|
||||
- Module boundaries and separation of concerns
|
||||
- Dependency management
|
||||
- Architectural decisions and trade-offs
|
||||
|
||||
### 2. Code Quality
|
||||
- Complexity hotspots (cyclomatic complexity)
|
||||
- Code duplication (DRY violations)
|
||||
- Naming conventions and consistency
|
||||
- Documentation coverage
|
||||
- Code smells and anti-patterns
|
||||
|
||||
### 3. Security
|
||||
- Common vulnerabilities (OWASP Top 10)
|
||||
- Input validation and sanitization
|
||||
- Authentication and authorization
|
||||
- Secrets management
|
||||
- Dependency vulnerabilities
|
||||
|
||||
### 4. Performance
|
||||
- Algorithmic complexity issues
|
||||
- Database query optimization
|
||||
- Memory usage patterns
|
||||
- Caching opportunities
|
||||
- Resource leaks
|
||||
|
||||
### 5. Testing
|
||||
- Test coverage assessment
|
||||
- Test quality and effectiveness
|
||||
- Missing test scenarios
|
||||
- Testing patterns and practices
|
||||
- Integration vs unit test balance
|
||||
|
||||
### 6. Maintainability
|
||||
- Technical debt assessment
|
||||
- Coupling and cohesion
|
||||
- Ease of future changes
|
||||
- Onboarding friendliness
|
||||
- Documentation quality
|
||||
|
||||
## Approach
|
||||
|
||||
1. **Explore** using Explore agent (thorough mode)
|
||||
2. **Identify patterns** with Grep and Glob
|
||||
3. **Read critical files** for detailed analysis
|
||||
4. **Run static analysis tools** if available
|
||||
5. **Synthesize findings** into actionable report
|
||||
|
||||
## Thoroughness Levels
|
||||
|
||||
- **Quick** (15-30 min): High-level, critical issues only
|
||||
- **Standard** (30-60 min): Comprehensive across all dimensions
|
||||
- **Deep** (60+ min): Exhaustive with detailed examples
|
||||
|
||||
## Output Format
|
||||
|
||||
```markdown
|
||||
# Code Audit Report
|
||||
|
||||
## Executive Summary
|
||||
- Overall health score
|
||||
- Critical issues count
|
||||
- Top 3 priorities
|
||||
|
||||
## Findings by Category
|
||||
|
||||
### Architecture & Design
|
||||
#### 🔴 High Priority
|
||||
- [Finding with file:line reference]
|
||||
- Impact: [description]
|
||||
- Recommendation: [action]
|
||||
|
||||
#### 🟡 Medium Priority
|
||||
...
|
||||
|
||||
### [Other categories]
|
||||
|
||||
## Prioritized Action Plan
|
||||
1. Quick wins (< 1 day)
|
||||
2. Medium-term improvements (1-5 days)
|
||||
3. Long-term initiatives (> 5 days)
|
||||
|
||||
## Metrics
|
||||
- Files analyzed: X
|
||||
- Lines of code: Y
|
||||
- Test coverage: Z%
|
||||
- Complexity hotspots: N
|
||||
```
|
||||
|
||||
## Tools Used
|
||||
|
||||
- **Task (Explore agent)**: Thorough codebase exploration
|
||||
- **Grep**: Pattern matching for issues
|
||||
- **Glob**: Find files by type/pattern
|
||||
- **Read**: Detailed file analysis
|
||||
- **Bash**: Run linters, coverage tools
|
||||
|
||||
## Success Criteria
|
||||
|
||||
- Comprehensive coverage of all six dimensions
|
||||
- Specific file:line references for all findings
|
||||
- Severity/priority ratings (Critical/High/Medium/Low)
|
||||
- Actionable recommendations (not just observations)
|
||||
- Estimated effort for fixes
|
||||
- Both quick wins and long-term improvements
|
||||
|
||||
## Integration
|
||||
|
||||
- **feature-planning**: Plan technical debt reduction
|
||||
- **test-fixing**: Address test gaps identified
|
||||
- **project-bootstrapper**: Set up quality tooling
|
||||
|
||||
## Configuration
|
||||
|
||||
Can focus on specific areas:
|
||||
- Security-only audit
|
||||
- Performance-only audit
|
||||
- Testing-only assessment
|
||||
- Quick architecture review
|
||||
159
skills/codebase-documenter/SKILL.md
Normal file
159
skills/codebase-documenter/SKILL.md
Normal file
@@ -0,0 +1,159 @@
|
||||
---
|
||||
name: codebase-documenter
|
||||
description: Generates comprehensive documentation explaining how a codebase works, including architecture, key components, data flow, and development guidelines. Use when user wants to understand unfamiliar code, create onboarding docs, document architecture, or explain how the system works.
|
||||
---
|
||||
|
||||
# Codebase Documenter
|
||||
|
||||
Generates comprehensive documentation for codebases - architecture, components, data flow, development guidelines.
|
||||
|
||||
## When to Use
|
||||
|
||||
- "explain this codebase"
|
||||
- "document the architecture"
|
||||
- "how does this code work"
|
||||
- "create developer documentation"
|
||||
- "generate codebase overview"
|
||||
- "create onboarding docs"
|
||||
|
||||
## What It Documents
|
||||
|
||||
### 1. Project Overview
|
||||
- Purpose & vision
|
||||
- Target users
|
||||
- Key features
|
||||
- Technology stack
|
||||
- Project status
|
||||
|
||||
### 2. Architecture
|
||||
- High-level structure
|
||||
- Design patterns
|
||||
- Data flow
|
||||
- Control flow
|
||||
- Diagrams (Mermaid)
|
||||
- Architectural decisions
|
||||
|
||||
### 3. Directory Structure
|
||||
- Organization purpose
|
||||
- Naming conventions
|
||||
- Entry points
|
||||
- Core modules
|
||||
- Configuration locations
|
||||
|
||||
### 4. Key Components
|
||||
- Major modules
|
||||
- Classes & functions
|
||||
- Responsibilities
|
||||
- Interactions
|
||||
- Extension points
|
||||
- Code examples
|
||||
|
||||
### 5. External Integrations
|
||||
- APIs consumed
|
||||
- Databases & schemas
|
||||
- Authentication
|
||||
- Caching
|
||||
- Message queues
|
||||
- File storage
|
||||
|
||||
### 6. Data Models
|
||||
- Database schema
|
||||
- Data structures
|
||||
- Validation
|
||||
- Migrations
|
||||
- Data transformations
|
||||
|
||||
### 7. Development Setup
|
||||
- Prerequisites
|
||||
- Installation steps
|
||||
- Configuration
|
||||
- Running the app
|
||||
- Testing
|
||||
- Debugging
|
||||
- Troubleshooting
|
||||
|
||||
### 8. Development Guidelines
|
||||
- Coding conventions
|
||||
- Testing approach
|
||||
- Error handling
|
||||
- Logging
|
||||
- Security practices
|
||||
- Performance patterns
|
||||
|
||||
### 9. Deployment
|
||||
- Build process
|
||||
- Deployment steps
|
||||
- Environments
|
||||
- Monitoring
|
||||
- Rollback procedures
|
||||
|
||||
### 10. Contributing
|
||||
- Development workflow
|
||||
- Code review guidelines
|
||||
- Testing requirements
|
||||
- Documentation updates
|
||||
|
||||
## Approach
|
||||
|
||||
1. **Explore** using Explore agent (thorough)
|
||||
2. **Map structure** with Glob
|
||||
3. **Read critical files** (README, entry points, core modules)
|
||||
4. **Identify patterns** with Grep (imports, exports)
|
||||
5. **Trace execution** paths
|
||||
6. **Extract knowledge** from docs, comments, tests
|
||||
7. **Synthesize** into cohesive documentation
|
||||
|
||||
## Output
|
||||
|
||||
Creates markdown documentation:
|
||||
```
|
||||
docs/
|
||||
├── README.md # Overview and quick start
|
||||
├── ARCHITECTURE.md # System architecture
|
||||
├── DEVELOPMENT.md # Development guide
|
||||
├── API.md # API documentation
|
||||
├── DEPLOYMENT.md # Deployment guide
|
||||
└── CONTRIBUTING.md # Contribution guidelines
|
||||
```
|
||||
|
||||
Or single comprehensive doc if preferred.
|
||||
|
||||
## Depth Levels
|
||||
|
||||
- **Quick**: High-level overview (15-30 min)
|
||||
- **Standard**: Comprehensive coverage (30-60 min)
|
||||
- **Deep**: Exhaustive with examples (60+ min)
|
||||
|
||||
## Visual Elements
|
||||
|
||||
- Mermaid diagrams (architecture, flow charts, sequence)
|
||||
- Code examples from codebase
|
||||
- Specific file:line references
|
||||
- Tables for structured info
|
||||
- Lists for guidelines
|
||||
|
||||
## Tools Used
|
||||
|
||||
- **Task (Explore agent)**: Codebase exploration
|
||||
- **Glob**: Map directory structure
|
||||
- **Grep**: Find patterns, imports, exports
|
||||
- **Read**: Analyze key files
|
||||
- **Write**: Create documentation
|
||||
- **Bash**: Extract metadata (git log, versions)
|
||||
|
||||
## Success Criteria
|
||||
|
||||
- Complete coverage of all areas
|
||||
- Clear explanations with examples
|
||||
- Visual diagrams for complex concepts
|
||||
- Specific file:line references
|
||||
- Actionable setup/development instructions
|
||||
- New developer can onboard using only docs
|
||||
- Organized, navigable structure
|
||||
- Accurate and current information
|
||||
|
||||
## Integration
|
||||
|
||||
- **code-auditor**: Includes quality/security context
|
||||
- **project-bootstrapper**: Documents bootstrap decisions
|
||||
- **visual-html-creator**: Create visual diagrams
|
||||
129
skills/conversation-analyzer/SKILL.md
Normal file
129
skills/conversation-analyzer/SKILL.md
Normal file
@@ -0,0 +1,129 @@
|
||||
---
|
||||
name: conversation-analyzer
|
||||
description: Analyzes your Claude Code conversation history to identify patterns, common mistakes, and opportunities for workflow improvement. Use when user wants to understand usage patterns, optimize workflow, identify automation opportunities, or check if they're following best practices.
|
||||
---
|
||||
|
||||
# Conversation 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
|
||||
|
||||
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**
|
||||
|
||||
## 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:**
|
||||
```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
|
||||
|
||||
## 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.
|
||||
375
skills/conversation-analyzer/scripts/analyze_history.py
Normal file
375
skills/conversation-analyzer/scripts/analyze_history.py
Normal file
@@ -0,0 +1,375 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Analyze Claude Code conversation history to identify patterns and common mistakes.
|
||||
"""
|
||||
|
||||
import json
|
||||
import re
|
||||
from collections import Counter, defaultdict
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
def load_history(history_path):
|
||||
"""Load and parse history.jsonl file."""
|
||||
conversations = []
|
||||
with open(history_path, 'r') as f:
|
||||
for line in f:
|
||||
try:
|
||||
conversations.append(json.loads(line))
|
||||
except json.JSONDecodeError:
|
||||
continue
|
||||
return conversations
|
||||
|
||||
def extract_patterns(conversations):
|
||||
"""Extract patterns from conversations."""
|
||||
patterns = {
|
||||
'common_tasks': Counter(),
|
||||
'projects': Counter(),
|
||||
'error_keywords': Counter(),
|
||||
'request_types': Counter(),
|
||||
'time_distribution': defaultdict(int),
|
||||
'complexity_indicators': Counter(),
|
||||
}
|
||||
|
||||
error_keywords = ['error', 'fix', 'bug', 'issue', 'problem', 'fail', 'broken', 'wrong', 'incorrect', 'merge conflict']
|
||||
complexity_indicators = ['refactor', 'implement', 'add feature', 'create', 'build', 'migrate', 'optimize', 'analyze']
|
||||
|
||||
for conv in conversations:
|
||||
display = conv.get('display', '').lower()
|
||||
project = conv.get('project', '')
|
||||
|
||||
# Count projects
|
||||
if project:
|
||||
patterns['projects'][project] += 1
|
||||
|
||||
# Count error-related requests
|
||||
for keyword in error_keywords:
|
||||
if keyword in display:
|
||||
patterns['error_keywords'][keyword] += 1
|
||||
|
||||
# Count complexity indicators
|
||||
for indicator in complexity_indicators:
|
||||
if indicator in display:
|
||||
patterns['complexity_indicators'][indicator] += 1
|
||||
|
||||
# Categorize request types
|
||||
if any(kw in display for kw in ['fix', 'error', 'bug', 'issue', 'problem']):
|
||||
patterns['request_types']['bug_fix'] += 1
|
||||
elif any(kw in display for kw in ['add', 'create', 'implement', 'build', 'new']):
|
||||
patterns['request_types']['feature_addition'] += 1
|
||||
elif any(kw in display for kw in ['refactor', 'improve', 'optimize', 'clean']):
|
||||
patterns['request_types']['refactoring'] += 1
|
||||
elif any(kw in display for kw in ['explain', 'what', 'how', 'why', 'analyze', 'understand']):
|
||||
patterns['request_types']['information_query'] += 1
|
||||
elif any(kw in display for kw in ['test', 'run', 'build', 'deploy']):
|
||||
patterns['request_types']['testing_deployment'] += 1
|
||||
else:
|
||||
patterns['request_types']['other'] += 1
|
||||
|
||||
# Time distribution (hour of day)
|
||||
if 'timestamp' in conv:
|
||||
dt = datetime.fromtimestamp(conv['timestamp'] / 1000)
|
||||
hour = dt.hour
|
||||
patterns['time_distribution'][hour] += 1
|
||||
|
||||
# Track all tasks
|
||||
patterns['common_tasks'][display] += 1
|
||||
|
||||
return patterns
|
||||
|
||||
def identify_common_mistakes(conversations):
|
||||
"""Identify patterns that might indicate common mistakes."""
|
||||
mistakes = {
|
||||
'repeated_fixes': [],
|
||||
'merge_conflicts': [],
|
||||
'repeated_requests': [],
|
||||
'vague_requests': [],
|
||||
'multi_step_without_planning': [],
|
||||
}
|
||||
|
||||
# Track repeated similar requests
|
||||
task_groups = defaultdict(list)
|
||||
for i, conv in enumerate(conversations):
|
||||
display = conv.get('display', '')
|
||||
|
||||
# Group similar tasks
|
||||
normalized = re.sub(r'\d+', '#', display.lower())
|
||||
normalized = re.sub(r'[^\w\s]', '', normalized)
|
||||
task_groups[normalized].append((i, display, conv))
|
||||
|
||||
# Identify repeated fixes
|
||||
for task, occurrences in task_groups.items():
|
||||
if len(occurrences) > 2 and any(kw in task for kw in ['fix', 'error', 'bug']):
|
||||
mistakes['repeated_fixes'].append({
|
||||
'pattern': task,
|
||||
'count': len(occurrences),
|
||||
'examples': [occ[1] for occ in occurrences[:3]]
|
||||
})
|
||||
|
||||
# Identify merge conflicts
|
||||
for conv in conversations:
|
||||
display = conv.get('display', '')
|
||||
if 'merge conflict' in display.lower():
|
||||
mistakes['merge_conflicts'].append(display)
|
||||
|
||||
# Identify repeated requests (exact matches)
|
||||
for task, occurrences in task_groups.items():
|
||||
if len(occurrences) > 3:
|
||||
mistakes['repeated_requests'].append({
|
||||
'pattern': occurrences[0][1],
|
||||
'count': len(occurrences)
|
||||
})
|
||||
|
||||
# Identify vague requests (very short or unclear)
|
||||
vague_keywords = ['this', 'that', 'it', 'the thing', 'stuff']
|
||||
for conv in conversations:
|
||||
display = conv.get('display', '')
|
||||
if len(display.split()) < 4 or any(vk in display.lower() for vk in vague_keywords):
|
||||
if len(display) < 30:
|
||||
mistakes['vague_requests'].append(display)
|
||||
|
||||
# Identify complex multi-step requests
|
||||
multi_step_indicators = [' and ', ', ', 'then ', 'also ', 'plus ']
|
||||
for conv in conversations:
|
||||
display = conv.get('display', '')
|
||||
if sum(indicator in display.lower() for indicator in multi_step_indicators) >= 2:
|
||||
mistakes['multi_step_without_planning'].append(display)
|
||||
|
||||
return mistakes
|
||||
|
||||
def generate_report(patterns, mistakes):
|
||||
"""Generate a comprehensive analysis report."""
|
||||
report = []
|
||||
|
||||
report.append("=" * 80)
|
||||
report.append("CLAUDE CODE CONVERSATION ANALYSIS REPORT")
|
||||
report.append("=" * 80)
|
||||
report.append("")
|
||||
|
||||
# Overall statistics
|
||||
report.append("## OVERALL STATISTICS")
|
||||
report.append(f"Total conversations: {sum(patterns['request_types'].values())}")
|
||||
report.append("")
|
||||
|
||||
# Request type distribution
|
||||
report.append("## REQUEST TYPE DISTRIBUTION")
|
||||
for req_type, count in patterns['request_types'].most_common():
|
||||
percentage = (count / sum(patterns['request_types'].values())) * 100
|
||||
report.append(f" {req_type.replace('_', ' ').title()}: {count} ({percentage:.1f}%)")
|
||||
report.append("")
|
||||
|
||||
# Most active projects
|
||||
report.append("## MOST ACTIVE PROJECTS")
|
||||
for project, count in patterns['projects'].most_common(10):
|
||||
report.append(f" {count:3d}x {project}")
|
||||
report.append("")
|
||||
|
||||
# Common error keywords
|
||||
report.append("## COMMON ERROR KEYWORDS")
|
||||
for keyword, count in patterns['error_keywords'].most_common(10):
|
||||
report.append(f" {keyword}: {count}")
|
||||
report.append("")
|
||||
|
||||
# Complexity indicators
|
||||
report.append("## COMPLEXITY INDICATORS")
|
||||
for indicator, count in patterns['complexity_indicators'].most_common(10):
|
||||
report.append(f" {indicator}: {count}")
|
||||
report.append("")
|
||||
|
||||
# Time distribution
|
||||
report.append("## TIME DISTRIBUTION (BY HOUR)")
|
||||
for hour in sorted(patterns['time_distribution'].keys()):
|
||||
count = patterns['time_distribution'][hour]
|
||||
bar = '█' * (count // 5)
|
||||
report.append(f" {hour:02d}:00 {bar} ({count})")
|
||||
report.append("")
|
||||
|
||||
# Common mistakes
|
||||
report.append("=" * 80)
|
||||
report.append("## IDENTIFIED COMMON MISTAKES AND PATTERNS")
|
||||
report.append("=" * 80)
|
||||
report.append("")
|
||||
|
||||
if mistakes['merge_conflicts']:
|
||||
report.append(f"### 1. MERGE CONFLICTS ({len(mistakes['merge_conflicts'])} occurrences)")
|
||||
report.append("These indicate potential git workflow issues:")
|
||||
for mc in mistakes['merge_conflicts'][:5]:
|
||||
report.append(f" - {mc}")
|
||||
report.append("")
|
||||
|
||||
if mistakes['repeated_fixes']:
|
||||
report.append(f"### 2. REPEATED FIX PATTERNS ({len(mistakes['repeated_fixes'])} patterns)")
|
||||
report.append("Similar fixes requested multiple times - may indicate recurring issues:")
|
||||
for fix in sorted(mistakes['repeated_fixes'], key=lambda x: x['count'], reverse=True)[:5]:
|
||||
report.append(f" - Pattern: '{fix['pattern']}' (occurred {fix['count']} times)")
|
||||
for example in fix['examples'][:2]:
|
||||
report.append(f" Example: {example}")
|
||||
report.append("")
|
||||
|
||||
if mistakes['repeated_requests']:
|
||||
report.append(f"### 3. REPEATED EXACT REQUESTS ({len(mistakes['repeated_requests'])} patterns)")
|
||||
report.append("Exact same requests multiple times - could be automated:")
|
||||
for req in sorted(mistakes['repeated_requests'], key=lambda x: x['count'], reverse=True)[:5]:
|
||||
report.append(f" - '{req['pattern']}' (x{req['count']})")
|
||||
report.append("")
|
||||
|
||||
if mistakes['vague_requests']:
|
||||
report.append(f"### 4. VAGUE REQUESTS ({len(mistakes['vague_requests'])} found)")
|
||||
report.append("Short or unclear requests that might benefit from more context:")
|
||||
for vague in mistakes['vague_requests'][:10]:
|
||||
report.append(f" - '{vague}'")
|
||||
report.append("")
|
||||
|
||||
if mistakes['multi_step_without_planning']:
|
||||
report.append(f"### 5. COMPLEX MULTI-STEP REQUESTS ({len(mistakes['multi_step_without_planning'])} found)")
|
||||
report.append("Requests with multiple steps that could benefit from planning:")
|
||||
for multi in mistakes['multi_step_without_planning'][:10]:
|
||||
report.append(f" - {multi}")
|
||||
report.append("")
|
||||
|
||||
# Most common tasks
|
||||
report.append("## TOP 20 MOST COMMON TASKS")
|
||||
for task, count in patterns['common_tasks'].most_common(20):
|
||||
if count > 1:
|
||||
report.append(f" {count:3d}x {task}")
|
||||
report.append("")
|
||||
|
||||
return "\n".join(report)
|
||||
|
||||
def generate_recommendations(patterns, mistakes):
|
||||
"""Generate specific recommendations based on analysis."""
|
||||
recommendations = []
|
||||
|
||||
recommendations.append("=" * 80)
|
||||
recommendations.append("RECOMMENDATIONS FOR IMPROVEMENT")
|
||||
recommendations.append("=" * 80)
|
||||
recommendations.append("")
|
||||
|
||||
rec_num = 1
|
||||
|
||||
# Merge conflict recommendations
|
||||
if mistakes['merge_conflicts']:
|
||||
recommendations.append(f"{rec_num}. GIT WORKFLOW IMPROVEMENTS")
|
||||
recommendations.append(" Problem: Multiple merge conflicts detected")
|
||||
recommendations.append(" Solutions:")
|
||||
recommendations.append(" - Create a pre-commit hook to check for conflicts")
|
||||
recommendations.append(" - Add a git alias for safe rebasing")
|
||||
recommendations.append(" - Document merge conflict resolution workflow")
|
||||
recommendations.append(" - Consider using git hooks to prevent pushing conflicted files")
|
||||
recommendations.append("")
|
||||
rec_num += 1
|
||||
|
||||
# Repeated fixes recommendations
|
||||
if mistakes['repeated_fixes']:
|
||||
recommendations.append(f"{rec_num}. PREVENT RECURRING BUGS")
|
||||
recommendations.append(" Problem: Same types of fixes requested repeatedly")
|
||||
recommendations.append(" Solutions:")
|
||||
recommendations.append(" - Add linting rules to catch common errors")
|
||||
recommendations.append(" - Create test cases for frequently fixed bugs")
|
||||
recommendations.append(" - Document common pitfalls in CLAUDE.md")
|
||||
recommendations.append(" - Consider pre-commit hooks for validation")
|
||||
recommendations.append("")
|
||||
rec_num += 1
|
||||
|
||||
# Repeated requests
|
||||
if mistakes['repeated_requests']:
|
||||
recommendations.append(f"{rec_num}. AUTOMATE REPETITIVE TASKS")
|
||||
recommendations.append(" Problem: Same requests made multiple times")
|
||||
recommendations.append(" Solutions:")
|
||||
recommendations.append(" - Create slash commands for common tasks")
|
||||
recommendations.append(" - Add shell aliases or scripts")
|
||||
recommendations.append(" - Consider creating Claude Code skills for workflows")
|
||||
recommendations.append(" - Document common patterns in CLAUDE.md")
|
||||
recommendations.append("")
|
||||
rec_num += 1
|
||||
|
||||
# Vague requests
|
||||
if mistakes['vague_requests']:
|
||||
recommendations.append(f"{rec_num}. IMPROVE REQUEST CLARITY")
|
||||
recommendations.append(" Problem: Many vague or unclear requests")
|
||||
recommendations.append(" Solutions:")
|
||||
recommendations.append(" - Create request templates in CLAUDE.md")
|
||||
recommendations.append(" - Add examples of good vs. bad requests")
|
||||
recommendations.append(" - Use more specific language and context")
|
||||
recommendations.append(" - Break down complex requests into steps")
|
||||
recommendations.append("")
|
||||
rec_num += 1
|
||||
|
||||
# Multi-step planning
|
||||
if mistakes['multi_step_without_planning']:
|
||||
recommendations.append(f"{rec_num}. BETTER TASK PLANNING")
|
||||
recommendations.append(" Problem: Complex multi-step requests without planning")
|
||||
recommendations.append(" Solutions:")
|
||||
recommendations.append(" - Use 'plan mode' for complex tasks")
|
||||
recommendations.append(" - Break down requests into discrete steps")
|
||||
recommendations.append(" - Create checklists for common workflows")
|
||||
recommendations.append(" - Consider using the feature-planning skill")
|
||||
recommendations.append("")
|
||||
rec_num += 1
|
||||
|
||||
# Error-heavy workflow
|
||||
error_ratio = sum(patterns['error_keywords'].values()) / max(sum(patterns['request_types'].values()), 1)
|
||||
if error_ratio > 0.3:
|
||||
recommendations.append(f"{rec_num}. REDUCE ERROR RATE")
|
||||
recommendations.append(f" Problem: High error rate detected ({error_ratio*100:.1f}% of requests)")
|
||||
recommendations.append(" Solutions:")
|
||||
recommendations.append(" - Implement comprehensive testing before changes")
|
||||
recommendations.append(" - Add validation hooks (pre-commit, pre-push)")
|
||||
recommendations.append(" - Create a testing checklist in CLAUDE.md")
|
||||
recommendations.append(" - Consider TDD approach for new features")
|
||||
recommendations.append("")
|
||||
rec_num += 1
|
||||
|
||||
return "\n".join(recommendations)
|
||||
|
||||
def main():
|
||||
history_path = Path.home() / '.claude' / 'history.jsonl'
|
||||
|
||||
print("Loading conversation history...")
|
||||
all_conversations = load_history(history_path)
|
||||
|
||||
# Focus on recent conversations (last 200)
|
||||
recent_conversations = all_conversations[-200:]
|
||||
|
||||
print(f"Analyzing {len(all_conversations)} total conversations...")
|
||||
print(f"Deep analysis on {len(recent_conversations)} recent conversations...")
|
||||
|
||||
patterns = extract_patterns(recent_conversations)
|
||||
mistakes = identify_common_mistakes(recent_conversations)
|
||||
|
||||
print("\nGenerating reports...")
|
||||
report = generate_report(patterns, mistakes)
|
||||
recommendations = generate_recommendations(patterns, mistakes)
|
||||
|
||||
# Save reports
|
||||
output_dir = Path.cwd()
|
||||
|
||||
# Add header with analysis scope
|
||||
header = f"""
|
||||
ANALYSIS SCOPE
|
||||
==============
|
||||
Total conversations in history: {len(all_conversations)}
|
||||
Recent conversations analyzed: {len(recent_conversations)}
|
||||
Time period: Last 200 interactions
|
||||
|
||||
"""
|
||||
|
||||
with open(output_dir / 'conversation_analysis.txt', 'w') as f:
|
||||
f.write(header)
|
||||
f.write(report)
|
||||
|
||||
with open(output_dir / 'recommendations.txt', 'w') as f:
|
||||
f.write(recommendations)
|
||||
|
||||
print("\n" + "=" * 80)
|
||||
print("Analysis complete! Reports saved to:")
|
||||
print(f" - {output_dir / 'conversation_analysis.txt'}")
|
||||
print(f" - {output_dir / 'recommendations.txt'}")
|
||||
print("=" * 80)
|
||||
|
||||
# Print summary to console
|
||||
print("\n" + report)
|
||||
print("\n" + recommendations)
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
150
skills/project-bootstrapper/SKILL.md
Normal file
150
skills/project-bootstrapper/SKILL.md
Normal file
@@ -0,0 +1,150 @@
|
||||
---
|
||||
name: project-bootstrapper
|
||||
description: Sets up new projects or improves existing projects with development best practices, tooling, documentation, and workflow automation. Use when user wants to start a new project, improve project structure, add development tooling, or establish professional workflows.
|
||||
---
|
||||
|
||||
# Project Bootstrapper
|
||||
|
||||
Sets up new projects or improves existing projects with development best practices, tooling, documentation, and workflow automation.
|
||||
|
||||
## When to Use
|
||||
|
||||
- "set up a new project"
|
||||
- "bootstrap this project"
|
||||
- "add best practices"
|
||||
- "improve project structure"
|
||||
- "set up development tooling"
|
||||
- "initialize project properly"
|
||||
|
||||
## What It Sets Up
|
||||
|
||||
### 1. Project Structure
|
||||
- Standard directories (src/, tests/, docs/, scripts/, .github/)
|
||||
- Logical file organization
|
||||
- Structure improvements
|
||||
|
||||
### 2. Git Configuration
|
||||
- Comprehensive `.gitignore`
|
||||
- `.gitattributes` for line endings/diffs
|
||||
- Git hooks (pre-commit, commit-msg)
|
||||
- Branch protection patterns
|
||||
- Git LFS if needed
|
||||
|
||||
### 3. Documentation
|
||||
- Comprehensive `README.md`
|
||||
- `CONTRIBUTING.md`
|
||||
- Code documentation (JSDoc, docstrings)
|
||||
- `CHANGELOG.md` structure
|
||||
- Architecture docs if complex
|
||||
|
||||
### 4. Testing Setup
|
||||
- Identify/suggest testing framework
|
||||
- Test structure and conventions
|
||||
- Example/template tests
|
||||
- Configure test runners
|
||||
- Coverage reporting
|
||||
- Testing scripts/commands
|
||||
|
||||
### 5. Code Quality Tools
|
||||
- Linters (ESLint, Pylint, etc.)
|
||||
- Formatters (Prettier, Black, etc.)
|
||||
- Type checking (TypeScript, mypy, etc.)
|
||||
- Pre-commit hooks for quality
|
||||
- Editor configs (.editorconfig)
|
||||
- Code quality badges
|
||||
|
||||
### 6. Dependencies Management
|
||||
- Package manager configuration
|
||||
- Organize dependencies
|
||||
- Check security vulnerabilities
|
||||
- Set up dependency updates (Dependabot, Renovate)
|
||||
- Create lock files
|
||||
- Document dependency choices
|
||||
|
||||
### 7. Development Workflow
|
||||
- Useful npm scripts / Makefile targets
|
||||
- Environment variable templates (.env.example)
|
||||
- Docker configuration if appropriate
|
||||
- Development startup scripts
|
||||
- Hot-reload / watch modes
|
||||
- Document development workflow
|
||||
|
||||
### 8. CI/CD Setup
|
||||
- GitHub Actions / GitLab CI config
|
||||
- Automated testing
|
||||
- Automated deployment (if applicable)
|
||||
- Status badges
|
||||
- Release automation
|
||||
- Branch protection
|
||||
|
||||
## Approach
|
||||
|
||||
### Discovery Phase
|
||||
|
||||
Ask clarifying questions:
|
||||
1. **Project type**: New or existing?
|
||||
2. **Primary purpose**: Web app, library, CLI tool?
|
||||
3. **Language/framework**: JS/TS, Python, Go, etc.?
|
||||
4. **Collaboration**: Personal or team?
|
||||
5. **Deployment target**: Server, cloud, mobile, desktop?
|
||||
6. **Preferences**: Specific tools/frameworks?
|
||||
7. **Scope**: Full setup or specific areas?
|
||||
|
||||
### Implementation Phase
|
||||
|
||||
1. **Analyze existing** structure (if existing project)
|
||||
2. **Create plan** based on answers
|
||||
3. **Show plan** and get approval
|
||||
4. **Implement systematically** (one area at a time)
|
||||
5. **Verify completeness**
|
||||
6. **Provide handoff** documentation
|
||||
|
||||
## Customization
|
||||
|
||||
Adapts to:
|
||||
- **Language ecosystem**: Node.js vs Python vs Go vs Rust
|
||||
- **Project size**: Small script vs large app
|
||||
- **Team size**: Solo vs collaborative
|
||||
- **Maturity**: Startup speed vs enterprise standards
|
||||
|
||||
## Tools Used
|
||||
|
||||
- **AskUserQuestion**: Gather requirements
|
||||
- **Write**: Create configuration files, documentation
|
||||
- **Edit**: Update existing files
|
||||
- **Bash**: Initialize tools (git init, npm init)
|
||||
- **Read**: Analyze existing structure
|
||||
- **Glob**: Find files to update
|
||||
|
||||
## Success Criteria
|
||||
|
||||
- All standard files present and configured
|
||||
- Clear and complete documentation
|
||||
- Documented development workflow
|
||||
- Automated quality tooling (pre-commit hooks)
|
||||
- Easy test execution
|
||||
- Follows language/framework conventions
|
||||
- Quick developer onboarding
|
||||
- No obvious best practices missing
|
||||
|
||||
## Templates
|
||||
|
||||
- Node.js/TypeScript web app
|
||||
- Python CLI tool
|
||||
- Python web API (FastAPI/Flask)
|
||||
- React/Next.js app
|
||||
- Go service
|
||||
- Rust CLI/library
|
||||
|
||||
## Integration
|
||||
|
||||
- **feature-planning**: For planning custom features
|
||||
- **code-auditor**: For validating setup quality
|
||||
- **codebase-documenter**: For generating detailed docs
|
||||
|
||||
## Scope Control
|
||||
|
||||
- **Full bootstrap**: Everything from scratch
|
||||
- **Partial setup**: Specific areas only (e.g., "just add testing")
|
||||
- **Improvement pass**: Enhance existing project
|
||||
- **Audit + fix**: Check what's missing and add it
|
||||
Reference in New Issue
Block a user