Prompt Coach - Claude Code 使用分析与提示词优化 Skill

cd ~/code/claude-code-prompt-coach-skill
./install.sh

cp -r ~/code/claude-code-prompt-coach-skill ~/.claude/skills/prompt-coach

ln -s ~/code/claude-code-prompt-coach-skill ~/.claude/skills/prompt-coach

"How much have I spent on tokens this month?"
"Analyze my prompt quality from last week"
"Which tools do I use most?"
"Show me my productivity patterns"
"What files do I edit most often?"
"When am I most efficient?"

"List all projects with Claude Code logs"
"Show me which projects I've worked on"
"What projects do I have session logs for?"

"Analyze my prompt quality for the project under ~/code/youtube/transcript/mcp"
"Analyze my prompt quality for /Users/username/code/my-app and save it as report.md"
"Show me token usage for the project in ~/code/experiments"
"What tools do I use most in the ~/code/my-app project?"

📊 Token Usage Analysis (Last 30 Days)

Input tokens: 450,000 ($1.35)
Output tokens: 125,000 ($1.88)
Cache writes: 200,000 ($0.75)
Cache reads: 1,500,000 ($0.45)
─────────────────
Total cost: $4.43

Cache savings: $4.05
Cache efficiency: 75% hit rate

💡 Tip: Your cache hit rate is excellent! You're saving ~$4/month by keeping focused sessions.

📝 Prompt Quality Analysis (Last 14 Days)

Total prompts: 145
Needed clarification: 51 (35%)
Average prompt score: 5.2/10 (Good, room for improvement)

🚩 Most Common Missing Elements:
1. File paths: Missing in 61 prompts (42%)
2. Error details: Missing in 34 prompts (23%)
3. Success criteria: Missing in 43 prompts (30%)
4. Specific approach: Missing in 28 prompts (19%)

🔴 Real Examples from Your Logs:

**Example 1: Missing File Context**
❌ Your prompt: "fix the bug"
🤔 Claude asked: "Which file has the bug? What's the error message or symptom?"
✅ Better prompt: "fix the authentication bug in src/auth/login.ts where JWT validation fails with 401 error"
📉 Cost: +2 minutes, +1 iteration

📉 Impact Analysis:
- 51 prompts needed clarification
- Average time lost per clarification: 2.8 minutes
- Total time lost to vague prompts: ~2.4 hours
- **Potential time savings: ~1.2 hours by improving top 25 vague prompts**

🎯 Your Top 3 Improvements (Maximum Impact):

**1. Always Include File Paths (42% of clarifications)**
Template: "[action] in [file path] [details]"
💰 Impact: Would eliminate ~21 clarifications (~1 hour saved)

**2. Provide Error Details When Debugging (23% of clarifications)**
Template: "fix [error message] in [file] - expected [X], getting [Y]"
💰 Impact: Would eliminate ~12 clarifications (~25 min saved)

**3. Define Success Criteria for Vague Actions (30% of clarifications)**
Instead of: "optimize", "improve", "make better"
Use: "[action] to achieve [specific measurable outcome]"
💰 Impact: Would eliminate ~15 clarifications (~40 min saved)

🛠️ Tool Usage Patterns (Last 30 Days)

Most used tools:
1. Read  ████████████████████ 450 uses
2. Edit  ████████████ 220 uses
3. Bash  ███████ 150 uses
4. Grep  ██ 34 uses

💡 Insights:
✅ Good: You use Read heavily - shows careful code review
⚠️ Opportunity: Low Grep usage (34 uses vs 450 Reads)
   → Try Grep for searching across multiple files
   → It's much faster than reading each file

### 9. Your Custom Analysis

**When asked about [your topic]:**

**Steps:**
1. Read session files
2. Look for [pattern]
3. Calculate [metric]
4. Present [insights]