reflect

Reflect Workflow

Analyze the current session to identify workflow improvements.

Mode

$ARGUMENTS

• full or empty: Full analysis with Gemini
• quick: Local analysis only (faster)
• patterns: Cross-session pattern analysis

Step 1: Find Transcript

# Get project hash for this directory
PROJECT_HASH=$(echo -n "$(pwd)" | md5sum | cut -d' ' -f1)
TRANSCRIPT_DIR=~/.claude/projects/$PROJECT_HASH

# Find most recent transcript
TRANSCRIPT=$(ls -t $TRANSCRIPT_DIR/*.jsonl 2>/dev/null | head -1)
echo "Transcript: $TRANSCRIPT"

If no transcript found, inform user and exit.

Step 2: Parse Session Data

Read the transcript and extract:

1. Tool calls (name, input, success/failure)
2. User messages (for corrections/friction)
3. Errors and retries

# Count tool calls and errors
cat "$TRANSCRIPT" | grep -c '"type":"tool_use"' || echo 0
cat "$TRANSCRIPT" | grep -c '"is_error":true' || echo 0

Step 3: Analyze Issues

Tool Failures

• Look for "is_error": true in tool results
• Note which tools failed and why
• Check for permission, path, or syntax errors

Retry Patterns

• Detect same tool called 3+ times consecutively
• Indicates approach not working

User Corrections

Scan user messages for friction signals:

• "no, I meant..."
• "actually..."
• "wait", "stop"
• Redirections or corrections

Efficiency Issues

• Same file read 3+ times
• Same search pattern used repeatedly
• Long gaps between actions

Step 4: Generate Analysis

Quick Mode

Summarize findings locally without external calls.

Full Mode

Use Gemini for deeper analysis:

gemini "Analyze this Claude Code session transcript for improvements.

Transcript path: $TRANSCRIPT

Look for:
1. Tool failures and their causes
2. Workflow friction (user corrections, abandoned approaches)
3. Missing capabilities that required workarounds
4. Efficiency issues (repeated operations, unnecessary steps)

For each issue found, suggest:
- A specific improvement (skill, hook, or agent enhancement)
- Priority (HIGH/MEDIUM/LOW)
- How to implement it

Output in this format:
ISSUE: <description>
CATEGORY: Tool Failure | Friction | Missing Capability | Efficiency
PRIORITY: HIGH | MEDIUM | LOW
EVIDENCE: <relevant excerpt>
SUGGESTION: <specific improvement>
IMPLEMENTATION: <how to add the improvement>"