haddock-development/claude-reflect-system / reflect
reflect
VerifiedAnalyzes conversation transcripts to extract user corrections, patterns, and preferences, then proposes skill improvements. Use this skill when users provide corrections, express preferences about code style, or when patterns emerge from successful approaches. Can be triggered manually with /reflect or automatically at session end when enabled.
| File | Kind | Size |
|---|---|---|
| .state/auto-reflection.json | config | 54 B |
| .state/last-reflection.timestamp | other | 0 B |
| README.md | markdown | 7.3 KB |
| SKILL.md | skill md | 2.8 KB |
| USER_GUIDE.md | markdown | 21.4 KB |
| commands/reflect-meta.md | markdown | 1.6 KB |
| commands/reflect-promote.md | markdown | 1.8 KB |
| commands/reflect-stats.md | markdown | 772 B |
| references/signal-patterns.md | markdown | 6.0 KB |
| scripts/extract_signals.pyexecutable | script | 12.3 KB |
| scripts/hook-stop.shexecutable | script | 2.2 KB |
| scripts/learning_ledger.py | script | 12.6 KB |
| scripts/meta_learning.py | script | 14.8 KB |
| scripts/present_review.pyexecutable | script | 9.9 KB |
| scripts/promote_learning.py | script | 8.0 KB |
| scripts/reflect.pyexecutable | script | 5.3 KB |
| scripts/scope_analyzer.py | script | 8.3 KB |
| scripts/semantic_detector.py | script | 8.1 KB |
| scripts/toggle-off.shexecutable | script | 431 B |
| scripts/toggle-on.shexecutable | script | 499 B |
| scripts/toggle-status.shexecutable | script | 2.5 KB |
| scripts/update_skill.pyexecutable | script | 8.2 KB |
scripts/hook-stop.sh
View on GitHub#!/bin/bash
# Stop hook that triggers reflection when enabled
SKILL_DIR="$HOME/.claude/skills/reflect"
STATE_FILE="$SKILL_DIR/.state/auto-reflection.json"
LOCK_FILE="$SKILL_DIR/.state/reflection.lock"
LOG_FILE="$HOME/.claude/reflect-hook.log"
# Log function
log() {
echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1" >> "$LOG_FILE"
}
log "Stop hook triggered"
# Check if auto-reflection is enabled
if [ ! -f "$STATE_FILE" ]; then
log "State file not found, allowing stop"
exit 0 # Not configured, allow stop
fi
ENABLED=$(cat "$STATE_FILE" | python3 -c "import sys, json; print(json.load(sys.stdin).get('enabled', False))" 2>/dev/null)
if [ "$ENABLED" != "True" ]; then
log "Auto-reflection disabled, allowing stop"
exit 0 # Disabled, allow stop
fi
# Check for stale lock (>10 minutes = 600 seconds)
if [ -f "$LOCK_FILE" ]; then
if [ "$(uname)" = "Darwin" ]; then
# macOS
LOCK_AGE=$(($(date +%s) - $(stat -f %m "$LOCK_FILE")))
else
# Linux
LOCK_AGE=$(($(date +%s) - $(stat -c %Y "$LOCK_FILE")))
fi
if [ $LOCK_AGE -lt 600 ]; then
log "Recent lock exists (age: ${LOCK_AGE}s), skipping"
exit 0 # Recent lock exists, skip
fi
log "Removing stale lock (age: ${LOCK_AGE}s)"
rm "$LOCK_FILE" # Remove stale lock
fi
# Create lock
touch "$LOCK_FILE"
log "Lock created"
# Get transcript path from stdin
INPUT=$(cat)
TRANSCRIPT_PATH=$(echo "$INPUT" | python3 -c "import sys, json; data = json.load(sys.stdin); print(data.get('transcript_path', ''))" 2>/dev/null)
log "Transcript path: $TRANSCRIPT_PATH"
# Run reflection in background to avoid timeout
(
log "Starting background reflection"
export TRANSCRIPT_PATH="$TRANSCRIPT_PATH"
export AUTO_REFLECTED="true"
python3 "$SKILL_DIR/scripts/reflect.py" >> "$LOG_FILE" 2>&1
REFLECT_EXIT=$?
if [ $REFLECT_EXIT -eq 0 ]; then
log "Reflection completed successfully"
# Could add notification here if needed
# echo "🧠 Learned from session" >> "$HOME/.claude/session-env/notification"
else
log "Reflection failed with exit code $REFLECT_EXIT"
fi
rm -f "$LOCK_FILE"
log "Lock removed"
) &
log "Background process spawned, allowing stop"
# Allow stop immediately (don't block the hook)
exit 0
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |