- New skills: clawddocs, claude-code-usage, summarize, homeassistant, humanizer, self-improving-agent - Add .learnings/ for self-improvement tracking - Document proaktive cron config (LRN-20260126-001) - Update USER.md: Löchgau as former residence - Update TOOLS.md: Peekaboo workaround - Memory files for 2026-01-25 and 2026-01-26
21 lines
680 B
Bash
21 lines
680 B
Bash
#!/bin/bash
|
|
# Self-Improvement Activator Hook
|
|
# Triggers on UserPromptSubmit to remind Claude about learning capture
|
|
# Keep output minimal (~50-100 tokens) to minimize overhead
|
|
|
|
set -e
|
|
|
|
# Output reminder as system context
|
|
cat << 'EOF'
|
|
<self-improvement-reminder>
|
|
After completing this task, evaluate if extractable knowledge emerged:
|
|
- Non-obvious solution discovered through investigation?
|
|
- Workaround for unexpected behavior?
|
|
- Project-specific pattern learned?
|
|
- Error required debugging to resolve?
|
|
|
|
If yes: Log to .learnings/ using the self-improvement skill format.
|
|
If high-value (recurring, broadly applicable): Consider skill extraction.
|
|
</self-improvement-reminder>
|
|
EOF
|