chore: inicializacao agente auto-melhoria + nova-self-improver + .learnings/ + MEMORY.md

- Adiciona .learnings/ completo (LEARNINGS, ERRORS, FEATURE_REQUESTS, PATTERN_COUNTER)
- Cria MEMORY.md, SESSION-STATE.md, USER.md template
- Cria memory/2026-05-19.md (log diario)
- cria IDENTITY.md (Pulse ⚡)
- Atualiza AGENTS.md, SOUL.md, TOOLS.md com regras de auto-melhoria
- Instala nova-self-improver v1.0.0 via clawhub
- Skills totais: 6 instaladas

skills/self-improvement/scripts/activator.sh

@@ -0,0 +1,20 @@
+#!/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