feat: add skills, memory, delegation and self-learning (Phase 3)

Add three Hermes-inspired capabilities to Shira:

- Skills system: firm-wide workflow templates (list/view/manage tools),
  4 pre-seeded skills (case summary, hearing prep, direct access report,
  deadline tracker), auto-learning via post-conversation meta-prompt
- Cross-conversation memory: per-lawyer profiles and per-case memory
  stored as bounded markdown files, injected into system prompts
- Sub-agent delegation: spawn up to 3 child AgentRunner instances for
  parallel document analysis and complex multi-step tasks

New files: skills.py, memory.py, delegate.py, learner.py, 4 SKILL.md
Updated: agent_runner (6 new tools, depth/blocked_tools support),
prompt_builder (skills/memory injection), route (memory loading,
background learning), main.py (data dirs), Dockerfile (pyyaml, skills)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.env.example

@@ -11,7 +11,11 @@ AI_GATEWAY_API_KEY=
 # Claude model (passed through to ai-gateway)
 CLAUDE_MODEL=sonnet
 MAX_OUTPUT_TOKENS=4096
+MAX_AGENT_ITERATIONS=10
 
 # EspoCRM — for MCP tools
 ESPOCRM_URL=https://espocrm.dev.marcus-law.co.il
 ESPOCRM_API_KEY=
+
+# Data directory — persistent volume for skills, memory, profiles
+SHIRA_DATA_DIR=/opt/data