feat: add decision calibration, prediction tracking, and reference routing

SKILL.md
- Add triggers/mode to frontmatter for better skill routing
- Add mandatory JSON decision skeleton before every trade
- Add multi-source confirmation rule and common-mistakes guardrails
- Add prediction logging to hourly review workflow
- Restructure References into an explicit routing table

CLAUDE.md
- Add Reference routing table for agent context
- Fix remaining Hermes-only wording in gate description

references/user-data-layout.md
- Add complete log schema: decisions, trades, predictions, errors
- Document predictions_YYYYMMDD.jsonl for calibration feedback loop

README.md
- Mention prediction tracking in "Why it works"
- Update runtime directory layout to include predictions.jsonl

references/shim-templates.md
- Show platform cron config usage examples

references/shim-templates.md

@@ -12,11 +12,11 @@ cp scripts/coinhunter_shim.py ~/.hermes/scripts/coinhunter_shim.py
 cp scripts/coinhunter_shim.py ~/.openclaw/scripts/coinhunter_shim.py
 ```
 
-Usage examples:
-- `coinhunter_shim.py pre`
-- `coinhunter_shim.py gate`
-- `coinhunter_shim.py review`
-- `coinhunter_shim.py rotate-log`
+Usage in platform cron configs:
+- `"script": "coinhunter_shim.py pre"` — lightweight gate / precheck
+- `"script": "coinhunter_shim.py gate"` — external gate runner
+- `"script": "coinhunter_shim.py review"` — review context generator
+- `"script": "coinhunter_shim.py rotate-log"` — log rotation helper
 
 The real business logic lives in the external `coinhunter` CLI package (installed from PyPI). This shim only delegates to it.