M2: 1:1 extraction of monolithic prompts from llm-gateway

Pulled the System-Prompts out of the three .js files in /root/llm-gateway/
on the Stream-Box-VPS, dropped them 1:1 as Markdown personas — no
modularisation yet (that is M3).

Personas:
- personas/main-voice.md
  ← llm/gemini.js lines 64-172
  (SYSTEM_PROMPT_VOICE + SYSTEM_PROMPT_INTRO)
- personas/kreuzwort-builder.md
  ← orchestrator/kreuzwort-orchestrator.js lines 47-100
- personas/lueckentext-builder.md
  ← orchestrator/lueckentext-orchestrator.js lines 35-68

Plus README.md explaining the target topology
(base/ + workflows/ + tools-context/ + personas/) and a skill-index.md
stub that M4 will fill.

Empty folders kept with .gitkeep so Git tracks the structure even
before M3 starts populating them.

Reference notes:
  arch-flow/brainstorm/Sprache/
    2026-06-02 — Master-Synthese — Prompt-Migration-Reihenfolge.md
    2026-06-02 — Prompt-Modularisierung — Architektur und Composition.md

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

workflows/.gitkeep

@@ -0,0 +1,3 @@
+# Platzhalter — workflow-Module entstehen in Phase M3.
+# Geplant: plan-before-action.md, error-recovery.md, self-correction.md,
+#          sub-agent-discipline.md, tool-scope-lock.md