chore: import .claude command skills, CLAUDE.md, .gitignore, next_steps.md

- Vendor local .claude/ command skills (autopilot, plan, implement, etc.)
- Add CLAUDE.md pointing slash commands to .claude/commands/*/SKILL.md
- Untrack docs-Lokal/ and ignore .planning/ for local-only planning docs
- Include next_steps.md pulled from upstream

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

.claude/commands/plan/templates/performance-tests.md

@@ -0,0 +1,35 @@
+# Performance Tests Template
+
+Save as `DOCUMENT_DIR/tests/performance-tests.md`.
+
+---
+
+```markdown
+# Performance Tests
+
+### NFT-PERF-01: [Test Name]
+
+**Summary**: [What performance characteristic this validates]
+**Traces to**: AC-[ID]
+**Metric**: [what is measured — latency, throughput, frame rate, etc.]
+
+**Preconditions**:
+- [System state, load profile, data volume]
+
+**Steps**:
+
+| Step | Consumer Action | Measurement |
+|------|----------------|-------------|
+| 1 | [action] | [what to measure and how] |
+
+**Pass criteria**: [specific threshold — e.g., p95 latency < 400ms]
+**Duration**: [how long the test runs]
+```
+
+---
+
+## Guidance Notes
+
+- Performance tests should run long enough to capture steady-state behavior, not just cold-start.
+- Define clear pass/fail thresholds with specific metrics (p50, p95, p99 latency, throughput, etc.).
+- Include warm-up preconditions to separate initialization cost from steady-state performance.