keyword cleanup: v2 engine, alias rule layer, LLM semantic suggestions

- build_review_bundle.py: 新增 _compute_percentile/_compute_growth,
  候选池从固定阈值改为百分位排名 + 增速因子 (v2 policy)
- term_cleanup_policy.json: 升级 v2 schema
- generate_term_cleanup_suggestions.py: 新增 _prepare_alias_suggestions,
  规则层输出 alias (大小写/单复数/分词变体)
- generate_term_cleanup_semantic_suggestions.py: 新增 LLM 语义建议脚本
  (DeepSeek API, 产出 semantic alias/stopword/promote)
- SKILL.md: 更新为 5 Phase 工作流程
- 首轮清洗 apply: interest 54, aliases 17组, stopwords 17个
- docs/design/keyword-cleanup-flow-overview.md: 流程文档
- plans/: 引擎设计方案

configs/term_aliases.json

@@ -1,5 +1,19 @@
 {
   "AI助手": "AI Agent",
   "图文RAG": "RAG",
-  "Prompt架构": "Prompt Engineering"
+  "Prompt架构": "Prompt Engineering",
+  "Agent Skill": "Agent Skills",
+  "Binlog": "binlog",
+  "Coding Agent": "AI Coding Agent",
+  "Subagent": "SubAgent",
+  "Subagents": "SubAgent",
+  "vibe coding": "Vibe Coding",
+  "Agent架构": "AI Agent",
+  "Agent专业化": "AI Agent",
+  "Agent Teams": "多Agent协作",
+  "Agentic Engineering": "AI Agent",
+  "CLI工具": "CLI",
+  "AI编程": "AI Coding Agent",
+  "记忆管理": "上下文管理",
+  "会话管理": "上下文管理"
 }