hologres-ai-plugins

AI-agent-friendly Hologres CLI with safety guardrails and structured JSON output. Use for database operations, schema inspection, SQL execution, data import/export, Dynamic Table lifecycle management (V3.1+ syntax), and GUC parameter management. Triggers: "hologres cli", "hologres command", "hologres database", "dynamic table", "hologres查询", "hologres guc", "GUC parameter"

Hologres 运维诊断日报生成技能。生成一份"诊断结论 + 根因解释 + 行动建议"的每日巡检报告， 覆盖实例健康、可用性、计算资源、SQL 性能、成本治理、容量预测六大维度。 触发词：日报、每日巡检、daily report、运维日报、诊断日报、实例巡检报告、每日健康报告。 实例 / 计算组 / SQL 数据通过 `hologres instance-manage get` / `hologres warehouse` / `hologres sql run` 获取；云监控数据通过 `hologres metric query` 获取。

Hologres 实例 CPU 使用率异常诊断技能。当用户提到 CPU 打满、CPU 持续高位、Worker CPU 不均、负载诊断、CPU 归因分析、后台 Compaction 干扰等场景时使用。 以 instance_id + 时间窗口为输入，自动完成 CPU 状态分级（持续打满 / 持续高位 / 安全平稳）、四象限归因诊断（宏观定性 / 分布定位 / 查询归因 / 后台任务干扰），并输出结构化的 Markdown 诊断报告与治理行动清单。 云监控数据通过 `hologres metric query` / `hologres metric latest` 获取；元仓与 PG 系统表数据通过 `hologres sql run` 获取，全程享有 hologres-cli 的安全护栏、JSON 结构化输出与自动错误重试能力。

Hologres 实例内存使用率异常诊断技能。当用户提到内存打满、OOM、内存持续高位、Worker 内存不均、内存泄漏、内存倾斜、内存归因分析等场景时使用。 以 instance_id + 时间窗口为输入，自动完成内存水位形态判定（全局高 / 局部倾斜 / 持续不回落）、业务指标对齐、内存分类初筛（Query vs System/Cache）， 并沿 Query 主线、倾斜主线、Write/后台主线、System/元数据主线四大归因维度自动下钻，输出结构化的 Markdown 诊断报告与治理行动清单。 云监控数据通过 `hologres metric query` / `hologres metric latest` 获取；元仓与 PG 系统表数据通过 `hologres sql run` 获取；OOM/Jeprof/Coredump 通过 `holo oncall common` 获取。

Hologres Query Execution Plan Analyzer and Optimizer. Use for analyzing SQL performance issues, understanding EXPLAIN/EXPLAIN ANALYZE output, interpreting query operators, and providing optimization recommendations for Hologres queries. Users may provide a query_id, raw SQL query, or pasted EXPLAIN ANALYZE result text. SQL execution / 慢日志查询通过 `hologres sql run` / `hologres sql explain`；GUC 通过 `hologres guc` 操作。 Triggers: "hologres explain", "query plan", "execution plan", "sql optimization", "query performance", "hologres performance", "slow query", "query optimizer", "explain analyze", "query_id"

Hologres slow query log analysis and diagnosis skill. Use for analyzing slow queries, failed queries, query performance diagnosis, and log management in Alibaba Cloud Hologres. All SQL is executed via `hologres sql run` (`hologres sql run --no-limit-check`). Triggers: "hologres slow query", "hg_query_log", "query diagnosis", "慢Query分析", "Hologres性能诊断"

通过 Hologres AI Function 生成广告素材并模拟投放效果分析。适用于广告视频生成、素材转视频、虚拟投放模拟及 ROI 分析场景。

Hologres Knowledge Base Management: Build search & RAG knowledge bases on Hologres using full-text inverted index (Tantivy + BM25), HGraph vector index, and holo-search-sdk. Covers create knowledge base → ingest documents (with embeddings) → vector / full-text / hybrid search → Q&A with LLM. Triggers: "知识库", "knowledge base", "RAG", "向量检索", "vector search", "全文检索", "fulltext search", "倒排索引", "BM25", "HGraph", "holo-search-sdk", "embedding", "混合检索", "hybrid search", "Hologres 搜索", "Hologres search", "tantivy", "jieba", "ik 分词", "向量索引"

Hologres 实例健康诊断与巡检分析。当用户提到实例健康诊断、实例巡检、实例使用状况分析、慢查询分析、报错分析、Warehouse 资源分析、连接数分析、CPU 内存使用分析、查询失败排查等场景时使用。覆盖 Warehouse 资源巡检、FAILED 报错归类分析、CPU/内存粒度慢查询分析三大核心模块，输出结构化诊断报告和优化建议。 所有 SQL 通过 hologres-cli 执行，享有安全护栏、结构化 JSON 输出和自动错误重试能力。

Hologres BSI（位切片索引）画像分析 Skill，用于用户画像和标签计算。 适用于 BSI 表设计、数据导入、属性标签+行为标签联合人群圈选、 GMV 分析、标签分布统计、Top K 查询、分桶并行计算等场景。 Triggers: "BSI", "位切片索引", "画像分析", "用户画像", "标签计算", "人群圈选", "行为标签", "bsi_build", "bsi_sum", "bsi_filter", "bsi_stat", "bsi_topk", "roaring bitmap profile", "标签圈人", "分桶计算"

Hologres privilege management using PostgreSQL standard authorization model (expert permission model). Use for creating users, granting/revoking Schema/table/column/view privileges, configuring default privileges for future objects, diagnosing permission issues, and planning role-based access control. Triggers: "hologres权限", "hologres grant", "hologres revoke", "permission denied", "权限管理", "hologres privileges", "hologres authorization", "default privileges", "角色权限", "授权"

Hologres DDL schema design and table creation expert. Use for generating CREATE TABLE statements, choosing storage formats (column/row/row-column), configuring table properties (distribution_key, clustering_key, bitmap_columns, event_time_column), designing partition tables, selecting data types, and optimizing table schemas for different query patterns. Triggers: "hologres建表", "hologres create table", "hologres schema", "hologres DDL", "distribution_key", "clustering_key", "bitmap_columns", "event_time_column", "列存", "行存", "行列共存", "分区表", "hologres table design", "表设计", "hologres数据类型"

Hologres UV/PV computation using Dynamic Tables and RoaringBitmap for real-time deduplication at scale. Use for building incremental UV/PV pipelines, RoaringBitmap-based user deduplication, flexible time-range UV aggregation, and text-to-int UID encoding for bitmap compatibility. Triggers: "hologres uv", "hologres pv", "roaringbitmap", "rb_build_agg", "rb_or_agg", "去重", "UV计算", "用户去重", "bitmap去重", "实时UV", "hg_id_encoding"