원클릭으로
adb-mysql
阿里云 AnalyticDB (ADB) for MySQL 只读数据分析。 多维分析(计数/聚合/时间序列)、交叉验证、Schema 文档生成、多 Profile。
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
阿里云 AnalyticDB (ADB) for MySQL 只读数据分析。 多维分析(计数/聚合/时间序列)、交叉验证、Schema 文档生成、多 Profile。
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Multi-agent brainstorming: async opinion collision with expert personas. Mixed Codex/Claude Code engine. Use when multiple AI agents need to collaboratively discuss, debate, and converge on solutions through structured dialog. Triggers: brainstorm, multi-perspective discussion, opinion collision, expert debate, war room, collective intelligence, 头脑风暴, 多视角讨论, 集思广益.
Elasticsearch / SLS 只读数据分析:索引探索、mapping、聚合统计、日志搜索、时间序列、多 Profile。
AI image generation and editing: e-commerce templates (hero/banner/detail/lifestyle), image refinement (background replace/remove, enhance, retouch, style transfer), icon extraction (bg-removal + detect + smart crop with transparent output).
Feishu (Lark) unified CLI for tasks, documents, wiki, bitable, messaging, approval, and Drive. Supports search/create/edit/publish/export across all modules. Use when reading/writing Feishu docs, searching docs or wiki, managing tasks, sending messages, creating approvals, exporting to Markdown, or any 飞书/Lark interaction.
Multi-agent SWE team built on the Workshop model. Full-stack vertical workers, meeting room with @mention notification, private pipes, shared task board. Git worktree isolation, Leader-driven coordination. Mixed Codex/Claude Code engine. Use when a task needs engineering depth beyond a single agent. NOT for simple task parallelism (use agent-task-orchestration) or design discussions (use agent-brainstorm).
Frontend design blueprints with craftsmanship scoring, self-critique loops, and engineering handoff. Aesthetic intelligence against AI homogeneity. Use for: UI/UX design specs, design system creation, visual direction exploration, component design review, design-to-engineering handoff.
| name | adb-mysql |
| metadata | {"version":"0.1.2"} |
| description | 阿里云 AnalyticDB (ADB) for MySQL 只读数据分析。 多维分析(计数/聚合/时间序列)、交叉验证、Schema 文档生成、多 Profile。 |
pip install pymysql
仅依赖 pymysql(纯 Python MySQL 驱动),无需本地 mysql 客户端。
./adb config add <profile-name> \
--host <DMS代理地址或ADB实例地址> \
--user <AccessID或用户名> \
--password <AccessSecret或密码> \
--database <数据库名> \
--test
凭据存储在 ~/.adb-mysql/profiles.json(权限 0600),支持多 Profile。
./adb config list # 列出所有 profile
./adb config use <profile-name> # 切换默认 profile
./adb config test [profile-name] # 测试连接
./adb config remove <profile-name> # 删除 profile
./adb query "SELECT * FROM users LIMIT 10"
./adb query -d mydb "SELECT COUNT(*) FROM orders"
./adb query -f report.sql --format csv
./adb query -p staging "SELECT 1" # 指定 profile
选项:-p profile / -d 数据库 / -f SQL 文件 / --format table|csv|json
./adb analyze -t orders -c # 计数分析
./adb analyze -t orders -g status -a "SUM(amount)" # 聚合分析
./adb analyze -t orders --time-col created_at \
--start-date 2024-01-01 --end-date 2024-02-01 # 时间序列
每次分析自动执行交叉验证:总行数 → 随机样本 → 数值统计 → 时间范围。
./adb schema mydb # 生成到 ~/.adb-mysql/schema/mydb/
./adb schema mydb -o ./docs/schema # 自定义输出目录
为所有表生成 Markdown 文档(字段定义、索引、ADB 分布键、查询示例)+ 索引文件。
Agent 工作流: 首次分析某数据库前,先运行 ./adb schema 生成文档到 ~/.adb-mysql/schema/,后续分析时读取作为上下文。
LIMIT 200,超出自动截断0600,密码不出现在命令行参数adb (Bash CLI 入口)
│
├── config → config.py 多 Profile 连接管理 (add/list/use/test/remove)
├── query → query.py SQL 只读查询 (table/csv/json 输出)
├── analyze → analyze.py 多维分析 + 交叉验证
└── schema → schema.py Schema 文档生成 (Markdown)
↓
adb_core.py 核心引擎 (pymysql 连接 + SQL 安全 + 输出格式化)
↓
~/.adb-mysql/
├── profiles.json 连接配置
└── schema/ Schema 文档输出