with one click
es-analytics
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。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
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。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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.
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。
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 | es-analytics |
| metadata | {"version":"0.1.2"} |
| description | 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。 |
仅使用 Python 3 标准库(urllib + json),不需要安装任何第三方包。
./es config add <profile-name> \
--url <ES基础URL> \
--user <用户名/AccessID> \
--password <密码/AccessSecret> \
[--default-index <默认索引名>] \
[--sls] \
--test
--sls 标记该连接为阿里云 SLS ES 兼容端点。SLS 端点有以下行为差异,技能会自动处理:
range 条件(除非用户已指定)terms 等聚合作用于未建索引的嵌套字段会报 sls_field_index_not_configed_source 过滤不可靠:部分嵌套字段在 _source 过滤后丢失凭据存储在 ~/.agents/data/es-analytics/profiles.json(权限 0600),支持多 Profile。
./es config list # 列出所有 profile
./es config use <profile-name> # 切换默认 profile
./es config test [profile-name] # 测试连接
./es config remove <profile-name> # 删除 profile
./es query '{"size":10,"query":{"match_all":{}}}'
./es query -i my-index '{"size":5,"sort":[{"@timestamp":"desc"}]}'
./es query -p prod -i logs '{"query":{"match":{"level":"ERROR"}}}'
./es query --format csv '{"size":50,"query":{"term":{"status":"200"}}}'
选项:-p profile / -i 索引 / --format table|csv|json / --full-range(SLS 自动全时间范围)
./es indices # 列出所有索引
./es indices -p prod # 指定 profile
./es indices --filter "chat*" # 过滤索引名
./es mapping my-index # 查看字段定义
./es mapping my-index -p prod # 指定 profile
./es count my-index # 总数
./es count my-index '{"query":{"match":{"level":"ERROR"}}}' # 按条件计数
./es count my-index --full-range # SLS 全时间范围计数
./es extract my-index --field auth_id # 提取去重字段
./es extract my-index --field auth_id --filter '{"match":{"auth_type":"user"}}'
./es extract my-index --field auth_id --full-range -o /tmp/uids.csv
高效分页提取指定字段的唯一值,自动 search_after,适合大数据量去重场景。
./es sample my-index # 最新 5 条数据,展示字段结构
./es sample my-index -n 10 -p prod # 指定数量和 profile
技能已内建以下保护机制:
range 条件覆盖全时间范围(可通过 --no-full-range 禁用)sls_field_index_not_configed 错误时,自动降级为 search_after 分页 + Python 侧聚合_source 过滤功能size: 2000600,密码不出现在命令行输出es (Bash CLI 入口)
│
├── config → config.py 多 Profile 连接管理 (add/list/use/test/remove)
├── query → query.py ES 只读查询 (table/csv/json 输出)
├── indices → indices.py 索引列表
├── mapping → mapping.py Mapping 查看
├── count → count.py 文档计数
├── extract → extract.py 全量去重提取 (search_after)
└── sample → sample.py 采样数据
↓
es_core.py 核心引擎 (HTTP 连接 + 安全 + 输出格式化)
↓
~/.agents/data/es-analytics/
└── profiles.json 连接配置