← 返回 Skills 市场
655
总下载
2
收藏
2
当前安装
3
版本数
在 OpenClaw 中安装
/install metric-query
功能描述
构建指标平台（语义层）的指标数据查询 API 请求。当用户需要查询指标数据、构造指标查询API请求体、使用同环比/占比/排名/时间限定等快速计算、定义临时指标、设置维度筛选过滤条件时，必须使用此 Skill。 触发场景包括但不限于：用户提到"查询指标"、"指标API"、"指标数据"、"语义层查询"、"metric...
安全使用建议
Before installing, confirm you trust aloudata.com and are comfortable storing a CAN_API_KEY for the Gateway in your agent environment. This skill will read that env var and make outbound requests to gateway.can.aloudata.com to discover metrics and execute queries — ensure the API key has appropriate (least) privileges and rotate it if you suspect misuse. If you do not use Aloudata CAN, do not provide a CAN_API_KEY. Monitor network activity and API usage for unexpected calls.
功能分析
Type: OpenClaw Skill
Name: metric-query
Version: 1.0.2
The metric-query skill bundle is a legitimate tool designed to help an AI agent construct complex JSON payloads for the Aloudata CAN metrics gateway API. It contains extensive documentation and 'iron rules' to ensure the agent generates valid queries, handles relative time correctly using NOW(), and avoids common logic errors in data analysis. While the skill requires 'env:read' for an API key and 'network:outbound' to 'gateway.can.aloudata.com', these permissions are strictly aligned with its stated purpose, and no evidence of data exfiltration, malicious execution, or harmful prompt injection was found in SKILL.md or _meta.json.
能力评估
Purpose & Capability
Name/description match the runtime instructions: the SKILL.md describes how to discover metrics/dimensions via the Aloudata CAN Gateway and then construct the metrics query JSON. The declared requirement (CAN_API_KEY) and the domain whitelist (gateway.can.aloudata.com) are exactly what this purpose needs.
Instruction Scope
SKILL.md instructs only to call the Gateway search and query endpoints, read the CAN_API_KEY env var, and construct JSON per a clear set of rules. It does not instruct reading unrelated files, other env vars, or sending data to endpoints outside gateway.can.aloudata.com. The doc explicitly forbids guessing metric names and mandates Gateway lookups first.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is written to disk or downloaded during install, which minimizes installation risk.
Credentials
Only one required environment variable (CAN_API_KEY) is declared and used; this is expected for authenticating to the Gateway. The SKILL.md documents where the user should store the key (~/.openclaw/.env). There are no additional unrelated credentials requested.
Persistence & Privilege
always is false and the skill is user-invocable; autonomous invocation is allowed (platform default). The skill does not request permanent/system-wide privileges or attempt to modify other skills or agent configs.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install metric-query - 安装完成后，直接呼叫该 Skill 的名称或使用
/metric-query触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.2
No functional changes introduced in this version.
- Updated SKILL.md to add explicit metadata fields: permissions, env_vars, domain_whitelist, version, author, homepage, metadata.openclaw.
- No code or logic modifications.
- No API or behavior changes.
v1.0.1
**Changelog for metric-query 1.0.1**
- Added _meta.json for enhanced metadata management.
- Gateway API Key使用方法更正：示例命令改为从环境变量 $CAN_API_KEY 读取，而非硬编码为 {your-api-key}，需在本地配置 .env 文件。
- 优化文档内容，细化了 curl 用法示例，强调所有调用必须使用环境变量方式传递 API Key。
v1.0.0
Initial release of metric-query: an API skill for metric data querying.
- Enables construction of metric data query API requests, including defining temporary metrics, filters, time constraints, quick calculations (YoY/MoM/Proportion/Ranking), and dimensional filtering.
- Must use Gateway API to search for metric and dimension info before building any query—strictly prohibits guessing names from memory.
- Comprehensive rules (九条铁律) ensure correct JSON formation, API usage, and prevent logical/query errors (e.g., date handling, metric registration, calculation chaining, filter misuse, etc.).
- Rejects any query if metric/dimension context is insufficient or user intention doesn't match a data query.
- Provides detailed API examples and strict guidelines for building requests and using authentication.
元数据
常见问题
Aloudata CAN SKILLS - metric-query 是什么？
构建指标平台（语义层）的指标数据查询 API 请求。当用户需要查询指标数据、构造指标查询API请求体、使用同环比/占比/排名/时间限定等快速计算、定义临时指标、设置维度筛选过滤条件时，必须使用此 Skill。 触发场景包括但不限于：用户提到"查询指标"、"指标API"、"指标数据"、"语义层查询"、"metric... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 655 次。
如何安装 Aloudata CAN SKILLS - metric-query？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install metric-query」即可一键安装，无需额外配置。
Aloudata CAN SKILLS - metric-query 是免费的吗？
是的，Aloudata CAN SKILLS - metric-query 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Aloudata CAN SKILLS - metric-query 支持哪些平台？
Aloudata CAN SKILLS - metric-query 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Aloudata CAN SKILLS - metric-query？
由 jackyujun（@jackyujun）开发并维护，当前版本 v1.0.2。
推荐 Skills