← 返回 Skills 市场
Metric Definition Catalog
作者
vx：17605205782
· GitHub ↗
· v1.0.0
· MIT-0
158
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install metric-definition-catalog
功能描述
把散落指标统一整理成口径、公式、归属、例外情况与常见误用。；use for metrics, catalog, analytics workflows；do not use for 编造指标来源, 替代 BI 平台配置.
安全使用建议
This skill appears to be what it says: a local tool to structure metric definitions and audit related files. Before installing or running it, review scripts/run.py yourself and run it in a controlled workspace. Do not point the script at system roots or directories containing secrets (e.g., /etc, your home dir, cloud credential files) unless you intentionally want those files scanned. Prefer --dry-run and output to a sandbox file, and inspect generated output for any redacted or sensitive content before sharing. If you need stronger isolation, run the script in a container or VM. If you want confirmation, request the author/publisher identity or run the included tests/smoke-test locally first.
功能分析
Type: OpenClaw Skill
Name: metric-definition-catalog
Version: 1.0.0
The skill bundle is a legitimate tool designed for organizing data metric definitions and performing basic governance audits. The primary script, `scripts/run.py`, processes local text and CSV files to generate structured reports and includes a 'pattern_audit' mode that proactively identifies (and masks) potential secrets or dangerous shell commands rather than executing them. The instructions in `SKILL.md` and `README.md` emphasize safety boundaries, read-only operations, and the requirement for human review before any system changes.
能力评估
Purpose & Capability
Name/description, SKILL.md, resources, and the included scripts all align: the bundle is designed to take metric-related inputs (files or text) and produce structured Markdown reports or audits. Requested binary (python3) and declared file resources are proportionate to the stated functionality.
Instruction Scope
SKILL.md instructs running scripts/run.py to produce reports and to prefer read-only/dry-run outputs. The script legitimately reads files, directories, and CSVs and can perform directory-level scans and pattern checks. This is coherent for analysis/audit use, but it means the skill can read arbitrary user-supplied file paths (including code, configs, CSVs)—so users should not point it at system or secret-containing directories unless they intend that.
Install Mechanism
No install spec or external downloads; this is an instruction-plus-local-script skill that only requires an existing python3 on PATH. No network fetches or archive extractions are performed by the skill package itself.
Credentials
No environment variables, secrets, or external credentials are requested. The script includes secret-detection regexes (to flag possible secrets) but does not contain or require credentials itself.
Persistence & Privilege
Skill is user-invocable, not forced-always, and does not request persistent agent-wide privileges or attempt to modify other skills. It can be invoked autonomously per platform defaults, which is expected behavior and not in itself a concern.
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-definition-catalog - 安装完成后，直接呼叫该 Skill 的名称或使用
/metric-definition-catalog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
v1.0.0
Initial release of metric-definition-catalog skill.
- Consolidates dispersed metric definitions, formulas, responsibilities, exceptions, and common misuses into a unified catalog.
- Designed for analytics workflows; not a replacement for BI platform configuration or metric source creation.
- Produces structured outputs: metric directory, definition, calculation, non-applicable scenarios, common misuses, and maintenance suggestions.
- Emphasizes information completeness, review drafts, explicit boundaries, and safe read-only operations.
- Supports both script-based and direct template-based outputs depending on environment capabilities.
元数据
常见问题
Metric Definition Catalog 是什么？
把散落指标统一整理成口径、公式、归属、例外情况与常见误用。；use for metrics, catalog, analytics workflows；do not use for 编造指标来源, 替代 BI 平台配置. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 158 次。
如何安装 Metric Definition Catalog？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install metric-definition-catalog」即可一键安装，无需额外配置。
Metric Definition Catalog 是免费的吗？
是的，Metric Definition Catalog 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Metric Definition Catalog 支持哪些平台？
Metric Definition Catalog 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（darwin, linux, win32）。
谁开发了 Metric Definition Catalog？
由 vx：17605205782（@52yuanchangxing）开发并维护，当前版本 v1.0.0。
推荐 Skills