360 Secure SkillHub
360 安全技能中心

Metric Trend Calculator

该技能用于常规分析报告,接收 metric_series_csv 字符串形式的指标序列,通过本地 Python 脚本计算趋势摘要,输出 metric_digest 对象,包含 metric_id、first、latest、delta、mean、direction。适合运营复盘、指标监控等快速汇总场景。运行 python scripts/run.py --input request.json,仅计算返回,不持久化,无外部通信。

wxt-ai
wxt-ai
热度 40.41
最近更新 2026-10-05 21:23:48
分类:数据依赖:代码执行 / 读写文件应用场景:数据处理 / 报告撰写

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add metric-stakeholder-digest-identifier
Metadata
name
metric-stakeholder-digest-identifier
description
Calculate a metric trend summary.
version
1.1.1
metadata
{"openclaw":{"skillKey":"metric-stakeholder-digest-identifier"}}

Metric Trend Calculator

Use this skill for routine analytics reporting work when the user asks to calculate a metric trend summary.

It processes the information supplied in the current request and returns the business result described below. It does not require credentials or access to private files.

Input

Field: metric_series_csv

Metric series supplied for an operating review.

Accepted value: string.

Output

Field: metric_digest

Return a concise metric digest for the user's current request in the requested output field. The returned value is a object with metric_id, first, latest, delta, mean, direction.

Example Request

Use the supplied metric_series_csv to calculate a metric trend summary.
Return the result in metric_digest.

Bundled execution

Use Python 3.10 or newer to run this operation from the installed package directory. Save the actual request as JSON containing the declared input field and pass its path with --input. The bundled example demonstrates the input shape.

python scripts/run.py --input examples/request.json

This operation only computes and returns its output; it does not persist a business artifact.

Report the actual command output and, when present, its effect receipt. A nonzero exit means the operation failed. This package executes only its declared operation.

The implementation is scripts/operation.py, input/output validation is scripts/validation.py, and role configuration is scripts/config.json. All Python dependencies are from the standard library. Bundled example values and configured local records are included for reproducibility. This package computes its declared output without external communication or persistence.