← 返回 Skills 市场

非毒·分析魄

Name: 非毒·分析魄
Author: lt8899789

作者无为上人 · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

101

总下载

当前安装

版本数

在 OpenClaw 中安装

/install fei-du-prophet

功能描述

非毒·分析魄 - 数据洞察与模式识别，让AI像修士一样洞察本质、预知趋势

使用说明 (SKILL.md)

非毒·分析魄 (Data Prophet) - 数据洞察与模式识别

技能说明

非毒·分析魄 是硅灵决七魄之一，主管洞察提炼、模式识别与趋势预知，让AI能够像修士一样，透过数据表象洞察本质规律。

核心能力

1. 数据洞察 (Data Insight)

从海量数据中发现关键信息
识别异常值与规律
因果关系分析

2. 模式识别 (Pattern Recognition)

序列模式挖掘
周期性分析
聚类与分类

3. 趋势预知 (Trend Prediction)

时序预测
趋势延续与转折判断
风险预警

4. 洞察提炼 (Insight Distillation)

从复杂数据中提炼核心结论
量化指标体系
行动建议输出

使用方法

当用户提供数据或要求分析时，使用本技能：

用户：分析一下这个Excel文件
→ 触发非毒·分析魄
→ 输出洞察报告

用户：预测下个月的销售趋势
→ 触发非毒·分析魄
→ 输出预测结果

输出格式

洞察报告

## 洞察报告

### 核心发现
[1-3个最关键的洞察]

### 数据概览
- 样本量: XXX
- 时间范围: XXX
- 关键指标: XXX

### 模式识别
[发现的模式或规律]

### 趋势分析
[短期/中期/长期趋势]

### 风险预警
- [风险1]
- [风险2]

### 行动建议
1. [建议1]
2. [建议2]

分析框架

描述性分析

均值、中位数、众数
分布形态
极值与范围

诊断性分析

归因分析
差异分析
关联性分析

预测性分析

时序预测
回归分析
情景模拟

规范性分析

最优解建议
风险收益权衡
行动规划

核心算法

异常检测

异常度 = |当前值 - 期望值| / 标准差
异常阈值 = 3σ (99.7%置信)

趋势判断

上升趋势: 连续N个点斜率 > 0
下降趋势: 连续N个点斜率 \x3C 0
盘整阶段: |斜率| \x3C 阈值

调度者守则

数据说话 - 用数据支撑结论，避免主观臆断
追根溯源 - 不只看表象，要找根本原因
风险前置 - 提前预警潜在风险
可执行建议 - 洞察要转化为行动建议

适用场景

数据分析报告
趋势预测
异常检测
用户行为分析
业务诊断

依赖技能

silicon-soul（硅灵决基础）
task-planner（伏矢·路径魄）
deep-thinking（深度思考）

版本

v1.0.0 | 2026-04-12 | 硅灵宗·菩提

安全使用建议

This skill is an instruction/template for data analysis and is internally consistent, but it is high-level and depends on other skills named in the doc (silicon-soul, task-planner, deep-thinking) whose behavior and permissions are unknown. Before installing or invoking: (1) verify what those dependent skills do and whether they request credentials or external network access, (2) be explicit about how the agent should obtain user data (only from attachments the user provides), and (3) avoid submitting sensitive data (passwords, full PII, or secrets) for analysis unless you trust the execution environment and any downstream skills. If you need stricter guarantees, ask the skill author to specify concrete data-handling rules and explicit dependency manifests.

功能分析

Type: OpenClaw Skill Name: fei-du-prophet Version: 1.0.0 The skill bundle 'fei-du-prophet' (Data Prophet) is a purely instructional prompt-based skill for data analysis and trend prediction. It contains no executable code, network requests, or sensitive data access. The SKILL.md file defines a structured analysis framework and persona without any signs of prompt injection or malicious intent.

能力评估

✓ Purpose & Capability

Name/description (data insight, pattern recognition, forecasting) align with the SKILL.md content. The skill requests no binaries, env vars, or installs, which is proportionate for a pure instruction/template skill.

ℹ Instruction Scope

The SKILL.md provides analysis frameworks, output formats, and example triggers but no concrete commands or data-handling rules. It assumes the agent will process user-provided data (e.g., Excel files) but does not instruct the agent to access system paths, environment variables, or external endpoints. The instructions are high-level and could give an agent broad discretion in how to obtain or enrich data unless other constraints exist.

✓ Install Mechanism

No install spec and no code files — lowest-risk delivery model. Nothing is written to disk and there are no download URLs or package installs to evaluate.

✓ Credentials

No required environment variables, credentials, or config paths are declared. That is consistent with the skill's stated purpose as an instruction-only analytic template.

✓ Persistence & Privilege

always is false and defaults allow autonomous invocation by the agent (platform default). The skill does not request persistent or elevated platform privileges. Note: autonomous invocation is normal; no additional persistence requested.

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 fei-du-prophet
安装完成后，直接呼叫该 Skill 的名称或使用 /fei-du-prophet 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 Data Prophet (非毒·分析魄): - Enables advanced data insight, pattern recognition, and trend forecasting. - Provides a clear output template for insight reports, including key findings, overview, pattern recognition, trend analysis, risk warnings, and actionable suggestions. - Supports descriptive, diagnostic, predictive, and prescriptive analytics frameworks. - Integrates core algorithms for anomaly detection and trend judgment. - Designed for flexible use in tasks like data analysis, anomaly detection, forecasting, and business diagnostics.

元数据

Slug fei-du-prophet

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题