skills.rest
bettercallfan
bettercallfanCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

risk-evidence-pack

Generate structured risk evidence packages for phone numbers from network graph data.

Updated Jun 2, 2026
Search Tags:#data analysis#risk assessment#evidence package#graph processing#phone network
One-click install
npx skills add https://github.com/bettercallfan/deerflow --skill risk-evidence-pack
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: risk-evidence-pack
Source: https://github.com/bettercallfan/deerflow/tree/main/skills/custom/phone-network-analysis/risk-evidence-pack
Command: npx skills add https://github.com/bettercallfan/deerflow --skill risk-evidence-pack

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill provides a structured risk evidence package for a single phone number, consolidating data to inform about potential risks associated with that number.

Core Features & Use Cases

  • Risk Evidence Pack Creation: Creates a structured risk evidence package containing information on a number's image, risk conclusion, communication evidence, shared device evidence, and collaborative partner evidence.
  • Application Scenarios: Appropriate for addressing queries related to the "reasons for high risk", "collation of evidence packages", and "creation of deliverables". Not suited for global top-N discoveries or group gang identification.

Quick Start

To create a risk evidence package for a specific phone number, run:

risk-evidence-pack --phone-id "<PHONE_ID>"

Frequently Asked Questions about risk-evidence-pack

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a risk evidence package for a specific phone number?▼

You generate a risk evidence package for a phone number by running a Python script that queries predefined phone network graphs. This produces a structured report containing the number's image, risk conclusion, and specific communication evidence.

What is included in a structured phone network risk evidence pack?▼

A phone network risk evidence pack includes the number's image, risk conclusion, communication evidence, shared device evidence, and collaborative partner evidence. It consolidates graph data to inform decisions about potential risks associated with that specific number.

Can I use this risk assessment approach to identify high-risk groups in a phone network?▼

No, this risk assessment approach is not suited for global top-N discoveries or group gang identification. It is specifically designed to generate structured evidence packages for individual phone numbers rather than analyzing network-wide risk clusters.

How does graph processing help collate evidence for high-risk phone numbers?▼

Graph processing queries a predefined dataset of phone network connections to extract specific relationship data. This mechanism isolates communication, shared device, and collaborative partner evidence to explain why an individual number is flagged as high risk.

Do I need Python scripts to analyze phone network graph data for risk assessment?▼

Yes, Python scripts are required to process and query the graph data for risk assessment. The scripts analyze the phone network dataset and generate the structured reporting deliverables needed for the evidence package.

Related Skills

Explore More Data & Analytics Skills→
FrancisVargaFrancisVarga

Graph Algorithms

Execute PageRank, Louvain, BFS, DFS, and shortest path algorithms on in-memory property graphs.

Community
Advanced
tradermontytradermonty
2.6k

portfolio-manager

Fetch live brokerage holdings via Alpaca MCP Server and generate Markdown portfolio reports.

Community
Advanced
bettercallfanbettercallfan

gang-cluster-analysis

Identify potential gangs or clusters in phone networks using shared devices and common contacts.

Community
Advanced
bettercallfanbettercallfan

topn-high-risk-discovery

Rank high-risk phone numbers using graph analysis and risk scoring.

Community
Advanced