research

Document public information about people or organizations into a PostgreSQL knowledge graph.

Updated Apr 3, 2026
One-click install
npx skills add https://github.com/i-richardwang/Dossier --skill research-i-richardwang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/i-richardwang/Dossier/tree/main/.claude/skills/research
Command: npx skills add https://github.com/i-richardwang/Dossier --skill research-i-richardwang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

对指定人物或组织进行深度研究,把发现写入 PostgreSQL 知识图谱

Core Features & Use Cases

  • 深度信息收集与整理:从公开来源提取与实体相关的事实、时间线和关系,并写入知识图谱。
  • 结构化写入:通过 add-rel、add-employment、add-observation 将证据与结论以可查询的记录形式存储。
  • 项目驱动研究:以 docs/research/projects/<项目名>/context.md 的背景信息为指导,持续扩展实体画像。

Quick Start

Provide the project name and target entity to begin a deep research session.

Frequently Asked Questions about research

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

FAQPage Schema
How do I research a person or organization and store findings in a knowledge graph?

To research a person or organization in a knowledge graph, you identify publicly available information, document facts and relationships, and write them into a PostgreSQL graph using structured entries like add-rel and add-observation with source evidence.

What is the best way to structure evidence and observations when collecting data on public entities?

The best way to structure evidence for public entity data collection is to record the source, excerpt, confidence level, and current status alongside each observation, relationship, or employment detail added to the knowledge graph.

How do I set up project context before starting a deep research session on an entity?

To set up project context for entity research, you create a context.md file under docs/research/projects/<project>/ to guide the research session, continuously expanding the entity profile based on that background information.

Can I use this approach to document employment history and relationships for a knowledge graph?

Yes, you can document employment history and relationships using the add-employment and add-rel commands, which store structured, queryable records with required evidence directly in the PostgreSQL knowledge graph.

What types of structured data can I enter when enriching a knowledge graph with public source information?

When enriching a knowledge graph with public source information, you can enter structured data via add-rel for relationships, add-employment for job history, and add-observation for facts, each requiring a source, excerpt, confidence, and status.