Customer Research

anthropics/knowledge-work-pluginsOfficial

This handles the messy reality of customer support research by searching across your actual connected tools (docs, CRM, Slack, email, support tickets) and synthesizing what it finds with clear source attribution and confidence scoring. It's designed for when a customer asks something you need to look up, or when you're investigating whether a bug has been reported before. The workflow is thorough, maybe even aggressive: it won't stop at the first result, it cross-references across source tiers, and it explicitly flags gaps and contradictions. One honest take: the confidence scoring and "what we don't know" sections are the most useful parts, because they keep you from confidently telling a customer something that's based on a single Slack message from six months ago.

skills.sh installs: 3.2K
GitHub stars: 35.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add anthropics/knowledge-work-plugins --skill customer-research --agent claude-code

Installs into .claude/skills of the current project.

Files

/customer-research

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Multi-source research on a customer question, product topic, or account-related inquiry. Synthesizes findings from all available sources with clear attribution and confidence scoring.

Usage

/customer-research <question or topic>

Workflow

1. Parse the Research Request

Identify what type of research is needed:

Customer question: Something a customer has asked that needs an answer (e.g., "Does our product support SSO with Okta?")
Issue investigation: Background on a reported problem (e.g., "Has this bug been reported before? What's the known workaround?")
Account context: History with a specific customer (e.g., "What did we tell Acme Corp last time they asked about this?")
Topic research: General topic relevant to support work (e.g., "Best practices for webhook retry logic")

SKILL.md on GitHub