<!--
name: 'Skill: deep-research'
description: Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. - When the user wants a deep, multi-source,
sdkPackage: '@anthropic-ai/claude-agent-sdk@0.3.168'
claudeCodeVersion: '2.1.168'
skill: "deep-research"
-->
# Skill: deep-research

## Metadata

- Source: SDK-shipped/runtime skill listing

## Description

Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. - When the user wants a deep, multi-source, fact-checked research report on any topic. BEFORE invoking, check if the question is specific enough to research directly — if underspecified (e.g., "what car to buy" without budget/use-case/region), ask 2-3 clarifying questions to narrow scope. Then pass the refined question as args, weaving the answers in.

## Token Impact

<!-- TOKEN_COUNT_START -->
- Description estimated tokens: **155**
- Measurement: description serialized independently as text against the common baseline
- Additivity: independent, non-additive estimate
<!-- TOKEN_COUNT_END -->
