Deep Research Skill - Setup Guide¶

Source: 199-biotechnologies/claude-deep-research-skill GitHub: 199-biotechnologies/claude-deep-research-skill (989 stars) Skills: 1 skill · 9.4K installs Category: Research First Seen: Jan 21, 2026 · catalogued August 15, 2026 evening sweep Quality Tier: 🟡 Trusted (Gen Agent Trust Hub Pass, Socket Pass, Snyk Warn)

A single-skill research engine: citation-tracked reports through a structured pipeline with evidence persistence, source identity management, claim-level verification, and progressive context management. The decision tree routes simple lookups to WebSearch and only complex analyses into the full pipeline - the right triage design for an autonomous agent.

Installation¶

npx skills add https://github.com/199-biotechnologies/claude-deep-research-skill --skill deep-research

Prerequisites¶

Requirement	Details
Node.js + npx	For the skill installer
Web search access	For source gathering
Markdown-friendly output target	Reports are markdown-first

What It Provides¶

Skill	Installs	Purpose
deep-research	9.4K	Citation-tracked research reports with evidence persistence

Quick Start¶

Install: npx skills add https://github.com/199-biotechnologies/claude-deep-research-skill --skill deep-research
Ask: "research the MCP server landscape and produce a citation-tracked report"
Review the Introduction and Methodology sections - the skill surfaces high-materiality assumptions there explicitly

CorpusIQ Use Cases¶

Use Case	How
Market research sweeps	Citation-tracked output for competitive and market reports
Funding research	Structured, verifiable reports for investor diligence
Docs content	Evidence-backed drafts for the knowledge base
Verification discipline	Claim-level verification as a pattern for our own research quality

Integration with CorpusIQ¶

CorpusIQ is the connector layer that lets AI assistants read the systems a business already runs on - accounting, payments, CRM, email, files and analytics - and answer with the source named. It is read-only by design: it retrieves data and never writes to, or acts in, a connected system, which is what makes it safe to point at live accounts.

This page is part of the CorpusIQ directory, the reference we maintain for the MCP server and agent-skill ecosystem. Run alongside CorpusIQ, a third-party server like this one can be combined with a company's own business data in a single answer.

See what CorpusIQ connects

Limitations / Verification¶

Security audits: Gen Agent Trust Hub Pass, Socket Pass, Snyk Warn (named in audit; manual review recommended)
Single-skill package - the pipeline is opinionated and may not fit ad-hoc research
Verification command: npx skills add https://github.com/199-biotechnologies/claude-deep-research-skill --skill deep-research

Powered by CorpusIQ