What does this skill do?

The Deep Research skill turns an agent into a research engine that produces comprehensive, citation-supported reports with quality validation.

It runs in four depth modes from quick exploration to maximum-thoroughness, and moves through an eight-phase pipeline: scope, plan, retrieve, triangulate, outline, synthesize, critique, and package.

It aggregates multiple search providers, requires multiple sources per major claim, scores source credibility, and red-teams findings with multiple critic personas before packaging Markdown, HTML, and PDF outputs.

  • Runs quick, standard, deep, or ultradeep research modes

  • Retrieves in parallel and triangulates across sources

  • Scores source credibility and validates citations

  • Red-teams findings before producing the final report

How it works

1

Scope and plan

The agent clarifies research boundaries and structures the investigation, retrieving the current date to avoid stale assumptions.

2

Retrieve and triangulate

It runs parallel searches plus focused sub-agents across multiple providers and cross-references findings.

3

Synthesize and critique

It composes findings from the evidence, then red-teams them with skeptical, adversarial, and implementation personas, looping back if gaps remain.

4

Validate and package

It validates citations, scores source credibility, and packages the report as Markdown, HTML, and PDF with a full bibliography.

Best use cases for this skill

  • Topic exploration: Run a quick scan to map a new topic.

  • Decision research: Produce a deep, citation-backed report for a critical decision.

  • Comparative analysis: Compare options with triangulated, validated sources.

  • Rigorous reports: Generate a validated report with source credibility scoring.

Frequently asked questions

What does the Deep Research skill do?

It produces citation-backed research reports with source credibility scoring, multi-provider search, red-team critique, and automated validation.

When should an agent use it?

Use it for topic exploration, standard research inquiries, or complex and critical questions that need rigor — across quick, standard, deep, and ultradeep modes.

How does it ensure quality?

It requires multiple sources per major claim, runs structural validation and DOI/URL checks, validates citations in automated loops, and red-teams findings with multiple critic personas.

What formats does it output?

Reports are generated as Markdown, HTML, and PDF, with an executive summary and a complete bibliography with URLs.

Use from source

Ask your Buda agent to install this community skill.

Copy this prompt into your own Buda agent. It includes the source repository and install command so the agent can complete the setup in natural language.

Prompt to send to your Buda agent
Please install the "Deep Research Skill" skill into this Buda agent.

Source repository: https://github.com/199-biotechnologies/claude-deep-research-skill
Install command: npx skills add 199-biotechnologies/claude-deep-research-skill -y -a universal

Please run the install command, verify the skill is available, and tell me any setup notes or follow-up steps from the source repository.
Explore marketplace

Install workflow

  1. 1Copy the prompt
  2. 2Send it to your Buda agent
  3. 3Done