Deep Research plugin: what it installs and how to add it
Runs auditable, multi-source investigations with hypothesis testing, source triangulation and adversarial review for high-stakes questions.
From the Marketplace: claude-code-skills marketplace
Install
> /plugin marketplace add alirezarezvani/claude-skills> /plugin install deep-research@claude-code-skillsRun both lines inside Claude Code: the first adds the marketplace, the second installs the plugin.
What is inside
- 1skill
- 1command
- 1agent
About this plugin
This plugin guides research through a structured nine-phase process: reframing a question into falsifiable hypotheses, planning searches, discovering available research capabilities, running parallel investigations, scoring and triangulating sources, synthesising findings, challenging the result, verifying citations and defining refresh targets. Each source is saved separately with verbatim quotes, and claims without sufficient evidence are marked accordingly.
Use it for strategy, comparing options, validating hypotheses or mapping a field when an incorrect answer carries significant cost. It produces a reusable research folder rather than a one-off chat response.
What's inside
- 1 skill:
deep-research - 1 slash command:
cs-deep-research - 1 agent:
cs-deep-research
More from claude-code-skills
- A11y AuditScans and fixes WCAG 2.2 accessibility issues in React, Vue, Angular, Svelte, Next.js and HTML projects.Marketplace: claude-code-skillsGitHub stars: 27.2k
- AEOAudits and optimises content for citation by AI answer engines including ChatGPT, Perplexity, Claude, Gemini and Mistral.Marketplace: claude-code-skillsGitHub stars: 27.2k
- Agent HarnessRuns bounded agentic loops that turn goals into verified tasks and close only when checks pass or are explicitly waived.Marketplace: claude-code-skillsGitHub stars: 27.2k
- Agent Launcher SkillsBuilds, launches, grades, and schedules Claude Managed Agents in your Anthropic account through bounded workflows and loops.Marketplace: claude-code-skillsGitHub stars: 27.2k
- Agent MemoryAdds tiered memory for Claude Code, recalling relevant project context while requiring repeated evidence and human approval before promotion.Marketplace: claude-code-skillsGitHub stars: 27.2k
- AgentHubRuns parallel Claude Code agents in isolated worktrees, evaluates their competing solutions and merges a selected winner.Marketplace: claude-code-skillsGitHub stars: 27.2k
Related plugins
- Last 30 DaysSearches recent online discussions and sources to produce a structured 30-day digest on any topic.Marketplace: claude-communityGitHub stars: 63.4k
- Math OlympiadOfficialSolves IMO, Putnam and USAMO-style competition maths problems, then checks proofs in a fresh context before presenting them.Marketplace: claude-plugins-officialGitHub stars: 37.3k
- Math ProofOfficialSolves hard mathematics problems through staged reasoning or multi-agent proof checks, ending with a self-contained proof file.Marketplace: claude-plugins-officialGitHub stars: 37.3k
- Deep Learning BookAdds a navigable study companion for Goodfellow's Deep Learning book, with chapter guidance and practical diagnostic tools.Marketplace: claude-code-skillsGitHub stars: 27.2k
Skills, not plugins
Prefer a single skill for research work? 41 skills in the same category, each installed on its own.