Skip to main content
skill CX Codex

deep-research · imbad0202 — Claude Code skill: systematic literature reviews

deep-research runs a team of 13 agents through academic research on any topic, from framing the question to an APA 7.0 report.

no license 8,200 installs ★ 58,001 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Imbad0202/academic-research-skills --skill deep-research -a claude-code
Open on GitHub

What deep-research does

The skill works in six stages: scoping the question and methodology, a systematic literature search with source checks, cross-source synthesis with a bias check, an APA 7.0 report, editorial and ethics review, and a final revision. Thirteen agents share the work.

There are eight modes. You can ask for a short brief instead of a full report, have a paper critiqued, check a claim against sources, build a literature review, or run a systematic review that adds a meta-analysis if you want one. A Socratic mode keeps asking questions until your topic is clear. One agent plays devil's advocate against the conclusions.

Hand it a draft and reviewer comments without naming a skill, and it asks what you want done before choosing a workflow. Begin the message with [direct-mode] and name the skill or agent to skip those questions.

What it helps with

  • build a literature review with verified sources
  • check a disputed claim against several sources
  • run a PRISMA-style systematic review
  • narrow a vague topic into a research question
  • get an APA 7.0 report with a risk-of-bias assessment

Example prompts for the agent

  • Use deep-research to study how AI affects quality control in universities
  • Fact-check this claim with sources: private universities lose students because birth rates are falling
  • Guide my research: I care about university quality assurance but have no firm question yet

How to install deep-research

1Skills CLI (Vercel)

npx skills add Imbad0202/academic-research-skills --skill deep-research -a claude-code

2Manually: put the files in place

~/.claude/skills/deep-research/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/deep-research/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about deep-research

How do I install deep-research in Claude Code?

Run npx skills add Imbad0202/academic-research-skills --skill deep-research -a claude-code. The skill file lands in ~/.claude/skills/deep-research/SKILL.md.

What does deep-research do?

It runs academic research on any topic with a team of 13 agents and produces an APA 7.0 report. It has eight modes, from a short brief to a systematic review.

Which tools support deep-research?

Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode. Each one has its own install command.

Similar skills

All skills for Science and research →

deep-research by other authors comes first.

deep-research affaan-m deep-research — a skill for Claude Code, Codex, Cursor and other agents that builds cited research reports from 15–30 sources using firecrawl and exa MCP tools. Triggers on phrases like "research", "deep dive", or "competitive analysis". CX Codex +1 7,000installs deep-research bytedance deep-research — a skill for Claude Code runs source-based research with current evidence and cross-checks. It fits questions that need more than one search. CX Codex +1 2,800installs deep-research 199-biotechnologies deep-research — a skill for Claude Code, Codex, Cursor and other agents that runs a multi-phase research pipeline and produces a fully cited report with per-claim verification. CX Codex +1 10,500installs deep-research ruvnet deep-research orchestrates multi-phase research using web search, codebase analysis, and memory storage. It generates structured findings with evidence ratings for complex topics. CX Codex +1 894installs deep-research HKUSTDial deep-research runs a topic investigation in the shape of a survey paper: pins the questions, searches from several angles, checks every reference and answers each question in the final report. Useful before you commit to a topic. CX Codex +1 687installs literature-review-planner travisjneuman literature-review-planner plans an academic literature review: picks the review type, builds the search string, screens sources and lays out a PRISMA flow. CX Codex +1 160installs academic-research-suite Imbad0202 academic-research-suite routes academic writing and analysis workflows from systematic literature reviews to peer review simulation. Triggers on slash commands and research prompts. CX Codex +1 2,200installs academic-deep-research kesslerio academic-deep-research — a skill that runs multi-step research: two search cycles per theme, an evidence hierarchy and APA 7 citations. Useful for literature reviews and competitive intelligence. CX Codex +1 562installs tooluniverse-literature-deep-research mims-harvard tooluniverse-literature-deep-research — a skill for deep literature search across PubMed, EuropePMC and bioRxiv, with citation networks and evidence grading. Useful when you need a review with citations. CX Codex +1 677installs deep-research-agent qodex-ai deep-research-agent is a Claude Code skill that automates data collection, source validation and report writing for market overviews, competitive analysis and academic literature reviews. CX Codex +1 290installs medical-imaging-review luwill The medical-imaging-review Claude Code skill guides reviews of AI in medical imaging. It supports protocol planning, study screening, qualitative synthesis, and manuscript drafting. CX Codex +1 695installs

From the same set5

Project sponsors

Companies that keep this analytics open