Research plugins

1,247 tagged Research, measured the same way as everything else here.

Browse within: cyanheads 29paper 29academic-writing 28cnki 28google 28google-scholar 28bun 26claude-plugin 23arxiv 20academic-research 17fact-checking 17knowledge-base 17chatgpt 16claude-skill 15

dsh-deepread

241

xiehuan123/dsh-deepread

Plugin Claude Code

Bundles 1 skill · 123 tokens together

Deep-reading assistant: five modes (quick, deep, knowledge-map, Feynman, full book) to extract core claims, argument structure, and key evidence from books and articles; exports Markdown, FreeMind/XMind mindmaps, and HTML reports.

44 +2 4d ago A tokens not measured original MIT

reviewer-2

242

xf686/Meet-Reviewer-2

Plugin Claude Code

Bundles 1 skill · 208 tokens together

Rigorous, fair peer review in two modes. (A) Red-team your OWN draft before you submit — a simulated panel (a generous champion, the brutal Reviewer 2, a novelty-hawk Area Chair) predicts the reviews and hands you a prioritized fix list. (B) Review SOMEONE ELSE'S paper when you're an assigned reviewer or helping your…

43 2mo ago A tokens not measured original MIT

newsmcp

243

pranciskus/newsmcp

Plugin Claude Code

Bundles 1 MCP server

Real-time world news for AI agents. AI-clustered events with topic and geographic filtering. Free, no API key.

42 6mo ago A tokens not measured original MIT

panews

244

panewslab/skills

Plugin Claude Code

Bundles 3 skills · 170 tokens together

PANews Agent Toolkit for crypto news discovery, Polymarket smart money leaderboard reading, PANews creator workflows, and PANews page-to-Markdown reading.

42 4mo ago A tokens not measured original MIT

costrict-plugins-repo/imbad0202-academic-research-skills-academic-research-skills

Plugin Claude Code

Bundles 4 skills, 16 commands, 37 agents, 2 hooks · 1,989 tokens together

Production-grade academic research pipeline for Claude Code: research → write → review → revise → finalize. 4 skills, 27 modes, 39-agent ensemble, v3.7.3 + v3.8 L3 claim-faithfulness gate, v3.9.0 cross-index triangulation, v3.10 triangulation policy layer, v3.11 deterministic citation verification gate (#182).

42 23d ago A tokens not measured

stress-test

247

gbasin/stress-test-skill

Plugin Claude Code

Bundles 1 skill · 32 tokens together

Adversarially stress-test technical plans by verifying claims against real docs, running POC code, and updating the plan before you build.

42 5mo ago A tokens not measured original MIT

indexandria

248

alicankiraz1/indexandria

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 32 tokens together

Crawl, index, and search web documentation directly inside Claude Code. Quick mode for focused lookups, deep mode for up to 100 pages with in-memory search.

42 6mo ago A tokens not measured original MIT

recursive-research

249

Anjos2/recursive-research

Plugin Claude Code

Bundles 1 skill · 71 tokens together

Recursive research up to PhD level across any domain (science, tech, business, arts, humanities). Source tiering, WDM + Munger inversion for autonomous decisions, disk checkpointing to survive context compaction.

42 +1 4mo ago A tokens not measured original MIT

vaaya

250

vaaya-ai/vaaya-mcp

Plugin Claude Code

Bundles 1 skill, 1 hook, 1 MCP server · 98 tokens together

Paid superpowers for any agent: media & video generation, product demo videos, web search & scraping, deep/market research, GTM & sales enrichment, code sandboxes, browser automation, email, memory — pay-per-call, no API keys.

42 +1 7d ago A tokens not measured original MIT

scg

251

bearlike/Assistant

Plugin Claude Code

Bundles 4 agents · 218 tokens together

Source Capability Graph — map connector reachability + route/traverse it for Agentic Search.

41 9d ago A tokens not measured original MIT

reality

254

lhl/realitycheck

Plugin Claude Code

Bundles 8 commands, 2 hooks · 83 tokens together

Framework for rigorous analysis of claims, sources, predictions, and argument chains.

41 2mo ago A tokens not measured original Apache-2.0

deep-research

255

oh-rid/deep-research

Plugin Claude Code

Bundles 1 agent · 300 tokens together

Deep research with 3-way LLM triangulation (Claude + Gemini via agy CLI + GPT-5 via codex CLI). Worktree-isolated, primary-source verified (mechanical URL check + passage match), defends against shared-corpus consensus hallucination.

41 3mo ago A tokens not measured original MIT

consulting

256

yoichiojima-2/consultant

Plugin Claude Code

Bundles 1 skill, 3 commands · 147 tokens together

50+ consulting frameworks used by McKinsey, BCG, Bain, and Accenture for structured problem-solving, strategic analysis, and business transformation.

41 +2 13d ago A tokens not measured original MIT

competitor-intel

258

hoangsonww/AI-News-Briefing

Plugin Claude Code

Bundles 1 skill · 29 tokens together

Given a company/product, finds its top competitors, compares their latest feature releases, pricing changes, and customer sentiment.

40 17d ago A tokens not measured original MIT

forge-knowledge

260

pan94u/forge

Plugin Claude Code

Bundles 3 skills, 3 commands · 54 tokens together

Enterprise knowledge access plugin for Forge. Provides skills and commands for searching internal wikis, runbooks, ADRs, and domain models via the forge-knowledge MCP server.

40 1mo ago A tokens not measured

qi marketplace

262

itsmostafa/qi

Plugin Claude Code

Plugin marketplace listing 1 plugin: qi.

39 23d ago A tokens not measured original MIT

advocacia-aberta

263

emidio-trancoso/advocacia-aberta

Plugin Claude Code

Bundles 10 skills · 685 tokens together

Método jurídico aberto e executável por agentes de IA: base curada de STF/STJ, legislação, súmulas, temas e teses; 10 protocolos (organizar caso, buscar fontes, redigir e revisar peça, transcrever, diagnosticar, diagramar) e motores locais. Fontes verificáveis, casos privados. Direito brasileiro, PT-BR.

39 9d ago A tokens not measured original MIT

calibre-mcp

264

sandraschi/calibremcp

Plugin Claude Code

Bundles 6 skills · 0 tokens together

Calibre e-book library MCP server with 21 portmanteau tools for search, management, export, and RAG.

39 5d ago A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: