Research skills

17,460 tagged Research, measured the same way as everything else here.

Browse within: agent 208LLM 183agents 129bioinformatics 102claudecode 101agentic-ai 90ai-scientists 87reasoning-agent 87reasoning-language-models 87tool-use 87academic-research 84data-analysis 80claude-code-skills 78skills 78

parallel-deep-research

1489

parallel-web/parallel-cursor-plugin

Skill Claude Code

ONLY use when user explicitly says 'deep research', 'exhaustive', 'comprehensive report', or 'thorough investigation'. Slower and more expensive than parallel-web-search. For normal research/lookup requests, use parallel-web-search instead. Supports multi-turn: pass --previous-interaction-id from a prior research or…

not rated 4 +1 4mo ago A 76 tokens original MIT

web-search

1490

dshein-alt/crawly-mcp

Skill Claude CodeCodex

Use when a context-limited LLM must search, fetch, and synthesize content from multiple pages with crawly-mcp, especially when bounded pagesearch(...), small fetch(contentformat="text") batches, and concise prose synthesis keep search work within a small context window.

not rated 4 4mo ago A 60 tokens original MIT

scoville-brainstorm

1492

benjaminstelzer/scoville-brainstorm

Skill Codex

Use only to explore materially different solution mechanisms before a choice, with isolated generation, bounded prior-art comparison, calibrated originality language, and a decision-ready shortlist. Activate for explicit Scoville Brainstorm, or when a task explicitly requests several materially different solution…

not rated 4 changed yesterday A 125 tokens original MIT

jusbrasil-mcp

1493

mcp-dir/jusbrasil-mcp

Skill Claude CodeCodex

Pesquisa jurídica brasileira via Legal MCP (alternativa ao Jusbrasil): raio-X de processos por nome/CPF/CNPJ/número, publicações no DJEN, sanções e jurisprudência. Use quando o usuário perguntar sobre processos, intimações, andamento, OAB ou consulta jurídica em geral.

not rated 4 +1 14d ago A 67 tokens original MIT

web-search-plus

1494

robbyczgw-cla/web-search-plus-mcp

Skill Claude CodeCodex

Use the Web Search Plus MCP tools (websearch, webextract) for source-backed web research: current events, prices, release notes, docs and API references, arXiv papers, CVEs, local and shopping queries, and reading a specific page. Use when the user mentions "web search plus", "websearchplus", "wsp", asks which sources…

not rated 4 changed 3d ago A 132 tokens original MIT

chixi-tension

1495

alephchixi/chixi-skills

Skill Claude CodeCodex

Anti-sycophancy and directional friction engine. Use this skill after the user or agent has developed two substantial research directions, arguments, or positions and needs to understand the field of forces between them WITHOUT declaring a winner. This skill directly addresses the LLM sycophancy problem identified by…

not rated 3 +1 4mo ago A 176 tokens

agentforge-compare

1496

yedanyagamiai-cmd/openclaw-mcp-servers

Skill Claude CodeCodex

AI coding tool comparison MCP server -- compare Claude Code vs Cursor vs Windsurf vs Devin vs Copilot side-by-side with feature matrices, pricing breakdowns, and AI-powered recommendations. Use when: (1) user asks 'compare Cursor and Windsurf' or 'which AI coding tool is best', (2) user says 'tell me about Devin' or…

not rated 3 5mo ago A 168 tokens original MIT

hotin

1497

abe238/hotinai

Skill Claude CodeCodex

Use when asked what is new, trending, hot, or worth using in AI right now - which repos, models, papers or launches matter this week, or whether a specific project is gaining traction. Answers from a ranked board with evidence instead of from training data or search-engine marketing.

not rated 3 today A 60 tokens original Apache-2.0

outscraper/outscraper-mcp-server

Skill Claude CodeCodex

Run a lead research and enrichment pipeline across several Outscraper MCP tools. Use when an agent needs to discover a company or business, enrich it with company metadata, find emails or contacts, and optionally extract structured messaging from a website for outbound sales, GTM research, or account planning.

not rated 3 4mo ago A 64 tokens original MIT

wallabag

1499

rusty4444/wallabag-mcp

Skill Claude CodeCodex

Use the wallabag MCP server for read-it-later article capture, reading queue management, tags, and annotations.

not rated 3 3mo ago A 26 tokens original MIT

mind-clone

1500

mrgnfndr-dr/mind-clone

Skill Claude CodeCodex

Build and talk to an AI "mind clone" of a real public author — a model of how they think, built from their public content, that reasons in the author's own frameworks and cites them with deep-links to the exact source moment. Use when the user wants to clone someone's mind/thinking from their public content (articles…

not rated 3 1mo ago A 191 tokens original MIT

create-scraper

1501

chrisdothtml/ai-job-finder

Skill Claude Code needs its repo

Given a careers page URL, uses Playwright browser tools to explore the page, identify reliable scraping patterns (preferring hidden JSON APIs over DOM scraping), then writes a TypeScript Scraper subclass for that company.

not rated 3 1mo ago A 46 tokens original MIT

AI-Kakashi/enterprise-encyclopedia

Skill Claude CodeCodex

A tool for looking up Chinese company registration and business-risk information, such as owners, executives, shareholders, business scope, registered capital, and legal disputes.

not rated 3 6mo ago A 114 tokens

archaeologist

1503

Lum1104/archaeologist

Skill Claude CodeCodex

Use when changing unusual or defensive code, mature APIs, dependencies, or architecture, or estimating a migration where Git history may reveal hidden constraints.

not rated 3 1mo ago A 32 tokens original MIT

primr

1504

blisspixel/primr

Skill Claude Code

Route and run Primr company research from an agent host. Use for a bare Primr company-and-URL request, named Primr report, full strategic dossier, Strategic Overview, or strategy module. Default to Primr Zero unless the user explicitly requests paid, metered, provider-backed, or premium execution; use an inline primr…

not rated 3 3d ago A 95 tokens original Apache-2.0

Systematic Review

1505

SkillMedev/academic-researcher

Skill Claude CodeCodex

Runs a PRISMA-compliant systematic review from PICO question and pre-registered protocol through search strings, two-stage screening, risk-of-bias appraisal, and GRADE-rated synthesis. Use when someone asks "run a systematic review", "build my search strategy and inclusion criteria", "screen these studies against a…

not rated 3 2mo ago A 123 tokens original MIT

SearchCans/searchcans-skills-zh

Skill Codex

A Chinese-language research workflow that uses web search and page-reading services to collect current, traceable evidence for a specific question.

not rated 3 19d ago A 101 tokens original Apache-2.0

academic-review

1507

inna-gazieva/academic-review-skill

Skill Claude CodeCodex

A review process for evaluating a scientific article for publication. It applies when an uploaded PDF or DOCX article needs a peer review or publication assessment.

not rated 3 changed 2d ago A 161 tokens CC-BY-4.0

journal-abbrev

1508

Agents365-ai/journal-abbrev

Skill Claude Code

Uma ferramenta para consultar e padronizar abreviações de nomes de revistas e periódicos científicos, incluindo os formatos ISO 4 e MEDLINE. Também trabalha com nomes de periódicos em arquivos BibTeX, usados para referências bibliográficas.

not rated 3 2mo ago A 121 tokens

dispatch-exploration

1509

ethanaubuchon/dossier-tradecraft

Skill Claude CodeCodex

Use during /research (or any recipe) to send 1-3 research queries in parallel — vault or web targets — and aggregate compressed findings. Routes each query to vault-researcher or web-researcher based on target. Hosts the cross-verify consent gate so any inline-research caller (/research, /design, /decompose) inherits…

not rated 3 yesterday A 85 tokens original MIT

zaker-news-search

1511

ZAKER-coder/skills

Skill Claude CodeCodex

A keyword news search tool for ZAKER, a Chinese news and information platform. It can filter results to a period within the past 30 days.

not rated 3 5mo ago A 69 tokens original MIT

target-prioritization

1512

Agents365-ai/target-prioritization

Skill Claude CodeCodex

Prioritize drug targets from a ranked gene list (e.g., scRNA-seq DE output) by orchestrating parallel API queries against UniProt, OpenTargets (with integrated DepMap CRISPR essentiality + gnomAD constraint), PubMed, the Human Protein Atlas (HPA), and ChEMBL tool compounds, then re-ranking by a composite score…

not rated 3 1mo ago A 227 tokens

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: