Research

28,063 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

lobster-research

985

hegeo/Lobster-Research

Skill Claude CodeCodex

A research-report workflow that produces market and topic reports across areas such as stocks, industries, technology, medicine, politics, and culture. It reads JSON input, performs additional searches, and fills a specified report-input file.

not rated 47 +6 5mo ago A 662 tokens

paper-explainer

987

PompeiiChan/skills-ExplainPaper

Skill Claude CodeCodex

A tool for explaining artificial-intelligence and computer-science research papers to readers without an engineering background. It turns technical ideas into a plain-language report with simple visual explanations and a single HTML file.

not rated 47 4mo ago A 90 tokens original MIT

lookout

988

realactivity/tula

Skill Claude CodeCodex

Personalized ambient health awareness. Pulls environmental, public-health, and place-based data for the user's location and triages it against their longitudinal record, surfacing only what matters. USE FOR: 'lookout for me' briefings, ambient/air/UV/weather/pressure checks, place-based resource queries, travel-mode…

not rated 47 20d ago A 106 tokens original Apache-2.0

zmustafa/AzureSupportAgent

Skill Claude CodeCodex

Build an evidence-backed identity dossier covering account state, roles, MFA, Conditional Access, and permitted activity.

not rated 47 2d ago A SkillSpector: pass 26 tokens original MIT

trip-master-plan

990

padak/claude-code-kit

Plugin Claude Code

Bundles 1 skill, 1 agent · 118 tokens together

Plan a trip end-to-end and deliver a versioned HTML MASTER itinerary: assessment interview, date-verified attractions and local events, route alternatives, real-geodata SVG maps whose routes follow actual roads, day cards with drive times, Wikimedia photos with credits, a weather widget, and copy-to-clipboard research.

not rated 47 +1 9d ago A tokens not measured

reviewer-2

991

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…

not rated 47 4mo ago A tokens not measured original MIT

academic-mcp2

992

LinXueyuanStdio/academic-mcp

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

MCP server "academic-mcp2" as configured in LinXueyuanStdio/academic-mcp. Runs academic_mcp with python. Needs 10 environment variables to run.

not rated 47 +1 2mo ago A tokens not measured original MIT

geo-review-writing

993

Xiangyu-Ge/sci-writing-geors

Skill Claude CodeCodex

A writing and analysis guide for review papers in geography, remote sensing, ecology, and soil science. It covers ordinary literature reviews, systematic reviews, meta-analyses, and studies that map research trends.

not rated 47 +21 3d ago A 216 tokens

explore

994

lsnackerman/raw-clauding-skills

Skill Claude Code

Build topic reserves by searching your entire system, or run discovery mode (no topic) to find what connects across territories. Use when consolidating scattered knowledge on a topic, before writing/sharing, before a sprint, or when curiosity has no specific target.

not rated 46 +1 changed 12d ago A 54 tokens

autoresearch

995

supratikpm/gemini-autoresearch

Skill Claude CodeCodex

Autonomous goal-directed iteration for Gemini CLI. Inspired by Karpathy's autoresearch. Use when asked to run autoresearch, iterate overnight, or autonomously improve any measurable goal. Loops forever: modify → verify → keep/revert → log → repeat. Never stops until interrupted. Gemini-native: uses Google Search…

not rated 46 7mo ago A 81 tokens

sota-scan

996

MerlijnW70/sota-scan

Skill Claude CodeCodex

Benchmark the current repo against the state of the art by scanning real online repos (GitHub and the wider web) in the same domain, then produce a cited capability matrix and a ranked, repo-grounded gap list. Use when the user asks "is our X top-tier", "what are we missing", "compare us to the best", "study online…

not rated 46 4mo ago A 89 tokens original MIT

mcp-web-tools

997

pietz/mcp-web-tools

MCP server Claude CodeCodexCursor +2

A powerful MCP server to equip LLMs with web access, search, and content extraction capabilities. Runs locally from the mcp-web-tools Python package.

not rated 46 11mo ago A tokens not measured

check

998

lhl/realitycheck

Skill Claude CodeCodex needs its repo

Full Reality Check analysis - fetch source, perform 3-stage analysis, extract claims, register to database, and validate. The flagship command for rigorous source analysis.

not rated 46 4mo ago A 34 tokens original Apache-2.0

context-hub

999

andrewyng/context-hub-skill

Skill Claude CodeCodex

Use this skill when the user asks for the latest docs, latest model, latest setup guidance, latest API behavior, or explicitly mentions chub or Context Hub. Use it by default whenever current documentation or current workflow guidance matters more than model memory. Ensure chub is available, run chub help, then use…

not rated 46 6mo ago A 83 tokens original MIT

notebooklm-mcp-server

1000

moodRobotics/notebooklm-mcp-server

MCP server Claude CodeCodexCursor +2

Node.js Model Context Protocol server for Google NotebookLM. Runs locally from the notebooklm-mcp-server npm package.

not rated 46 +1 2mo ago A tokens not measured original MIT

paper-workflow

1001

brycewang-stanford/Paper-WorkFlow

Skill Claude Code

A staged workflow for producing an evidence-based economics or social-science research paper, from choosing a topic through submission. It coordinates existing tools and analysis options, including Python, Stata, and R.

not rated 46 +1 changed 14d ago A 101 tokens original MIT

lit-review-agent-tools

1002

brycewang-stanford/lit-review-agent-tools

Plugin Claude Code

Bundles 1 skill · 288 tokens together

Recommend AND run open-source AI literature-review tools — a curated 70+ catalog plus a launcher that installs & runs MinerU, PaperQA2, ASReview, GPT Researcher, STORM, and arXiv/Zotero MCP servers.

not rated 46 +5 4d ago A tokens not measured original CC0-1.0

sole-search

1003

djfksjd/sole-search

Plugin Claude Code

Bundles 1 skill · 0 tokens together

A Korea-only research tool for finding support programs for small businesses, including grants, vouchers, government-backed loans, guarantees, training, and consulting. It searches Korean government sources and checks eligibility against a shop profile.

not rated 45 3mo ago A tokens not measured original MIT

webscraping-ai

1004

webscraping-ai/webscraping-ai-mcp-server

MCP server Claude CodeCodexCursor +2

Web scraping tools with Chromium JS rendering, rotating proxies, and AI question answering. Runs locally from the webscraping-ai-mcp npm package. Needs 4 environment variables to run.

not rated 45 11d ago A tokens not measured

frostant/awesome-claude-skills

Skill Claude CodeCodex

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.

not rated 45 9mo ago A 49 tokens

skills

1006

Youhai020616/stealth-cli

Skill Claude CodeCodex needs its repo

Anti-detection browser CLI powered by Camoufox. Browse the web, search, extract data, take screenshots, and crawl pages — all with C++ level fingerprint spoofing that bypasses Cloudflare, Google, and most bot detection systems.

not rated 45 1mo ago B 0 tokens original MIT

panews

1008

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.

not rated 45 changed 27d 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: