Research

26,139 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.

PaperCash

529

Jesseovo/PaperCash

Plugin Claude Code

Bundles 1 skill · 37 tokens together

A plugin providing skills for the full research-paper workflow. Its description does not provide enough detail to identify the specific tasks covered.

not rated 130 +10 5mo ago A tokens not measured original MIT

nativ3ai/hermes-geopolitical-market-sim

Skill Codex

PrediHermes, also named geopolitical-market-sim, tracks geopolitical topics, selects relevant open Polymarket contracts near deadline, generates MiroFish seed packets from WorldOSINT data, runs or inspects MiroFish simulations, and resolves historical branches or injected actors from local artifacts. Use this when the…

not rated 129 2mo ago A 108 tokens AGPL-3.0

time-range-info

531

syy12335/Environment-Runtime

Skill Claude Code

A time-sensitive information lookup workflow that first fixes the meaning of relative dates such as “yesterday” or “next week,” then searches for supporting information.

not rated 129 +2 3mo ago A 35 tokens original MIT

co-researcher

533

poemswe/co-researcher

Plugin Claude Code

Bundles 15 skills, 3 commands, 1 hook · 396 tokens together

PhD-level research capabilities: literature review, multi-source investigation, critical analysis, hypothesis-driven exploration, quantitative/qualitative methods.

not rated 128 today A tokens not measured original MIT

research-refine

534

zjYao36/Auto-Research-Refine

Skill Claude CodeCodex

A workflow for turning a vague research direction into a concrete plan for solving a defined problem.

not rated 128 5mo ago A 101 tokens

notebooklm-studio

535

Toolsai/notebooklm-studio-Skill

Skill Claude CodeCodex

Operate Google NotebookLM from Codex for authorized source ingestion, notebook setup, source-grounded Q&A, and Studio artifacts such as Audio Overviews, Video Overviews, reports, mind maps, quizzes, flashcards, slide decks, infographics, and data tables.

not rated 128 3mo ago A 60 tokens original MIT

openzim-mcp

536

cameronrye/openzim-mcp

MCP server Claude CodeCodexCursor +2

OpenZIM MCP - ZIM MCP Server that enables AI models to access and search ZIM format knowledge bases offline. Runs locally from the openzim-mcp Python package. Needs 1 environment variable to run.

not rated 129 +1 today A tokens not measured original MIT

NVIDIA-AI-IOT/jetson-device-skills

Skill Claude CodeCodex

Use when Jetson codec, profile, chroma, bit-depth, dimension, engine-count, or operational support must be reconciled using live SDK APIs, authenticated NVIDIA samples, and NVIDIA documentation. Also use for Jetson questions about Netflix, Widevine, or other DRM-protected streaming-service playback to apply the…

not rated 131 +1 21d ago A 73 tokens

okx-sentiment-tracker

538

Dennis-bv/dex-trade-agent-kit

Skill Claude CodeCodex

Use this skill when the user asks about: 'any crypto news', 'latest news', 'market update', 'daily briefing', 'BTC news', 'ETH news', 'news on SOL', 'search SEC ETF', 'regulation news', 'Bitcoin halving', 'is BTC bullish or bearish', 'coin sentiment', 'sentiment trend', 'trending coins', 'top bullish coins', 'bearish…

not rated 127 5d ago A SkillSpector: pass 173 tokens original MIT

damionrashford/RivalSearchMCP

Plugin Claude Code

Bundles 1 skill · 151 tokens together

Agent skill and CLI helpers for using RivalSearchMCP research tools from Claude Code. Includes workflows, command references, and a standalone CLI for the hosted MCP server.

not rated 127 yesterday A tokens not measured original MIT

cnemri/google-genai-skills

Skill Claude CodeCodex

Search and retrieve Google's developer documentation using the Developer Knowledge API. Query documentation chunks, get full document content, or batch retrieve multiple documents. Covers ai.google.dev, developer.android.com, docs.cloud.google.com, firebase.google.com, and more.

not rated 126 7mo ago A 54 tokens original MIT

idea-generation

541

voidful/academic-skills

Skill Claude CodeCodex

A structured method for generating academic research ideas, checking them against existing literature, and narrowing them to one research proposal. It starts with many possible ideas and ends with a concise plan for one selected idea.

not rated 126 5mo ago A 119 tokens original MIT

context7

542

NoahDuongMaster/vibe-code-stack-for-ceos

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.

not rated 126 16d ago A tokens not measured copy · 78% MIT

mcp-jobs

543

mergedao/mcp-jobs

MCP server Claude CodeCodexCursor +2

A job search and crawling tool built with Model Context Protocol. Runs locally from the mcp-jobs npm package.

not rated 126 +1 2mo ago A tokens not measured

web-search

544

yixinforu/ops-mind-agent

Skill Claude CodeCodex

Use this skill when the user needs recent public internet information such as official announcements, release notes, news, vulnerability notices, or public documentation.

not rated 125 2mo ago A 31 tokens original Apache-2.0

apitap

545

n1byn1kt/apitap

Skill Claude CodeCodex

ApiTap gives AI agents cheap access to web data through three layers.

not rated 125 1mo ago A 0 tokens original Apache-2.0

freestylefly/wechat-article-extractor-skill

Skill Claude CodeCodex

Extract metadata and content from WeChat Official Account articles. Use when user needs to parse WeChat article URLs (mp.weixin.qq.com), extract article info (title, author, content, publish time, cover image), or convert WeChat articles to structured data. Supports various article types including posts, videos…

not rated 125 +1 6mo ago A 76 tokens

consensus-check

547

Yijia-Xiao/FinanceHarness

Skill Claude CodeCodex

Summarize the sell-side view on an equity — analyst price targets, forward EPS/revenue estimates and ratings — and corroborate it against recent guidance and estimate revisions from the web.

not rated 126 +12 17d ago A 41 tokens copy · 89% Apache-2.0

net-deep-research

548

h4444433333/net-deep-research

Skill Claude CodeCodex

Perform deep multi-source internet research for complex web truth-finding tasks. Prefer explicit /net-deep-research invocation. Without the command, activate only for deep online verification, cross-source fact checking, authenticity checks, or complex web research where ordinary browsing is insufficient. Do not use…

not rated 125 +1 15d ago A 73 tokens MIT-0

early-experience-data

549

OSU-NLP-Group/EarlyExperience

Skill Claude CodeCodex

Use this skill whenever the user asks to generate, collect, inspect, or prepare early-experience training data (Implicit World Modeling or Self-Reflection, in the sense of arXiv:2510.08558) for an agent environment. Trigger phrases include "rollout", "collect expert trajectories", "generate reflection", "smoke test…

not rated 124 2mo ago A SkillSpector: pass 125 tokens original MIT

research-superpower

550

kthorn/research-superpower

Plugin Claude Code

Bundles 10 skills, 1 hook · 217 tokens together

Systematic literature searching and review toolkit for Claude Code. Search PubMed, screen papers, extract data, traverse citations, and synthesize findings from scientific literature.

not rated 123 10mo ago A tokens not measured original MIT

osint

551

smixs/osint-skill

Skill Claude CodeCodex needs its repo

Conduct deep OSINT research on individuals. Build full digital footprint, psychoprofile (MBTI/Big Five), career history, social graph with confidence scores. Recursive self-evaluation until completeness threshold is met. Includes internal intelligence (Telegram history, email, vault contacts) before going external.…

not rated 123 +4 6mo ago A 153 tokens original MIT

xiaohongshu

552

zhjiang22/openclaw-xhs

Skill Claude CodeCodex

A tool for Xiaohongshu, a Chinese social platform for lifestyle and consumer posts, images, and videos.

not rated 121 +1 6mo ago A 166 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: