Research

26,336 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.

librarian

1249

Timeflys2018/zeyi

Agent Claude Code

External reference researcher — looks up library docs, framework conventions, OSS examples. Read-only, no memory injection. (Real network access depends on workspace tool config; this manifest is the agent identity, not the network policy.).

not rated 21 1mo ago A 48 tokens original MIT

bitcoin-knowledge-base

1251

tnull/bitcoin-knowledge-base

Skill Claude CodeCodex

Search across the Bitcoin and Lightning development ecosystem: BIPs, BOLTs, bLIPs, LUDs, NUTs, GitHub issues/PRs/commits, mailing lists, IRC logs, Delving Bitcoin, BitcoinTalk, and Optech newsletters.

not rated 21 4mo ago A 0 tokens

arxiv-retriever

1252

PKUfudawei/arxiv-skills

Skill Claude CodeCodex

Search and download arXiv papers by extracting parameters from natural language requests.

not rated 21 changed 9d ago A SkillSpector: pass 20 tokens original MIT

sdlc-project-research

1253

BlueSkyXN/Codex-is-all-you-need

Skill Claude CodeCodex

A repository-research workflow for building a map of a project's existing capabilities from code and other repository evidence.

not rated 21 28d ago A 55 tokens GPL-3.0

polyresearch

1254

superagent-ai/polyresearch

Skill Claude CodeCodex

Coordinate distributed AI research using the polyresearch protocol and CLI. Use when working in a repo containing POLYRESEARCH.md, claiming theses, running experiments, submitting candidates, reviewing PRs, or performing lead duties like syncing results, generating theses, and deciding PRs. Triggers on: polyresearch…

not rated 21 4mo ago A 84 tokens

parallel

1255

mvanhorn/clawdbot-skill-parallel

Skill Claude CodeCodex

High-accuracy web research platform with 7 APIs - Search, Extract, Task (Deep Research), Chat, FindAll, Monitor, and Task Groups. Fast mode, 8 processor tiers, MCP tool calling, authenticated browsing, SSE streaming, and OpenAI-compatible chat. OpenClaw skill.

not rated 21 6mo ago A 62 tokens

whois-mcp

1256

modelcontextprotocol-servers/whois-mcp

MCP server Claude CodeCodexCursor +2

MCP to lookup whois information. Runs locally from the @mcp-server/whois-mcp npm package.

not rated 21 1y ago A tokens not measured

llm-wiki

1258

AnisurRahmann/llm-wiki-kit

Skill Claude CodeCodex

Maintain a personal LLM-generated wiki/knowledge base in Obsidian. Use this skill whenever the user wants to: ingest a new source (AI tool, GitHub repo, article, social post, project doc) into their wiki, query or search their wiki, lint/health-check the wiki, create or update wiki pages, manage the wiki index or log…

not rated 21 5mo ago A 201 tokens original MIT

github-stars-curator

1259

Leexunhuan743/github-stars-curator

Skill Claude CodeCodex

Organize starred GitHub repos into stable, clear lists: detect new stars, download READMEs into a local corpus, classify each repo against the taxonomy, and sync the approved mapping back to GitHub via gh. Use this when a user wants their starred repos sorted into lists, a recent batch of new stars filed…

not rated 21 changed 8d ago A 105 tokens original MIT

websearch-mcpserver

1260

daidaiJ/websearch-mcpserver

MCP server Claude CodeCodexCursor +2

MCP server "websearch-mcpserver" as configured in daidaiJ/websearch-mcpserver. Launched with https://github.com/daidaiJ/websearch-mcpserver/releases/download/v3.1.1/websearc.

not rated 21 +1 today A tokens not measured original MIT

researcher

1262

mikeshu2001/content-factory

Agent Claude Code

A research agent for gathering facts before an overview article is planned. It studies a topic for a defined audience and records the findings in a research brief.

not rated 21 1mo ago A 47 tokens original MIT

focus-group

1263

bradautomates/focus-group

Plugin Claude Code

Bundles 1 skill, 1 hook · 67 tokens together

Clone your customers from real call transcripts, then run them as a standing focus group. Discovers customer archetypes, builds composite personas, and convenes them to react to any offer, hook, price, page, or email before it goes live.

not rated 21 +1 2mo ago A tokens not measured original MIT

manuscript-review

1264

shaowen-ye/manuscript-review-skill

Skill Claude CodeCodex

A review process for academic papers that uses six specialist AI reviewers and produces an annotated document in English and Chinese.

not rated 21 1mo ago A 103 tokens original MIT

arxiv-fetch

1265

yang3kc/daily_arxiv_digest

Plugin Claude Code

Bundles 1 skill · 66 tokens together

Fetch the latest arXiv papers and generate an on-demand digest. The agent judges relevance itself — no API keys needed.

not rated 21 18d ago A tokens not measured original MIT

hoangtng/real-estate-agents

Agent Claude Code

Orchestrates the full relocation experience for clients moving into or out of a market. Handles community orientation, school research, vendor referrals, move logistics coordination, and the dozens of invisible decisions that make a relocation succeed or fail.

not rated 21 +1 4mo ago A 53 tokens original MIT

semantic-scholar-mcp

1267

smaniches/semantic-scholar-mcp

MCP server Claude CodeCodexCursor +2

Model Context Protocol server for Semantic Scholar — 200M+ academic papers, 14 tools spanning paper search, citation graph traversal, author profiles, and recommendations. Runs locally from the s2-mcp-server Python package. Needs 1 environment variable to run.

not rated 21 +1 5d ago A tokens not measured original MIT

academic

1268

SlideSpeak/slide-design-skill

Skill Claude CodeCodex

University-tier research and lecture decks. Citation-heavy, evidence-led, restrained. Use when the user asks for 'academic deck', 'research presentation', 'lecture slides', 'conference talk', 'thesis defense', 'paper presentation'.

not rated 21 +2 2mo ago A 48 tokens original MIT

econ-review

1269

hanlulong/econ-paper-review-skill

Plugin Claude Code

Bundles 2 skills · 227 tokens together

Produce a rigorous, source-grounded referee report and prioritized revision plan for an economics paper. After a direct plugin install, ask the agent to run econ-review-setup once.

not rated 21 +2 11d ago A tokens not measured

socialcrawl

1270

socialcrawl/mcp

MCP server Claude CodeCodexCursor +2

Access 48 platforms and 381 endpoints through one unified API — social media, commerce & product reviews, retail (Amazon, Walmart, Target, Home Depot, eBay, Google Shopping), app stores (Google Play, App Store), places & travel (Tripadvisor, Google Busine. Runs locally from the socialcrawl-mcp npm package. Needs 1…

not rated 21 +8 4d ago A tokens not measured original MIT

kivgraph

1271

Luqueee/kivgraph

Skill Claude CodeCodex

Use Kivgraph's local MCP server to search symbols, read their source, and follow references, dependencies, cross-repository consumers and graph status in the indexed code graph.

not rated 21 +2 changed 5d ago A SkillSpector: pass 39 tokens original Apache-2.0

academic-deep-research

1272

kesslerio/academic-deep-research-clawhub-skill

Skill Claude CodeCodex

Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (websearch, webfetch, sessionsspawn). Use for…

not rated 21 1mo ago A 85 tokens original Apache-2.0

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: