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.

verify-claim

1753

jamditis/mooc-starter-kit

Command Claude Code

Walk a claim through the SIFT method (Stop, Investigate, Find better coverage, Trace).

not rated 11 1mo ago A 20 tokens

marianfoo/sap-api-policy-skill

Skill Codex

Evidence-based assessment of whether an SAP API/interface usage scenario aligns with the SAP API Policy (v.4.2026a). Use whenever someone asks whether a way of calling SAP is allowed/compliant — e.g. Published API vs internal/private/"confidential" API status, "Documented Use", whether a third-party tool / iPaaS /…

not rated 11 5mo ago A 228 tokens original MIT

hacktricks-mcp-server

1756

Xplo8E/hacktricks-mcp-server

MCP server Claude CodeCodexCursor +2

Search and query HackTricks pentesting documentation with quick lookup and section extraction. Runs locally from the hacktricks-mcp-server npm package.

not rated 11 7mo ago A tokens not measured original MIT

bili-content-analysis

1757

222wcnm/BiliStalkerMCP

Skill Claude CodeCodex

Deep analysis and tracking of Bilibili creators, videos, dynamics, and articles with BiliStalker MCP tools or CLI. Use when users ask for transcript interpretation, timeline reconstruction, theme extraction, behavior analysis, recent shift tracking, or discussion grounded in fetched Bilibili source material.

not rated 11 +1 changed 27d ago A 63 tokens original MIT

openpitch

1758

Avierovich/openpitch

MCP server Claude CodeCodexCursor +2

The OpenPitch MCP server — open, sourced, confidence-scored intelligence on AI startups. Runs locally from the openpitch-mcp Python package.

not rated 11 yesterday A tokens not measured original MIT

scholar-sidekick

1759

mlava/scholar-sidekick-mcp

Skill Claude CodeCodex

This skill should be used when the user mentions a scholarly identifier (DOI, PMID, PMCID, ISBN, arXiv, ISSN, NASA ADS bibcode, WHO IRIS URL) and wants structured metadata, a formatted citation, a bibliography export file, a retraction check, an open-access check, or verification that a claimed citation is real (not…

not rated 11 changed 3d ago A 153 tokens original MIT

nothumansearch

1760

unitedideas/nothumansearch

Skill Claude CodeCodex

Search and score AI-ready websites via MCP. Find MCP servers, check site AI-readiness scores, and verify MCP endpoint compliance using the Not Human Search API at nothumansearch.ai.

not rated 11 +1 2mo ago A 42 tokens original MIT

startup-info

1761

mnfst/startup-info

Skill Claude CodeCodex

Research any startup and produce a concise investor-style briefing. Use when the user asks to look up, research, analyze, or get information about a startup, company, or tech venture. Triggers on "tell me about {company}", "research {startup}", "startup info {name}", "what does {company} do", "analyze {startup}".…

not rated 11 8mo ago A 80 tokens original MIT

heor-agent

1762

neptun2000/heor-agent-mcp

MCP server Claude CodeCodexCursor +2

HEOR MCP server: literature search, CEA, BIA, NMA/MAIC, HTA dossiers (NICE/FDA/EMA/JCA). Runs locally from the heor-agent-mcp npm package.

not rated 11 +1 4mo ago A tokens not measured original MIT

shen169/amazon-product-research-skill

Skill Claude CodeCodex

Amazon Best Sellers category analysis for e-commerce product research and selection decisions. Activates when users analyze Amazon categories, find black horse products, research competitors, or evaluate market entry opportunities. Triggers on phrases like analyze Amazon category, find high-potential products, Amazon…

not rated 11 7mo ago A 166 tokens

lore

1764

hyunjae-labs/lore

Plugin Claude Code

Bundles 2 skills, 1 hook · 290 tokens together

Semantic search skill + MCP server for Claude Code conversation history.

not rated 11 5mo ago A tokens not measured original MIT

omics-skills

1765

fmschulz/omics-skills

Plugin Claude Code

Bundles 34 skills, 4 agents · 1,570 tokens together

Bioinformatics, literature discovery, scientific writing, and data visualization agents and skills for Claude Code and Cowork.

not rated 11 changed 2mo ago A tokens not measured original MIT

apresmoi/jianglens

Skill Codex

Use this skill after every published Jiang Lens episode, or when reassessing an existing episode, to decide and record how that source mutates the corpus, existing lens pages, lens points, atlas structure, chronology, and canon candidates.

not rated 11 1mo ago A 52 tokens

paper-jiedu-latex

1767

tianhanz/paper-jiedu-latex

Skill Claude Code

A workflow for turning a research paper or PDF into a Chinese LaTeX explanation PDF. LaTeX is a document system commonly used for technical papers, and arXiv is an open repository for research papers.

not rated 11 3mo ago A 142 tokens

adversaria

1768

damionrashford/Adversaria

Plugin Claude Code

Bundles 5 skills, 3 agents, 4 hooks · 490 tokens together

Critical thinking platform for decision analysis, proposal review, debate preparation, and due diligence. Three agents (advocate, adversary, judge) over a grounded argument graph, with a live transcript UI, appeal review, and 10 reasoning traditions.

not rated 11 changed 2mo ago A tokens not measured original MIT

sec-edgar-8k-retrieval

1769

suhaas/earnings-edge

Skill Claude CodeCodex

Retrieves a company's most recent 8-K current report and its Exhibit 99.1 earnings press release text from SEC EDGAR via edgartools. Use whenever the task needs an official earnings press release, 8-K event items, or a transcript fallback when earningscall has no coverage for the ticker.

not rated 11 +1 1mo ago A 72 tokens

dsh-web-search-free

1770

sheep-programmer/dsh-web-search-free

MCP server Claude CodeCodexCursor +2

A locally run web-search provider that can be connected to coding agents such as Claude Code and Codex. It supports a free search option, a paid search option, and two ways for software to connect to it.

not rated 11 +1 2mo ago A tokens not measured original MIT

prefer-context-dev-mcp

1771

context-dot-dev/cursor-plugin

Cursor rule Cursor

Use the Context.dev MCP for live web search, company news, scraping, extraction, parsing, brand data, account usage, monitoring, and batches.

not rated 11 +1 changed 1mo ago A 29 tokens original MIT

german-legal-mcp

1772

metaneutrons/german-legal-mcp

MCP server Claude CodeCodexCursor +2

MCP server and typed components for German, Austrian and EU legal research. Runs locally from the @metaneutrons/german-legal-mcp npm package.

not rated 11 7d ago A tokens not measured GPL-3.0

telegram-archive-mcp

1773

GeiserX/telegram-archive-mcp

MCP server Claude CodeCodexCursor +2

MCP server for Telegram Archive — search messages, browse chats, and access history. Runs locally from the telegram-archive-mcp npm package. Needs 3 environment variables to run.

not rated 11 +2 2d ago A tokens not measured GPL-3.0

davidtoby/agent-skills

Skill Claude CodeCodex

Generate polished Chinese consulting-style PDF reports from YouTube videos. Uses a transcription priority chain -- YouTube auto-subs first, Whisper fallback second (with quality gates and proper noun verification). Includes bot-detection bypass escalation when yt-dlp is blocked. Use when a user shares a YouTube link…

not rated 11 yesterday A 76 tokens original MIT

deep-research-swarm

1775

serejaris/kimi-skills

Skill Claude CodeCodex

Orchestrate multi-agent epistemic triangulation: diverge across research dimensions, detect overlaps and contradictions, verify deeply, then converge into a validated synthesis. Swarm parallelism serves epistemic robustness — not merely speed.

not rated 11 +2 3mo ago A 0 tokens original MIT

forager-skills

1776

CyranoB/web-forager

Plugin Claude Code

Bundles 7 skills · 282 tokens together

Seven research skills powered by DuckDuckGo search and Jina Reader: article auditing, web research, fact-checking, news monitoring, competitive intelligence, technology evaluation, and geopolitical analysis.

not rated 11 +1 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: