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.

research

1369

eddiebelaval/squire

Command Claude Code

You are the orchestrator for the id8Labs Research Lab at /Development/id8/research-lab/.

not rated 21 2mo ago A 0 tokens original MIT

fact-check

1370

victorbuto/claude-skills

Skill Claude CodeCodex

A fact-checking workflow for reports and claims that checks primary sources and independent sources, then gives a transparent reliability assessment. It supports a chat report and other requested output modes.

not rated 21 +5 4d ago A 0 tokens

vhir-tool-reference

1371

AppliedIR/sift-mcp

Skill Claude CodeCodex

Which Valhuntir MCP tool or SIFT tool to use for a question, file, IOC or artifact, and the step-by-step workflows that combine them (IOC investigation, threat actor research, detection engineering, malware analysis, disk, memory, timeline and network). Use when choosing tools or planning a multi-step analysis.

not rated 21 +2 changed 21d ago A 69 tokens original MIT

applied-micro

1372

kennethkhoocy/applied-micro-skills

Plugin Claude Code

Bundles 17 skills · 2,984 tokens together

Claude Code skills for empirical applied-micro research: reproducibility auditing, LLM-pipeline methods, event studies, WRDS, Stata, publication-grade tables.

not rated 20 2mo ago A tokens not measured copy · 86% MIT

challenge

1373

grainulation/wheat

Command Claude Code

You are stress-testing a specific claim by researching the strongest possible counter-argument with real evidence. Read CLAUDE.md for sprint context and claims.json for existing claims.

not rated 20 6mo ago A 0 tokens original MIT archived

lastsearch

1374

LastSearch-HQ/lastsearch

MCP server Claude CodeCodexCursor +2

Evidence-backed web research for AI agents with citations and confidence scores. Runs locally from the lastsearch npm package. Needs 1 environment variable to run.

not rated 20 2d ago A tokens not measured original Apache-2.0

gemini-research

1375

rmedranollamas/research-cli

Skill Claude CodeCodex

Perform deep research on complex topics using the Gemini Interactions API. Use when the user needs in-depth information, technical analysis, or comprehensive reports on a specific topic. This skill leverages the Gemini Interactions API for multi-step reasoning and tool use.

not rated 20 yesterday A SkillSpector: pass 55 tokens original Apache-2.0

news-fact-checker

1376

kaixindelele/wechat_agent_bridge_skills

Skill Claude CodeCodex

A tool for translating English research-paper PDFs into Chinese while keeping the original page layout, including figures, formulas, and images. It accepts an arXiv link, an arXiv ID, or a local PDF.

not rated 20 6mo ago A 126 tokens original MIT

bytebell

1377

ByteBell/openspecs-index

Skill Claude Code

Bytebell-public local knowledge graph. Discover, search, lookup, and retrieve from code repositories indexed locally by bytebell-server. TRIGGER when using: listknowledge, smartsearch, keywordlookup, retrievefile.

not rated 20 2mo ago A 46 tokens

github-kb

1379

CopeeeTang/rednote-mind-skills

Skill Claude CodeCodex

GitHub Knowledge Base - Unified tool for managing local repos, discovering trending projects, and tracking tech hot topics. Use when: (1) searching local GitHub repos, (2) updating repo index, (3) discovering new repos via social media (Xiaohongshu, Twitter/X) and web search, (4) researching topics on Xiaohongshu, (5)…

not rated 20 9mo ago A 123 tokens original MIT

opentwitter

1380

6551Team/openskills-weixin

Skill Claude Code

Twitter/X data via the 6551 API. Supports user profiles, tweet search, user tweets, follower events, deleted tweets, and KOL followers.

not rated 20 7mo ago A 35 tokens original MIT

mcp-webresearch

1381

chuanmingliu/mcp-webresearch

MCP server Claude CodeCodexCursor +2

MCP server for web research. Runs locally from the @mzxrai/mcp-webresearch npm package.

not rated 20 1y ago A tokens not measured original MIT

davanstrien/hub-semantic-search-mcp

MCP server Claude CodeCodexCursor +2

MCP server "hub-semantic-search-mcp" as configured in davanstrien/hub-semantic-search-mcp. Runs locally from the hub-semantic-search-mcp Python package.

not rated 20 1y ago A tokens not measured original MIT

spek-knowledge

1384

jumppad-labs/spektacular

Skill Claude CodeCodex

Search, contribute to, or update the project's knowledge base.

not rated 20 changed 1mo ago A SkillSpector: warn 17 tokens original Apache-2.0

pinpoint-lesson

1385

ajs7270/zotero-ai-summary

Skill Claude CodeCodex

Compose a long-form pin-point lesson from one paper and register it as a Zotero child note. Use when the user provides a PDF or paper title and wants a math-grounded, idea-genealogy, fundamental-why analysis rather than a quick summary. Contrast with the summary skill, which produces a shorter overview note.

not rated 20 5mo ago A 70 tokens original MIT

vault-scout

1386

mm-weber/loremaester

Skill Claude CodeCodex

Use when you need to find, list, or read-and-summarize Obsidian vault notes mechanically — e.g., "find all NPC notes tied to faction X", "list all session N scene files", "read frontmatter of these 12 notes and return a table", "grep all Locations/ notes for wikilinks to [[NPC Name]]". Dispatches a Haiku subagent to…

not rated 20 +1 changed 2d ago A 147 tokens original MIT

openorder

1387

realnaka/alphaloop

Skill Claude CodeCodex

OpenOrder — Order out of investment chaos. An AI-maintained investment research wiki that compounds your edge across every conversation. Triggers automatically on: (1) any stock ticker (US/HK/A-share/TW/JP) or company name; (2) industry/theme discussions (semiconductors, AI infra, photonics, HBM, energy, biotech…

not rated 20 4mo ago A 195 tokens original MIT

anysite-skills

1388

anysiteio/agent-skills

Plugin Claude Code

Bundles 18 skills, 1 plugin · 2,213 tokens together

Professional skills for GTM and data work on the anysite MCP server. Includes the GTM/CRM package (GTM onboarding, CRM setup, enrichment, buying signals, champion tracking, prospecting, scoring, inbound lead verdicts, account briefs, lookalikes, competitor displacement) plus research skills for LinkedIn, Instagram…

not rated 20 changed 1mo ago A tokens not measured original MIT

TobiasBlask/open-paper-machine

Plugin Claude Code

Bundles 33 skills, 21 commands, 4 agents · 3,926 tokens together

Open Academic Paper Machine — Autonomous academic paper production system with idea evaluation gate and paper-vs-code audit. NEW in v6.4: /audit-paper command and audit-engine skill — static audit of a paper's empirical claims (datasets, models, hyperparameters, metrics) against the linked code repository, classifying.

not rated 20 7mo ago A tokens not measured original MIT

hive

1390

hive-intel/hive-sdk

Plugin Claude Code

Bundles 18 skills, 1 MCP server · 1,915 tokens together

One OAuth-ready connection for evidence-backed crypto due diligence, with sources, freshness, and a runtime receipt on every Hive call.

not rated 20 changed yesterday A tokens not measured original MIT

wtfp-argument-verifier

1391

akougkas/wtf-p

Agent Claude Code

Verify that completed section text actually delivers the claims, evidence, constraints, and connections promised by its plan. Execution summaries are navigation aids, not proof; verdicts must be grounded in the manuscript itself.

not rated 20 changed 1mo ago A 47 tokens original MIT

mcp-web-hound

1392

ilgizar-valiullin/mcp-web-hound

MCP server Claude CodeCodexCursor +2

MCP Web Hound — unified web search, GitHub search, and GitLab search tools with caching, reranking, and rate limits. Runs locally from the mcp-web-hound npm package.

not rated 20 +1 4d 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: