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.

nuetzliches/powerbrain

Skill Claude CodeCodex

Use when searching company knowledge, querying internal documentation, checking policies, or accessing the Powerbrain knowledge base via MCP.

not rated 5 2d ago A 28 tokens original Apache-2.0

agentcache-research

2162

masteragentcoder/agentcache

Skill Claude CodeCodex

Conducts deep, multi-angle research using the agentcache library's parallel cache-safe forks. Use when the user asks to research a complex topic, investigate architecture trade-offs, or synthesize information from multiple angles.

not rated 5 5mo ago A 47 tokens

run-user-interviews

2163

junetic/usercall-mcp

Skill Claude CodeCodex

Run real user interviews (voice or text) through Usercall and return themes with verbatim quotes. Use when the user wants qualitative feedback, onboarding research, usability tests, prototype review, or to talk to real users instead of guessing.

not rated 5 16d ago A 52 tokens original MIT

searching-with-serpapi

2165

aryrabelo/serpapi-agent-toolkit

Skill Claude CodeCodex

Use when an agent needs live, structured search-engine data through SerpApi (web results, news, shopping, local, jobs, flights, scholar, images, video). Covers picking the right engine for the intent, choosing compact vs complete output, query operators, pagination, deduping and citing results, and when NOT to search.…

not rated 5 3mo ago A 104 tokens original MIT

b2b-marketing-skills

2166

adam-lagerhausen/b2b-marketing-skills

Plugin Claude Code

Bundles 9 skills · 393 tokens together

B2B product marketing skills for AI agents — customer research, positioning, messaging, launches, sales narratives, demos, customer proof, category POVs, and AI PMM review.

not rated 5 2mo ago A tokens not measured original MIT

dimosgit/grounded-knowledge-engine

Skill Codex

Use Grounded Knowledge Engine to select an isolated workspace, answer from local evidence, resume an explicitly identified project, create an explicit project checkpoint, and retain durable knowledge. Trigger when a user asks about their documents, workspace or client context, previous research, project state…

not rated 5 3d ago A 91 tokens original MIT

youtube-research

2168

spinnakergit/a0-youtube-transcribe

Skill Claude Code

Research and analyze YouTube video content. Get summaries, detailed notes, and insights from video transcripts.

not rated 5 4mo ago A 24 tokens original MIT

philo-council

2169

umair-tareen/philosopher-council

Skill Claude CodeCodex

Convene an eleven-philosopher LLM council on a question, decision, plan, or claim - virtue-scored opinions from named philosophers (Socrates, Kant, Lao Tzu, ...), a synthesis, and a first-class minority report. Use when the user asks to "convene the council", "ask the philosophers", wants a decision deliberated from…

not rated 5 1mo ago A 108 tokens original MIT

research-guardian

2170

htlin222/research-guardian-skill

Skill Claude CodeCodex

A research-quality checking system for AI agents. It verifies facts, compares literature, checks experiment designs, and reviews claims about new findings.

not rated 5 4mo ago A 222 tokens

gpt-pro-expert-ally

2171

Icyoung/gpt-pro-expert-ally

Skill Claude CodeCodex

Recruit ChatGPT Pro as an external expert ally for complex engineering, research, review, or artifact work through the user's Codex in-app Browser or Chrome. Package safe context, open a dedicated Pro conversation, monitor long-running work, recover and download deliverables, and independently validate them. Use when…

not rated 5 23d ago A 121 tokens original MIT

expert-librarian

2174

thoreinstein/readwise

Skill Claude CodeCodex

An expert librarian that helps you organize, search, and synthesize your Readwise highlights and documents.

not rated 5 7mo ago A 25 tokens

catch-me-up

2175

0xmerkle/cascadiajs-apify-workshop-2026

Skill Claude CodeCodex

Use when the user asks for recent, latest, current, or web-based information about a topic using their private Apify catch-me-up Actor.

not rated 5 3mo ago A 33 tokens

JeonKH81/claude-cove-reference-verifier

Plugin Claude Code

Bundles 1 skill · 237 tokens together

Detects and corrects reference hallucinations in academic manuscripts using Chain-of-Verification (CoVe). Verifies each citation against PubMed ground truth and produces a structured report with field-level diffs and corrected Vancouver citations.

not rated 5 1mo ago A tokens not measured original MIT

optimai-search

2178

OptimaiNetwork/optimai-search-skill

Skill Claude CodeCodex

Use when an AI coding agent needs to integrate OptimAI Search using the OptimAI MCP server or OptimAI x402 SDK, configure MCP clients, build pay-per-call search agents, explain response formats, choose MCP versus x402, persist payment context, or troubleshoot public OptimAI Search developer workflows.

not rated 5 4mo ago A 63 tokens original ISC

知识库

2181

luna-jmy/thinkdokit-skills

Skill Claude CodeCodex

A search and question-answering helper for a local knowledge-base folder containing notes and files such as PDFs and spreadsheets. It follows index pages to find the right area before searching individual files.

not rated 5 5mo ago A 103 tokens original MIT

competitive-analysis

2182

insight68/Skills

Skill Claude CodeCodex

Analyze competitors with feature comparison matrices, positioning analysis, and strategic implications. Use when researching a competitor, comparing product capabilities, assessing competitive positioning, or preparing a competitive brief for product strategy.

not rated 5 5mo ago A 40 tokens original MIT

research-skills

2183

cailmdaley/skills

Plugin Claude Code

Bundles 8 skills · 709 tokens together

Agent skills for research: autonomous iteration loops, bibliography management, data visualization, scientific coding, image generation, and TTS.

not rated 5 3mo ago A tokens not measured

script-director

2184

semoji-ai/auto_kairos

Skill Claude Code

A production workflow that turns research findings into a script, scene breakdown, visual direction, and motion plan.

not rated 5 changed 5d ago A 33 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: