Research skills

17,426 tagged Research, measured the same way as everything else here.

Browse within: agent 215LLM 191agents 131bioinformatics 102claudecode 101agentic-ai 90ai-scientists 87reasoning-agent 87reasoning-language-models 87tool-use 87cursor 85academic-research 84data-analysis 80skills 80

digital-person

1753

justinjia0813/digital-person-skill

Skill Claude Code

A tool that studies someone’s public posts on WeChat public accounts, Weibo, and Twitter/X to extract their ideas, decision methods, and writing style.

not rated 2 4mo ago A 121 tokens

research

1754

marvinleonbutlerii/.dotfiles

Skill Claude Code

Deep research and knowledge synthesis. Activates for ANY task involving factual claims, technical decisions, implementation patterns, or domain knowledge. Deactivated ONLY when the mechanical task test passes (all three conditions true).

not rated 2 12d ago A 46 tokens

wiki-ingest

1755

HAR5HA-7663/graphify-starter

Skill Claude CodeCodex

Ingest a file from /brain/raw/ into the wiki. Extract key concepts and entities, create or update pages in /brain/wiki/pages/, add cross-references, append to log.md. Use when the user says "/wiki-ingest", "ingest raw/...", or drops a file in raw/ and asks to process it.

not rated 2 3mo ago A 72 tokens

knowledge-acquisition

1756

wawiesel/InfiniClaw

Skill Claude CodeCodex

Explore, organize, and extract knowledge using WKSM MCP tools. Use for filesystem exploration, file organization, document extraction, vault generation, and knowledge base management.

not rated 2 5mo ago A 36 tokens

notebooklm

1757

fredchu/claude-dotfiles

Skill Claude CodeCodex

Complete API for Google NotebookLM - full programmatic access including features not in the web UI. Create notebooks, add sources, generate all artifact types, download in multiple formats. Activates on explicit /notebooklm or intent like "create a podcast about X".

not rated 2 1mo ago A 57 tokens original MIT

find-docs

1758

lordjabez/claude-code-config

Skill Claude CodeCodex

Retrieves up-to-date documentation, API references, and code examples for any developer technology. Use this skill whenever the user asks about a specific library, framework, SDK, CLI tool, or cloud service -- even for well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot. Your…

not rated 2 1mo ago A 172 tokens MIT-0

wiki

1759

read2001/wiki

Skill Claude Code

Operate an LLM-maintained personal knowledge base (an "LLM Wiki") — a persistent, interlinked markdown wiki that the LLM builds and maintains from raw sources, used for study, research, and reading notes. Use this whenever the user wants to ingest sources into their knowledge base — one at a time or in a batch via…

not rated 2 2mo ago A 181 tokens original MIT

选题大师

1760

Feng-wj/xuanti-master-skill

Skill Claude CodeCodex

A research-topic adviser that turns a vague idea into a clearer study question through guided questions, different viewpoints, and checks against academic standards.

not rated 2 2mo ago A 107 tokens

rumi-run/ai-truthfulness-rules

Skill Claude CodeCodex

Use when answering strategic, executive, analytical, research, coding, business, financial, compliance, or high-impact questions where the AI must avoid generic trendy advice, separate facts from assumptions, challenge weak premises, compare options fairly, and make evidence, risks, uncertainty, and human verification…

not rated 2 4mo ago A 66 tokens original MIT

applied-math

1762

Team-Deepiri/deepiri-axiom

Skill Claude Code

Invent mathematics for a system nobody has modeled yet — starting from brainstorming an abstract idea into a concrete, bounded direction, then observation before formalism, invariants, symmetry, dimensional analysis, and state-variable discovery, followed by formulation, proof strategy, and adversarial validation. No…

not rated 2 yesterday A 73 tokens original Apache-2.0

zaowanqaq/systematic-understanding-framework

Skill Claude CodeCodex

A structured method for understanding complex subjects by breaking them into parts, finding patterns, asking challenging questions, and testing conclusions. It includes tools such as first-principles thinking, analogies, root-cause analysis, and the Feynman technique.

not rated 2 3mo ago A 171 tokens original MIT

voc-analysis

1764

bcefghj/anker-ai-product-studio

Skill Claude CodeCodex

A tool for turning real user comments into traceable findings about problems and opportunities. VOC means voice of the customer, and ABSA means analysing the sentiment and topic of specific parts of feedback.

not rated 2 2mo ago A 53 tokens

arxiv-translate

1765

StellarCurtain/arxiv-translate

Skill Claude CodeCodex needs its repo

A tool for downloading research papers from arXiv, an open website for sharing scientific papers, and translating their LaTeX source into another language.

not rated 2 4mo ago A 68 tokens original MIT

quantskills/skill-overseas-equity-factor-miner

Skill Claude CodeCodex

Discover and validate cross-sectional alpha factors for Hong Kong and US equities - generate candidate factors, compute them, and screen by IC, decay, and turnover. Use when a user wants to mine, test, or rank overseas equity factors from Pandadata HK/US price and fundamental data rather than apply a fixed factor set.

not rated 2 2mo ago A 73 tokens GPL-3.0

ddggkkcc/industry-intelligence-researcher

Skill Claude CodeCodex

This skill should be used when conducting evidence-led industry, market, competitive, value-chain, business-model, or investment research across any sector. It converts broad questions into a decision-oriented research brief; combines official statistics, company filings, trade data, expert/participant evidence, and…

not rated 2 27d ago A 111 tokens original MIT

tell-truth

1768

boogiefromzk/tell-truth-skill

Skill Claude CodeCodex

Makes AI when answering to stop being a victim of propaganda but apply at least some epistemic discipline and critical thinking.

not rated 2 1mo ago A 27 tokens original MIT

lycroot/Skills

Skill Claude CodeCodex

A Chinese-language workflow for closely reading research papers and turning them into practical research materials. It covers papers about topics such as wireless sensing, signal processing, and deep learning.

not rated 2 2mo ago A 246 tokens

ai-radar

1770

orzazade/awesome-ai-radar

Skill Claude Code needs its repo

AI trend research and community contribution. Three modes: /ai-radar briefing — personalized AI news briefing based on your stack /ai-radar contribute — research trends and open a PR to awesome-ai-radar /ai-radar catch-up [topic] — deep dive on a specific AI topic Use when: "what happened in AI", "AI trends", "what…

not rated 2 5mo ago A 106 tokens original MIT

Lord1Egypt/awesome-skill-forge

Skill Claude Code

A citation tool for research papers and theses, including documents written for academic degrees. It finds real publication details and formats citations and reference lists in styles such as APA, MLA, Chicago, IEEE, and Harvard.

not rated 2 3mo ago A 35 tokens original MIT

brutal-idea-eval

1772

sssemil/SKILLS

Skill Claude Code

Comprehensive IDEA evaluation combining Reality's Moat scar tissue framework, Revenue Reality Check, VC Power-Law filter, and structured deep research pipeline. Point it at an IDEA.md for end-to-end analysis: defensibility ratio, revenue viability, VC scalability, validated research, and synthesized verdict with pivot…

not rated 2 1mo ago A 69 tokens original MIT

ucsb-dreamlab/skills

Skill Claude CodeCodex

Follow best practices for research data management, including folder structure, file naming, and documentation standards.

not rated 2 1mo ago A 22 tokens

asimov

1774

asimov-platform/skills

Skill Claude CodeCodex

Use the ASIMOV CLI to join the user's personal knowledge (such as mail, messages, documents) and public data in one knowledge base. Use when the user mentions ASIMOV, wants their own data in the task, or needs a data source an ASIMOV module handles.

not rated 2 changed 7d ago A 61 tokens original Unlicense

tech-topic-research

1775

85danf/agent-skills

Skill Claude Code

Research a technology, tool, framework, concept, or methodology — or compare two or more of them — through a progressive flow: preliminary gist delivered immediately from web search, informed clarifying questions, then parallel subagent research synthesised into a conversational explanation or a written study guide.…

not rated 2 3mo ago A 85 tokens original MIT

find-influencers

1776

agentrhq/agent-automation-skills

Skill Codex

Use when finding, researching, filtering, evaluating, comparing, or shortlisting influencers and creators on YouTube or X/Twitter for a topic, campaign, partnership, or outreach list, especially when numeric thresholds, qualitative content fit, audience signals, cross-platform identity matching, or CSV output are…

not rated 2 26d ago A 65 tokens 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: