AI Agent Skills for Research
Browse reusable agent skills for research, synthesis, documentation, knowledge capture, and evidence-backed AI workflows.
Reusable skills turn ad hoc prompting into repeatable research workflows.
This cluster is built for analysts, operators, and technical teams that need reusable instructions for discovery, summarization, due diligence, and knowledge capture.
Top matches for research agent skills
These listings are pulled from the live catalog using category and keyword relevance signals.
Consensus
AI summaries of academic research.
Elicit
AI literature research assistant.
Gamma
AI-powered platform for creating presentations, documents, and webpages with intelligent design and fast workflows.
Superhuman AI
Speedy, intelligent email management.
Slite AI
Team docs with AI-powered summaries.
Readwise Reader
Improved reading with smart highlights and notes.
Recall
Learning assistant with summaries and quizzes.
Obsidian
AI-enhanced features for the popular markdown-based knowledge management system.
Perplexity Pro
AI-enhanced search engine offering real-time answers with citations.
SEO AI
Unlock top search positions for your website
Gemini CLI
Open-source AI agent bringing Google Gemini directly to terminal with ReAct loop and MCP support
Qwen CLI
AI-powered command-line tool for code analysis and editing with Qwen3-Coder model and MCP integration
Reusable skills for this workflow
Operational instructions and reusable agent workflows that complement the tools above.
A popular GitHub collection of specialized AI agents for engineering, marketing, product, support, design, and multi-tool workflows.
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
News and articles tied to this use case
Context pages that help explain launches, workflow shifts, and the surrounding market.
Most people still think AI is just a smarter chatbot. You type something, it replies. End of story. But the moment you give an AI actual skills, everything changes. Suddenly it stops talking and starts doing. I’ve watched this shift happen in real products we build at aidrift.tech. The teams that treat AI like a colleague with specific abilities get 5–10× more done than the ones who only prompt. Here’s what AI skills actually are, why they matter right now, and the exact examples you can copy today.
blog
A deep dive into the AI video generator that went from a quiet Chinese tech lab to one of the most talked-about creative tools on the planet.
blog
OpenAI challenges researchers to build the best language model in just 16 MB - and uses the competition to scout talent. The article OpenAI turns model compression into a talent hunt with its 16 MB "Parameter Golf" chall
news
Autonomous LLM agents like OpenClaw are shifting the paradigm from passive assistants to proactive entities capable of executing complex, long-horizon tasks through high-privilege system access. However, a security analy
news
Discover why developers are switching to Goose. We compare Block's free, open-source AI agent against Anthropic's expensive Claude Code for coding.
blog
Explore the Microsoft Copilot bug that exposed confidential emails. We analyze the implications for AI data privacy, enterprise security, and the future of LLM governance.
blog