- Home
- Skills
- Research & Analysis
- Research Assistant
Works with the AI Agents you already use
Research Assistant
It ties its advice to why you are researching, so the action steps fit your situation.
$5
Research Assistant
Example session with this skill installed
I'm trying to decide between [option A], [option B], and [option C] for [what you need it for]. My budget is [amount], and the most important things to me are [your top priorities].
- Read your context and instructions
- Compiled the research assistant
Claude's first reply
This skill will deliver your complete Research Brief. Let me ask a few questions so it covers exactly what you need.
- What do you want to research? It sounds like you're comparing three email platforms. Is that right?
- Why? What will you do with this? For example, pick one this week, or move an existing list.
After the consultation, the brief (excerpt)
DECISION BRIEF: Which email platform fits a 2,000-subscriber shop
OPTIONS COMPARED
| Factor | Option A | Option B | Option C |
|---|---|---|---|
| Ease of setup | Simple drag-and-drop editor | Steeper learning curve | Simple, fewer templates |
| Automations | Basic welcome series | Advanced, branching flows | Basic |
| Price/Cost | Lowest at your list size | Highest | Mid-range |
RECOMMENDATION
Because you want to launch this month and don't need advanced flows yet, Option A fits best.
THINGS TO VERIFY BEFORE DECIDING
Check current pricing for your list size on each platform's pricing page, since plans change often.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
When you ask an AI to "research" something, you often get a wall of text full of vague headings like "cost is an important factor" and no clear answer to the question you actually had.
What it does
Research Assistant is a skill for Claude, made by The Lily Studio. It starts with a short consultation, asking two or three questions at a time: what you want to research, why you need it, which mode you want, how much you already know, any specific questions, and any limits like budget, timeline, or location.
Then it delivers one of three briefs:
- Quick brief: 3 to 5 key facts, 2 to 3 things to watch out for, a bottom line for your situation, and where to learn more
- Deep dive: an executive summary, detailed findings by topic, common mistakes, what it couldn't determine, action steps, and a source roadmap
- Decision research: a side-by-side table of 2 to 4 options with key factors, cost, pros, and cons, a recommendation based on your situation, and what to check before you decide
When it's done, Claude offers to go deeper on any section, add options to the comparison, or look into something it missed.
Why it beats prompting it yourself
This skill states real findings, not topic labels. Every finding has a specific fact or claim in it. It ties its advice to why you are researching, so the action steps fit your situation. It is honest about what it doesn't know, with a "what I couldn't determine" section in every deep dive. Instead of made-up links or fake citations, it gives you specific search terms, website names, and resources so you can check each finding yourself.
Use cases
- Comparing products, services, or tools before you buy
- Getting up to speed on a new field, industry, or topic before a meeting
- Preparing for a big decision, like choosing a software platform or a course
- Building a starting point for an article, presentation, or business plan
Known limitations
- It works from Claude's own knowledge. It doesn't browse the web or pull live data, so prices, availability, and recent news may be out of date. The brief tells you what to check.
- It doesn't give web links or formal citations. It gives search terms and resource names instead, so nothing is made up.
- It isn't legal, medical, or financial advice. For those decisions, check with a qualified professional.
- One research brief per use.
- Built and tested for Claude.
Cannot browse the live web. Requires user to verify time-sensitive data (like current pricing) using the provided source roadmaps.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
12 uses
Times used to date
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 8 days ago
Permissions
No special permissions declared or detected