IQ

    IDEAgent: Quality-Diversity Research Ideation

    1

    Generate portfolios of high-quality, mutually diverse research ideas using Steno memory, adversarial panels, and Yield clique search.

    $15

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more
    IQ

    IDEAgent: Quality-Diversity Research Ideation

    Example session with this skill installed

    Generate 5 high-quality, mutually distinct research directions on test-time compute scaling for code synthesis.

    • Read your context and instructions
    • Compiled the ideagent

    Produces a portfolio of validated research ideas with Steno signatures, multi-dimensional scores (N, S, C), 5-member adversarial evaluations, and exact Yield clique metrics.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Based on IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation (Gumma, Majumder, Sinhahajari, Poria; NTU DeCLaRe Lab, arXiv:2607.22375v2).

    Standard LLM brainstorming fails in two coupled failure modes:

    1. Optimizing for Quality alone causes conceptual collapse: multiple paraphrases or minor variants of a single strong idea.
    2. Optimizing for Diversity alone produces semantic sprawl into trivial, unsound, or hand-wavy ideas.

    IDEAgent solves this by treating ideation as an explicit Quality-Diversity (QD) Conjunction: discovering a maximal set of ideas where every proposal independently satisfies rigorous quality thresholds (Non-Obviousness $N \ge 60$, Soundness $S \ge 60$, Clarity $C \ge 60$) and all pairs remain mutually distinct ($D \ge 60$).

    Determine the following configuration (ask at most one clarifying question if critical details are missing):

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 14 days ago

    Software
    Python 3.9+

    Permissions

    Terminal / Shell
    Listed14 days ago

    What's inside

    Frequently Asked Questions

    Yield is the size of the maximum clique in a graph where nodes are ideas meeting all quality thresholds (Non-Obviousness, Soundness, Clarity >= 60) and edges represent pairwise conceptual distinctness (D >= 60).

    Instead of passing full prior ideas into context (which causes context contamination and drops Yield to 0.000), IDEAgent generates against 5-field Steno signatures and failure patterns, enforcing true conceptual diversity.