Back to resources

SKILL

scientific-brainstorming

Primary machine endpointhttps://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/scientific-brainstorming
Use with an agent

SUMMARY

What it does

This Agent Skill provides a structured, evidence-aware brainstorming workflow for scientific ideation. It guides users through independent idea generation, structured discussion, explicit assumption recording, transparent evaluation with pre-defined criteria, adversarial review, literature checking, and decision logging. The skill emphasizes separating ideation from evidence assessment and hypothesis validation, and includes bias and failure controls. It also bundles optional local command-line utilities for session scaffolding, validation, and evaluation matrix calculation. The skill is designed for early-stage research brainstorming and prioritizing candidate directions, and explicitly defers empirical validation, study design, ethics/regulatory review, and clinical questions to appropriate experts or skills.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

research.brainstormweight 100 · confidence 90research.evaluateweight 80 · confidence 80research.reviewweight 70 · confidence 70research.documentweight 60 · confidence 60

MACHINE-READABLE ENDPOINTS

How agents read it

ACCESS

Access requirements

Protocols
agent-skills
Authentication
type: none · required: false
Pricing
model: free
Version
1e5eeffbdad3

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.