Scientific Brainstorming Facilitator
Runs evidence-aware research ideation with independent generation, transparent scoring, adversarial review, and an auditable decision log.
EducationIntermediate★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026
What it does
- Scopes a session around one focal question, recording constraints, out-of-scope topics, and sensitive areas (human subjects, animals, clinical care, controlled technologies).
- Forces independent, private idea generation before group discussion to limit anchoring and production blocking.
- Captures each idea with a stable ID, provenance (human / AI-assisted / literature-inspired), assumptions, testable predictions, and possible disconfirming evidence.
- Defines criteria, directions, and weights before scoring, keeping raw ratings, uncertainty ranges, dissent, and abstentions visible.
- Runs adversarial review by non-authors and enforces feasibility/ethics/dual-use gates that override any high creativity score.
- Ships optional deterministic Python CLIs (standard library only, no network or LLM calls) to scaffold a session register, validate it, and compute a fully disclosed weighted matrix with sensitivity analysis.
Who it's for
- Researchers and PIs facilitating lab meetings or grant ideation who need bias controls.
- R&D and strategy teams prioritizing candidate directions with a documented rationale.
- Teams that must disclose and audit AI-assisted contributions to research ideas.
Example uses
- "Which mechanisms could explain this microbiome observation?" → scope, independent round, clustering, criteria definition, then a weighted evaluation matrix.
- Narrowing five candidate directions to two: assign non-originating reviewers, log falsifying observations, alternative explanations, mitigations, and the final decision.
- Run
python scripts/session_scaffold.pyto create a register, thenvalidate_register.pyto catch missing provenance or structural gaps.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/scientific-brainstorming/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/scientific-brainstorming folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/scientific-brainstorming/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/scientific-brainstorming ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal. If you want the CLIs, confirm
python3 --versionis 3.11 or newer. - Clone the repo:
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git - Create the skills directory:
mkdir -p ~/.claude/skills - Copy the skill:
cp -r scientific-agent-skills/skills/scientific-brainstorming ~/.claude/skills/ - Verify that
SKILL.mdplus thereferences/andscripts/folders exist under~/.claude/skills/scientific-brainstorming/. - Restart Claude Code and ask something like "Facilitate a scientific brainstorming session on this research question."
View source on GitHub ↗License: MIT