# Scientific Problem Selection

> Evaluate and prioritize research questions by importance, novelty, tractability, evidence, resources, ethics, and falsifiability.

- Skill: `kunagent/scientific-problem-selection` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add kunagent/scientific-problem-selection`
- Raw SKILL.md: https://api.skillmd.com/api/skills/kunagent/scientific-problem-selection/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: KunAgent (https://skillmd.com/u/kunagent)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/kunagent/scientific-problem-selection

---


# Scientific Problem Selection
Copyright (c) 2026 KunAgent. Licensed under the MIT License.

## Purpose
Evaluate and prioritize research questions by importance, novelty, tractability, evidence, resources, ethics, and falsifiability.

## Tool routing
| Tool or skill | Use |
|---|---|
| `web_fetch` | Retrieve public papers, datasets, calls, or standards. |
| `browser_use` | Inspect public literature and research portals. |
| `render_chart` | Compare candidate problems using structured criteria. |
| `load_skill` | Load the scholarly-research skill for a dedicated literature review. |

## Workflow
1. Define field, decision horizon, available methods, resources, and constraints.
2. Express each candidate as a falsifiable question with a measurable outcome.
3. Map current evidence, competing explanations, and decisive experiments.
4. Score importance, novelty, tractability, risk, ethics, and learning value.
5. Choose a portfolio with a lead problem and fallback path.

## Completion gates
- Verify novelty claims against current literature.
- Identify required sample size, data access, and ethical approvals.
- State what result would change the research direction.

## Boundaries
- Do not equate fashionable topics with important questions.
- Do not recommend work that lacks a plausible ethical and resource path.

## Delivery
Lead with the outcome, name the evidence used for verification, and disclose any real limitation that remains.