Scientific Problem Selection

Scientific Problem Selection is an AI Engineering skill for Claude Code, published by anthropics in knowledge-work-plugins.

23.3K stars2.8K forkson anthropics/knowledge-work-pluginsAdded 2026/07/19Repository updated 2026/08/06

View source on GitHub Download repo ZIP

Install in seconds

Install Scientific Problem Selection

Copy Scientific Problem Selection into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/anthropics/knowledge-work-plugins/tree/main/bio-research/skills/scientific-problem-selection ~/.claude/skills/scientific-problem-selection

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/anthropics/knowledge-work-plugins.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: bio-research/skills/scientific-problem-selection/SKILL.md in anthropics/knowledge-work-plugins
Installs to: ~/.claude/skills/scientific-problem-selection
Collection: One of 26 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What Scientific Problem Selection does

Helps scientists systematically select research problems, generate ideas, troubleshoot projects, and make strategic decisions through a structured conversational framework.

Scientific Problem Selection is cataloged under AI Engineering on DirSkills.

Documentation

README

Excerpt

Scientific Problem Selection Skills

A conversational framework for systematic scientific problem selection based on Fischbach & Walsh's "Problem choice and decision trees in science and engineering" (Cell, 2024).

Getting Started

Present users with three entry points:

1) Pitch an idea for a new project — to work it up together

2) Share a problem in a current project — to troubleshoot together

3) Ask a strategic question — to navigate the decision tree together

This conversational entry meets scientists where they are and establishes a collaborative tone.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Scientific Problem Selection

What else does anthropics publish alongside Scientific Problem Selection?
Scientific Problem Selection is one of 26 skills that DirSkills catalogs from anthropics/knowledge-work-plugins, the repository it ships in. Its siblings there include Accessibility Review, Analyze Data and Bio-Research Start. Each one is a separate skill with its own page in this directory, installs the same way Scientific Problem Selection does, and is maintained by anthropics in that same repository. The rest of the collection is listed on the anthropics/knowledge-work-plugins page.
How does Scientific Problem Selection compare to other AI Engineering skills?
Scientific Problem Selection ranks #263 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Scientific Problem Selection against them. Open each page to compare what they document and how they install.