Discovery Director

by dekan-aleksandr

Discovery Director is an AI Engineering skill for Claude Code, published by dekan-aleksandr in biodiscovery-skills.

10 stars2 forkson dekan-aleksandr/biodiscovery-skillsAdded 2026/08/12+900% in starsRepository updated 2026/08/08

View source on GitHub Download repo ZIP

agent-skillsai-scientistbioinformaticsclaude-code-skillsclaude-skillsscientific-discovery

Install in seconds

Install Discovery Director

Copy Discovery Director 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/dekan-aleksandr/biodiscovery-skills/tree/main/skills/discovery-director ~/.claude/skills/discovery-director

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/dekan-aleksandr/biodiscovery-skills.git

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

In this catalog

Source file: skills/discovery-director/SKILL.md in dekan-aleksandr/biodiscovery-skills
Installs to: ~/.claude/skills/discovery-director
Collection: One of 2 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Discovery Director does

Discovery Director operates as a research director for open-ended biological questions and datasets. It helps explore omics or experimental data, generate and test hypotheses, investigate anomalies, and choose the next analysis or experiment.

Discovery Director is cataloged under AI Engineering on DirSkills. Discovery Director comes from a repository tagged agent-skills, ai-scientist, bioinformatics, claude-code-skills and claude-skills.

Documentation

README

Excerpt

DISCOVERY MINDSET

Data is sacred. Never delete source data; move replaced material to old/.

Treat the user's question, data, figures, methods, instruments, constraints and prior results as the research environment, not a fixed recipe.

Explore broadly → discriminate → go deep on exceptional leads → confirm independently.

Be risk-tolerant. Expect many failed attempts. Keep a conventional core + adventurous tail: reliable foundations with unusual questions, measurements, representations, scales, subsets or connections. Maintain competing explanations; attach to none.

Allocate effort by scientific upside × expected information relative to the binding resource. Cheap is useful, not sacred.

Optimize for breakthroughs, not for avoiding failure.

ARCHITECTURE

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

Frequently asked about Discovery Director

What else does dekan-aleksandr publish alongside Discovery Director?
Discovery Director is one of 2 skills that DirSkills catalogs from dekan-aleksandr/biodiscovery-skills, the repository it ships in. Its siblings there include Discovery Toolbox. Each one is a separate skill with its own page in this directory, installs the same way Discovery Director does, and is maintained by dekan-aleksandr in that same repository. The rest of the collection is listed on the dekan-aleksandr/biodiscovery-skills page.
How does Discovery Director compare to other AI Engineering skills?
Discovery Director ranks #2443 by stars among the 2451 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 Discovery Director against them. Open each page to compare what they document and how they install.