Experiment Suite

Experiment Suite is an AI Engineering skill for Claude Code, published by ai4s-research in ai4s-skills.

204 stars19 forkson ai4s-research/ai4s-skillsAdded 2026/09/05Repository updated 2026/07/28

agent-skillsai-agentai-for-scienceai-scientistai4sclaude-codeclaude-skillsliterature-reviewopen-scienceopencodepaper-writingreproducible-researchresearch-toolsscientific-research

Install in seconds

Install Experiment Suite

Copy Experiment Suite 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/ai4s-research/ai4s-skills/tree/main/skills/experiment-suite ~/.claude/skills/experiment-suite

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/ai4s-research/ai4s-skills.git

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

In this catalog

Source file: skills/experiment-suite/SKILL.md in ai4s-research/ai4s-skills
Installs to: ~/.claude/skills/experiment-suite
Collection: One of 7 skills cataloged from this repository
Category: AI Engineering — 3101 skills

What Experiment Suite does

Experiment Suite builds a complete research experiment package with design docs, runnable code, results, publication-grade figures, and a structured report. Use it when a research question needs an end-to-end experiment workflow with honest provenance.

Experiment Suite is cataloged under AI Engineering on DirSkills. Experiment Suite comes from a repository tagged agent-skills, ai-agent, ai-for-science, ai-scientist and ai4s.

Documentation

README

Excerpt

Experiment Suite

Overview

End-to-end experiment package builder. Single stage, full quality from the start. The agent (Claude Code / Cursor / Aider / Codex / …) writes everything directly using its own tools (Write, Bash, WebFetch, …). This skill contains procedure + reference playbooks + figure-example scripts — no Python runtime, no LLM SDK.

The substantive work is decomposed into reference playbooks under references/:

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

Frequently asked about Experiment Suite

What else does ai4s-research publish alongside Experiment Suite?
Experiment Suite is one of 7 skills that DirSkills catalogs from ai4s-research/ai4s-skills, the repository it ships in. Its siblings there include AI4S Agent, Integrity Auditor and Literature Survey. Each one is a separate skill with its own page in this directory, installs the same way Experiment Suite does, and is maintained by ai4s-research in that same repository. The rest of the collection is listed on the ai4s-research/ai4s-skills page.
How does Experiment Suite compare to other AI Engineering skills?
Experiment Suite ranks #2802 by stars among the 3101 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 Experiment Suite against them. Open each page to compare what they document and how they install.