Is the Scientific Hypothesis Generation skill free?

Yes. The skill itself is free from TobiasBlask/open-paper-machine. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Scientific Hypothesis Generation SkillProof Score?

8.0/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 3/5.

How do I install Scientific Hypothesis Generation?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Scientific Hypothesis Generation with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Scientific Hypothesis Generation

Turns an observation into 3-5 literature-grounded, falsifiable hypotheses with experiment designs and predictions.

by TobiasBlask · TobiasBlask/open-paper-machine

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.0/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 2e1ea13

The reasoning workflow (steps 1-7) produced a genuinely rigorous A/B win: a literature-grounded set of 4 falsifiable hypotheses with a randomized-encouragement design that specifically isolates the causal story from a self-selection confound the baseline only mentioned in passing. But step 8 calls a 'MANDATORY' figure-generation script that physically lives in a sibling scientific-schematics skill folder (not included in a verbatim copy) and that script itself silently requires Gemini API access ("Nano Banana 2" + Gemini 3.1 Pro Preview) never disclosed in this skill's frontmatter.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 3/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 3/5

What Scientific Hypothesis Generation does

Runs a structured scientific-method workflow — literature search, competing-hypothesis generation, quality scoring (testability, falsifiability, parsimony), experimental design, and testable predictions — from a raw observation or dataset finding. Triggers when the user has an observation and wants rigorous, testable explanations rather than open-ended brainstorming.

How to install Scientific Hypothesis Generation

git clone https://github.com/TobiasBlask/open-paper-machine.git
cd open-paper-machine
mkdir -p ~/.claude/skills
cp -r scientific-skills/hypothesis-generation ~/.claude/skills/hypothesis-generation

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Scientific Hypothesis Generation

/hypothesis-generation Turns an observation into 3-5 literature-grounded, falsifiable hypotheses with experiment designs and predictions.

It also activates on plain-language prompts like these:

I noticed 24h onboarders retain 3x better, help me form testable hypotheses
Generate falsifiable explanations for this retention pattern with experiments
Turn this dataset finding into rigorous, literature-backed hypotheses to test

Frequently asked questions

Is the Scientific Hypothesis Generation skill free?: Yes. The skill itself is free from TobiasBlask/open-paper-machine. SkillProof publishes the install command and an independent test verdict at no cost.
Does Scientific Hypothesis Generation work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Works with setup. The reasoning workflow (steps 1-7) produced a genuinely rigorous A/B win: a literature-grounded set of 4 falsifiable hypotheses with a randomized-encouragement design that specifically isolates the causal story from a self-selection confound the baseline only mentioned in passing. But step 8 calls a 'MANDATORY' figure-generation script that physically lives in a sibling scientific-schematics skill folder (not included in a verbatim copy) and that script itself silently requires Gemini API access ("Nano Banana 2" + Gemini 3.1 Pro Preview) never disclosed in this skill's frontmatter.
What is the Scientific Hypothesis Generation SkillProof Score?: 8.0/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 3/5.
How do I install Scientific Hypothesis Generation?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Scientific Hypothesis Generation with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.