Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Scientific Hypothesis Generation

Turns observations into evidence-bounded candidate hypotheses, rival explanations, discriminating predictions, and preregistration-ready analysis plans.

EducationAdvanced★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026

What it does

  • Keeps observation, research question, hypothesis, mechanism, estimand, prediction, and evidence strictly separate so nothing gets promoted to "fact" prematurely.
  • Forces generation of rival explanations first: measurement artifact, confounding, selection/attrition, collider conditioning, reverse causation, chance, competing mechanisms.
  • Requires declaring the claim type (descriptive / associational / predictive / causal / mechanistic) and, for causal targets, a fully specified estimand with identification assumptions.
  • Builds a dated evidence boundary (search date, databases, queries, exclusions) so you say "not located within the documented search boundary" instead of "no prior work exists".
  • Ships deterministic, offline CLIs (Python 3.11+ stdlib only) for causal-claim linting, operationalization checks, prediction/rival matrices, evidence-ledger audits, and preregistration scaffolding.

Who it's for

  • Graduate students and researchers drafting papers, theses, or grant proposals.
  • Teams preparing OSF preregistrations, Registered Reports, or clinical/epidemiological protocols.
  • Data analysts who need guardrails against sliding from association to causation.

Examples

  1. "Patients on drug A show lower relapse rates in our cohort" → get a labeled candidate set plus confounding/selection/reverse-causation rivals and tests that discriminate between them.
  2. Lint a manuscript draft with python3 scripts/lint_causal_claims.py draft.md to catch unsupported causal language.
  3. Fill a hypothesis record JSON, then run generate_preregistration_scaffold.py record.json -o preregistration.md to produce a preregistration skeleton.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/hypothesis-generation/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/hypothesis-generation folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/hypothesis-generation/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/hypothesis-generation ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r scientific-agent-skills/skills/hypothesis-generation ~/.claude/skills/
  5. Verify Python: python3 --version (3.11+ required for the bundled CLIs; no extra packages needed).
  6. Restart Claude Code, then prompt something like "Turn this observation into candidate hypotheses and rival explanations" to trigger the skill.
View source on GitHub ↗License: MIT