Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Scientific Hypothesis Generation

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

EducationAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

  • Freezes the observation (source, population, unit, uncertainty, exploratory vs. planned) before any interpretation.
  • Frames the research question with the right template — PICO/PICOT, PECO, diagnostic accuracy, prognosis, or a domain construct frame — instead of forcing PICO everywhere.
  • Records a dated evidence boundary: search date, databases, queries, filters, and limitations, so "not located" never becomes "does not exist".
  • Generates rivals across distinct explanatory classes: measurement artifact, confounding, selection/attrition, collider conditioning, reverse causation, stochastic variation.
  • Declares claim type and causal estimand, then derives predictions that genuinely discriminate between candidates, with real negative and procedural controls.
  • Guards against HARKing with preregistration scaffolds, deviation logs, and replication planning.
  • Ships deterministic, offline Python CLIs that validate structure and internal consistency only — they never score or pick a hypothesis.

Who it's for

  • Graduate students and researchers drafting proposals, protocols, or theses
  • Teams preparing OSF preregistrations or Registered Reports
  • R&D and clinical research groups that must keep causal language disciplined
  • Reviewers stress-testing a study design for hidden assumptions

Examples

  1. Feed in "patients using the app had fewer readmissions" and get a labeled candidate set (mechanism, confounding, selection, reverse causation) plus a prediction–rival matrix.
  2. Run lint_causal_claims.py on a manuscript draft to catch causal phrasing unsupported by an observational design.
  3. Convert a completed hypothesis record JSON into a preregistration draft with generate_preregistration_scaffold.py.

· · · Install guide · · ·

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 and confirm Python 3.11+ is available: python3 --version
  2. Create the skills directory: mkdir -p ~/.claude/skills
  3. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  4. Copy just this skill: cp -r scientific-agent-skills/skills/hypothesis-generation ~/.claude/skills/
  5. Restart Claude Code and confirm hypothesis-generation appears in your skills list.
  6. Trigger it with a prompt like "help me turn this observation into testable hypotheses and rival explanations".
  7. Smoke-test the bundled tools from the skill folder: python3 scripts/validate_hypothesis_schema.py assets/hypothesis_record_template.json
View source on GitHub ↗License: MIT