How do I install the Thinking Science skill?

Run npx skillmds@latest add carlheath/thinking-science in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Thinking Science safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Thinking Science?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Thinking Science free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Thinking Science?

carlheath (@carlheath) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Thinking Science by carlheath — Agent Skill

Name: Thinking Science
Author: carlheath

Thinking Science

Hypothesis-driven experimentation loop. Formulates testable hypotheses, designs experiments, measures results, and iterates. [WHAT] Scientific method applied to any kind of question: formulate hypotheses, identify what would falsify them, design tests, analyse results, update understanding. Works for tech, policy, strategy, and research. [WHEN] Use when: hypothesis, experiment, test the assumption, scientific method, "is it actually true that..." [EXPERTISE] Hypothesis formulation, experiment design, falsification, iterative learning

carlheath a98803e 2.9 KB Updated Sep 17, 2026

File contents

Science Protocol

Role: hypothesis-driven inquiry. Tone: rigorous but pragmatic. Hypotheses are formulated sharply, tests are designed realistically.

Method

Phase 1: hypothesis formulation

Rule: at least 3 competing hypotheses. A single hypothesis invites confirmation bias. Three hypotheses force discriminating experiments.

Formulate H1, H2, H3 as rival explanations (not variants of the same)
Formulate H0 (null hypothesis — no effect / random)
For every Hi: what would FALSIFY it? (Popper test)
Scale: anecdotal (1 observation) → pattern (3-5) → statistical (n>30) → causal (controlled experiment)
Define a success criterion per level

Phase 2: experiment design

What data / evidence is needed?
How is it collected? (search, computation, code test, interview, etc.)
What confounders exist?
What is the minimum viable test?

Phase 3: execution

Run the experiment
Document results objectively
Note unexpected observations

Phase 4: analysis

Do the results support H1 or H0?
How strong is the support? (anecdotal → statistical)
What new questions arise?

Phase 5: iteration

Update the hypothesis based on results
Design the next experiment if the question remains
Document what we have learned

Output format

## Science: [The question]

### Hypothesis
**H1:** [Testable hypothesis]
**H0:** [Null hypothesis]
**Falsifiable by:** [What would disprove H1?]
**Success criterion:** [What counts as support?]

### Experiment
**Method:** [How do we test?]
**Data:** [What is needed?]
**Confounders:** [What could disturb?]

### Results
[Objectively documented results]

### Analysis
**Support for:** H1 / H0 / Inconclusive
**Strength:** Weak / Medium / Strong
**Reasoning:** [Why this assessment?]

### Updated understanding
[What do we know now that we didn't before?]

### Next experiment (if relevant)
[What should be tested next?]

Rules

Hypotheses MUST be falsifiable. "AI will change society" is not testable. "AI automation reduces average handling time by >30% within 12 months" is testable.
Document results BEFORE analysis. Avoid interpreting while observing.
Be honest about the strength of support. "One Google search" is weak support. "5 independent studies" is strong.
Works equally well for code tests, policy analysis, and research questions.

---name: thinking-sciencedescription: Hypothesis-driven experimentation loop. Formulates testable hypotheses, designs experiments, measures results, and iterates. [WHAT] Scientific method applied to any kind of question: formulate hypotheses, identify what would falsify them, design tests, analyse results, update understanding. Works for tech, policy, strategy, and research. [WHEN] Use when: hypothesis, experiment, test the assumption, scientific method, "is it actually true that..." [EXPERTISE] Hypothesis formulation, experiment design, falsification, iterative learning---# Science Protocol**Role:** hypothesis-driven inquiry.**Tone:** rigorous but pragmatic. Hypotheses are formulated sharply, tests are designed realistically.## Method### Phase 1: hypothesis formulation**Rule: at least 3 competing hypotheses.** A single hypothesis invites confirmation bias. Three hypotheses force discriminating experiments.- Formulate **H1, H2, H3** as rival explanations (not variants of the same)- Formulate **H0** (null hypothesis — no effect / random)- For every Hi: **what would FALSIFY it?** (Popper test)- **Scale:** anecdotal (1 observation) → pattern (3-5) → statistical (n>30) → causal (controlled experiment)- Define a success criterion per level### Phase 2: experiment design- What data / evidence is needed?- How is it collected? (search, computation, code test, interview, etc.)- What confounders exist?- What is the minimum viable test?### Phase 3: execution- Run the experiment- Document results objectively- Note unexpected observations### Phase 4: analysis- Do the results support H1 or H0?- How strong is the support? (anecdotal → statistical)- What new questions arise?### Phase 5: iteration- Update the hypothesis based on results- Design the next experiment if the question remains- Document what we have learned## Output format```markdown## Science: [The question]### Hypothesis**H1:** [Testable hypothesis]**H0:** [Null hypothesis]**Falsifiable by:** [What would disprove H1?]**Success criterion:** [What counts as support?]### Experiment**Method:** [How do we test?]**Data:** [What is needed?]**Confounders:** [What could disturb?]### Results[Objectively documented results]### Analysis**Support for:** H1 / H0 / Inconclusive**Strength:** Weak / Medium / Strong**Reasoning:** [Why this assessment?]### Updated understanding[What do we know now that we didn't before?]### Next experiment (if relevant)[What should be tested next?]```## Rules- Hypotheses MUST be falsifiable. "AI will change society" is not testable. "AI automation reduces average handling time by >30% within 12 months" is testable.- Document results BEFORE analysis. Avoid interpreting while observing.- Be honest about the strength of support. "One Google search" is weak support. "5 independent studies" is strong.- Works equally well for code tests, policy analysis, and research questions.

Frequently asked questions