Skip to main content
skill CX Codex

good-hypothesis — Claude Code skill for testing hypotheses

The good-hypothesis Claude Code skill helps assess research explanations and shape hypotheses that can be tested. It loads during Explain or Test when candidate explanations seem weak.

MIT ★ 93 updated 2026-11-15

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Insilico-org/plsi --skill good-hypothesis -a claude-code
Open on GitHub

What good-hypothesis does

The skill helps judge whether a hypothesis earns its place by ruling out a possible outcome. It sorts falsifiers by what could check them: existing data, a study that can be found, or a measurement nobody has made yet.

Candidates that predict the same result should be merged; an observation that separates the remaining candidates becomes the next question. Evidence without an origin counts against a candidate, not in its favor. Leave untouched candidates open. A measurement that has not been made is a research direction, not a test.

What it helps with

  • write a falsifier that can be checked
  • merge candidates with matching predictions
  • separate a test from a measurement that does not exist yet
  • account for evidence with no known origin

Example prompts for the agent

  • Assess this explanation and name an observation that could disprove it.
  • Compare these candidates: what observation would make their predictions differ?
  • Review the evidence and leave untouched candidates open.

How to install good-hypothesis

1Skills CLI (Vercel)

npx skills add Insilico-org/plsi --skill good-hypothesis -a claude-code

2Manually: put the files in place

~/.claude/skills/good-hypothesis/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/good-hypothesis/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about good-hypothesis

How do I install good-hypothesis in Claude Code?

Run npx skills add Insilico-org/plsi --skill good-hypothesis -a claude-code. The skill file is at ~/.claude/skills/good-hypothesis/SKILL.md.

What does good-hypothesis do?

It helps judge what a hypothesis rules out and identify an observation that could falsify it. It also guides merging candidates with matching predictions and keeping untested ones open.

When does good-hypothesis load?

It loads during the Explain or Test move in research when candidate explanations seem thin.

Source text

SKILL.md · MIT
---
name: good-hypothesis
description: Use as PLSI Research Orchestrator when proposing or judging a candidate explanation in research - what makes one worth having, how to write a falsifier something can actually touch, when two candidates are really one, and when to kill or supersede. Load it from the Explain or Test move when the candidates feel thin.
---

# What makes a hypothesis worth having

The move pages say what to produce: `lab/explain` (the boring three first, `if_false`, `tested_by`, sharpening as
a new node) and `lab/test` (personal data first, the context question, closing what died). This says how to tell a
candidate that earns its place.

**A hypothesis earns its place by what it rules out.** "Something about the exposure affects sleep" excludes
nothing. "The effect is dose dependent" excludes a flat dose-response.

## The falsifier has to name something that could exist

`save` refuses a candidate with no `if_false` but cannot judge it. Three grades, and only the first two are
tests:

| Grade | The falsifier is met by | What to do |
|---|---|---|
| **cheap** | something already in the graph, or in the user's own record | test it now, at no retrieval cost |
| **reachable** | a study that exists and can be found | that is a Gather |
| **wished for** | a measurement nobody has made | **not a test.** Record it as a direction, the question that would settle it, and say in the body that nothing can touch it yet |

## Two candidates that predict the same thing are one

Ask of each pair: **what observation would come out differently between them?** If none, merge them and say so in
`dropped`. The observation that separates the survivors is the next question.

## Unattributed evidence, untouched candidates

- **Unattributed evidence counts against a candidate and not for it**: a finding with no origin may repeat one
  already counted.
- **Leave a candidate open** when nothing has touched it. Many untested candidates and no evidence means Gather was
  needed.

© Insilico-org · MIT · Insilico-org/plsi

Similar skills

SKILL.md skills catalog →

From the same set85

The whole set →
education The education Claude Code skill finds longevity medicine courses and prepares patient handouts. It activates for requests about training, CME, or a handout on a topic. CX Codex +1 ★ 93repo stars notes This Claude Code skill turns a physician’s visit notes into work items for the care team. It sorts records, follow-ups, plan changes, and patient messages by owner. CX Codex +1 ★ 93repo stars prune The prune Claude Code skill removes research notes marked retire. PLSI calls it after a research session or daily run when retired notes are forwarded. CX Codex +1 ★ 93repo stars brief Assembles a pre-visit brief for one patient. It gathers changes, data gaps, plan status, and questions ahead of an appointment. CX Codex +1 ★ 93repo stars proposal This skill for Claude Code drafts grant and project proposals from research material. It activates on requests to turn notes, findings, and field maps into a proposal. CX Codex +1 ★ 93repo stars protocol The protocol Claude Code skill turns a physician’s request and patient data into plan options with doses and predicted outcomes. It runs on a request for a specific patient’s plan or when visitprep/notes suggests a change. CX Codex +1 ★ 93repo stars activities Finds nearby activities based on a person’s goals, preferences, and limitations. It searches for sports or other things to do this week. CX Codex +1 ★ 93repo stars review A skill for Claude Code builds graded reviews of evidence on an intervention, test, or protocol. It activates when a physician asks what research supports a clinical option and can factor in one patient’s care context. CX Codex +1 ★ 93repo stars

Project sponsors

Companies that keep this analytics open