Skip to main content
skill CX Codex

explain · insilico-org — Claude Code skill: what it does, how to install

A Claude Code skill for turning research findings into competing, testable explanations. It activates when plsi research next selects explain.

MIT ★ 93 updated 2026-11-15

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

What explain does

The skill turns research findings into competing hypotheses and records them in a graph. It considers chance or no effect, confounding, and measurement artifacts before moving to mechanistic explanations. Each surviving hypothesis includes an observable result that would show it is wrong.

It writes hypothesis nodes with a question, an if_false condition, and a tested_by link when the relevant question already exists. Set-aside candidates go in dropped with a reason; the skill does not issue verdicts. It needs relevant findings from next; when the search itself was wrong, the instruction is to gather instead. Node structure comes from shared/research-graph, while persona.md and shared/team provide working norms.

What it helps with

  • turn research findings into testable explanations
  • distinguish mechanisms from chance and measurement artifacts
  • state what observation would falsify a hypothesis
  • record discarded explanations and why they were set aside

Example prompts for the agent

  • Turn the findings from plsi research next into competing explanations.
  • For each hypothesis, name an observation that would show it is wrong.
  • Separate testable hypotheses from candidates that should be set aside.

How to install explain

1Skills CLI (Vercel)

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

2Manually: put the files in place

~/.claude/skills/explain/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/explain/

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

Questions about explain

How do I install explain in Claude Code?

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

What does the explain skill do?

It builds competing hypotheses from research findings, describes an observable way each could be disproved, and saves the candidates in the research graph.

How does explain handle hypotheses that cannot be distinguished?

It compares candidates in pairs. If no observation could tell two explanations apart, they are merged; each surviving hypothesis gets an observable falsifier.

Source text

SKILL.md · MIT
---
name: explain
description: Use as PLSI Research Orchestrator when `plsi research next` says the move is `explain` - put the competing accounts of the evidence on the table, the boring ones first, each with what we would see if it were false.
---

# Explain

Follow persona.md norms and `shared/team`. Owner: **PLSI Research Orchestrator**. Writes `hypothesis` nodes; the
shape is in `shared/research-graph`.

`next` has handed you the question, every finding that bears on it, and each one's `note`. Nothing here needs a
search.

Explain is due only where findings exist. Where they say nothing useful, explaining the absence is legitimate (a
tooling limit, a question nobody asked, a result only in tables this loop cannot read), and each is a falsifiable
candidate. If the honest answer is that the search was wrong, do a gather instead and save that.

When the candidates feel thin, or you cannot tell whether a falsifier is any good, read `lab/good-hypothesis`.

## 1. The boring three first, as a checklist

Before any mechanism, consider:

1. **Nothing**: chance, or no real effect.
2. **Confounding**: something else accounts for it.
3. **Artifact**: measurement, selection or reporting produced it.

Then the mechanistic candidates. Write the boring ones that are live as nodes and name the ones you dismissed in
`dropped`, with why.

## 2. Every candidate that survives the separating test, each with `if_false`

There is no fixed number. **Two candidates that no observation could separate are one** (`lab/test` §3):
run that test over every pair, merge what it catches, and keep what survives. A question that needs many more is
split in Ask, not crowded here. `next` hands back `dropped` in `already_tried`, so a set-aside candidate stays set
aside.

**Every candidate records what we would see if it were wrong** (refusal 2). An `if_false` must name something
observable: *"the symptom began before the prescription date in the user's own log"*, not *"the hypothesis would
not hold"*.

Fill `tested_by` only with a question that **already exists** (refusal 6 rejects a link to a missing node).
Otherwise leave it empty and say in the body what would settle it; Test fills the link when it creates that
question. Never point `tested_by` back at the question that proposed the hypothesis.

## 3. Sharpening, not nesting

Hypotheses do not nest. A candidate sharpened after new evidence is a **new** hypothesis under the same question,
with the old one closed `superseded` and cited. Structure lives in the question tree.

## 4. Read your way to hypotheses

A topic holds tens of findings, far too few for graph-structure hypothesis generation; candidates come from
reading the findings. The graph stops you asking the same question twice and counts what you find.

## 5. Save

`nodes` of `kind: hypothesis`, each with its `question`, `if_false`, `tested_by` where you know it, and a body of
one or two lines saying what it claims. In `dropped`, the candidates you set aside, with why.

## Rules

- You never write a verdict, and never a verdict word as a status (refusal 7).
- Do not propose a candidate nothing could test. Put it in `open` as a direction that needs a measurement nobody
  has.

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

Similar skills

All skills for Science and research →

explain by other authors comes first.

explain entireio This Claude Code skill explains why a piece of code exists. It traces a function, file, or line back to the session that produced it. CX Codex +1 625installs explain SerhiiKorniienko explain breaks down concepts from code, docs or articles at the depth you need: analogies for beginners, mechanisms for practitioners, or full deep-dives. CX Codex +1 ★ 164repo stars explain sammcj Explains code, systems, and algorithms using terminal ASCII diagrams or standalone interactive HTML step-through pages. CX Codex +1 ★ 173repo stars explain TakaGoto The explain skill teaches RAG concepts, from plain-language intuition to code and practical trade-offs. Use it to dig into topics such as embeddings, chunking, or hybrid search. CX Codex +1 ★ 30repo stars scientific-thinking Agents365-ai scientific-thinking is a skill for analyzing research findings, evaluating evidence, and constructing rigorous arguments. It separates facts from interpretations and calibrates conclusions to evidence quality. CX Codex +1 308installs research-ideation Awesome Econ AI Community research-ideation guides economists from raw observations or datasets to testable research questions. Useful when starting dissertation projects or designing policy evaluations. CX Codex +1 196installs hypothesis-generation franklee16 hypothesis-generation formulates testable scientific hypotheses from raw data and observations. Proposes mechanistic explanations, experimental setups, and quantitative predictions. CX Codex +1 ★ 240repo stars good-question franklee16 good-question is a Claude Code skill that shapes and tests research questions, hypotheses, and project ideas. It engages when a direction needs refining, a proposal is in progress, or research has stalled. CX Codex +1 ★ 240repo stars trade-hypothesis-ideator tradermonty trade-hypothesis-ideator turns trade logs, journal notes and market data into falsifiable hypotheses with experiment designs and kill criteria. CX Codex +1 3,600installs explain-diff claesbackman The explain-diff skill turns a code-change review into a standalone HTML page with a quiz. Use it to explain a diff and examine its effects on empirical results. CX Codex +1 ★ 579repo stars

From the same set85

The whole set →
trials This Claude Code skill finds clinical trials using a person’s health context, goals, and location. It activates when PLSI is asked about joining a trial or has no suitable standard option for a goal. CX Codex +1 ★ 93repo stars devices This Claude Code skill compares at-home tests and devices by validation evidence, cost, and export options. It runs when PLSI needs a device recommendation or home measurements to fill map gaps. CX Codex +1 ★ 93repo stars hevy This Claude Code skill connects PLSI to the Hevy workout log and shares training data with Coach. It runs for connection setup, checks, repairs, removal, or workout-history requests. CX Codex +1 ★ 93repo stars risks This Claude Code skill estimates a person’s main health risks from their recorded state and evidence. It runs when PLSI requests the future part of a life trajectory or a user asks about their risks. CX Codex +1 ★ 93repo stars diet This Claude Code skill builds a nutrition plan around health goals, medical conditions, allergies, and food preferences. It activates for requests about diet, weight, or eating with high cholesterol or glucose. CX Codex +1 ★ 93repo stars history The history Claude Code skill records health events from a personal story, a conversation, or another bot’s notes. It updates relevant PLSI maps and returns past events alongside the current state. CX Codex +1 ★ 93repo stars substances The substances Claude Code skill builds plans to quit or reduce smoking, vaping, or alcohol use. It checks for risks from stopping without supervision and sets a stepwise schedule. CX Codex +1 ★ 93repo stars extend extend is a Claude Code skill for adding operations to PLSI that maps and single formulas cannot handle. It comes into play when PLSI needs to read a new file format, run a more involved calculation, or search another evidence source. CX Codex +1 ★ 93repo stars

Project sponsors

Companies that keep this analytics open