Skip to main content
skill CX Codex

ask · insilico-org — Claude Code research skill: questions and setup

This Claude Code skill turns a research direction into a question that search can settle, or breaks it into child questions. It activates when plsi research next selects ask.

MIT ★ 93 updated 2026-11-15

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

What ask does

The skill writes testable research questions as question nodes. Before a search, it checks whether evidence could exist, whether either answer is possible, whether the subject and measurement are bounded, and whether the result would change the main conclusion.

A broad direction becomes three to five questions spanning at least three angles, such as mechanism, magnitude, or harm. A narrow direction gets one question with search terms. For a direction with a named subject, the skill can run plsi research discover --about "<the subject>" to distinguish well-studied relations from candidates. Saved nodes include stakes, angle, and parent links; a claim that a topic has not been studied requires last_search with two rounds using different vocabularies.

What it helps with

  • turn a broad research direction into a searchable question
  • split a topic across distinct research angles
  • filter out questions whose answers are already known
  • record how child questions relate to a parent

Example prompts for the agent

  • Split this research direction into three to five questions from different angles.
  • Write a focused question about how a gene affects the outcome, with search terms.
  • Check which relations have been studied for the subject "<the subject>".

How to install ask

1Skills CLI (Vercel)

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

2Manually: put the files in place

~/.claude/skills/ask/SKILL.md

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

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

Questions about ask

How do I install ask in Claude Code?

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

What does ask do?

It turns a research direction into a question that search can resolve, or divides a broad topic into child questions. It saves those questions as nodes in the research graph.

When does ask split a direction into child questions?

When one research cycle cannot settle the direction, it creates three to five questions across at least three angles. For a narrow direction, it writes one question with search terms instead.

Source text

SKILL.md · MIT
---
name: ask
description: Use as PLSI Research Orchestrator when `plsi research next` says the move is `ask` - turn the top frontier direction into one question a search could settle, or split it into three to five children across different angles.
---

# Ask

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

A frontier item is a direction; a question is something a search can settle. Most of what the rest of the cycle
costs is decided here.

## 1. Four tests, before any search

A question that fails any of these is reworked, not searched.

1. **Could the evidence exist?** Something a study design could have measured.
2. **Can it come out both ways?** If one answer is already known, it is not a question.
3. **Is it bounded?** Who or what (population, system, sample), what was varied (exposure, marker,
   intervention), measured how (outcome). Without all three a finding cannot say where it came from.
4. **Does it change anything?** If either answer leaves the question in chief where it was, drop it.

For test 2, when the direction has a subject (a drug, a gene, a condition), ask the field first:

```bash
plsi research discover --about "<the subject>"
```

`well_studied` lists what the field has answered: do not write those children. `candidates` are relations
standing on a handful of papers, each with PMIDs to aim Gather at. It is optional, and it proposes only: a
relation unrelated to the question in chief is a different topic. `lab/deep-search` says what the counts
mean.

## 2. Split it, or sharpen it

**Split** when the direction is too big to settle in one cycle: three to five children, **from at least three
different angles**.

| Angle | Asks |
|---|---|
| mechanism | is there a route by which this could happen at all? |
| magnitude | how large is it, and in whom? |
| boundary | where does it stop holding — dose, age, sex, comorbidity, duration? |
| alternative | what else would produce the same observation? |
| harm | what does it cost, and to whom? |

Three siblings from one angle are three rewordings. The angles are counted and shown.

Each child records `link: decomposes` and the parent waits for them all, then rolls up into an answer. A child
of a parent that is already answered records `link: continues`. **Write `link` at creation**: it cannot be
worked out later.

**Sharpen** instead when the direction is already narrow: one question, with the search terms you will use. A
question that needs a fourth level of depth was not narrowed properly at the first. `next` gives the depth and the advisory limits (three deep, three to five wide). Go past them only for a
candidate at the depth limit whose settling question cannot be written anywhere else, and say why in the body.
Otherwise, at the limit, answer something instead of splitting again.

## 3. The gap sets the shape of the question

- **unsearched**: nobody has looked yet. The cheapest search.
- **unstudied**: we looked and found nothing. *Does it exist under any other name?*
- **unexplained**: evidence is in and nothing accounts for it. *What would account for this?* (often a sign to
  let Explain run instead)
- **unreplicated**: one independent line. *Does it replicate in a different design or population?*
- **surrogate-only**: known only through a marker. *Does the marker track the outcome that matters?*
- **disputed**: sources disagree and the context question did not dissolve it. *What differs between the two
  settings?*

## 4. Save

`nodes` of `kind: question`, each with `stakes`, `angle`, the parent and `link` where there is one, and a body of
one or two plain lines saying why this question. Claiming nothing has been studied needs `last_search` with two
rounds in different vocabularies (refusal 3).

In `expanded`, what you split and along which angles; in `open`, which children you did **not** create and why.

The frontier ranks directions by moves to a verdict, so a new question starts at the bottom. Write one when the
research needs it, not because the one in front of you is hard.

## Rules

- **Stakes is ordinal**: `high`, `some` or `low` - how much resolving it would change the answer in chief. Never
  a number.
- A question that cannot come out both ways is dropped, not ranked.
- Rewording an existing question is a **new** question; close the old one `superseded` and cite it. Titles
  never change: links are made of them.
- Keep at least one open direction that is not a continuation of the current best.

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

Similar skills

All skills for Science and research →

ask by other authors comes first.

ask Yeachan-Heo ask — a skill to route prompts through local CLIs of different models (Claude, Codex, Gemini, Cursor and others) and save results as artifacts. CX Codex +1 787installs ask buiducnhat Halts premature coding and asks targeted clarification questions one by one before any task starts. CX Codex +1 305installs ask iurykrieger Ask questions about a knowledge vault; the skill checks its graph first and expands the search when needed. CX Codex +1 ★ 111repo stars ask szarkans ask sends one question to several AI models at once and displays their direct answers side by side without merging them. CX Codex +1 ★ 25repo stars bgpt-paper-search K-Dense-AI bgpt-paper-search searches BGPT scientific papers by topic or DOI. Extracts full-text experimental evidence, reported statistics, and source provenance. CX Codex +1 2,300installs scholar-evaluation K-Dense-AI scholar-evaluation provides qualitative, evidence-traceable developmental feedback on research drafts and protocols. Audits assessment rubrics without proxy prestige metrics. CX Codex +1 2,300installs nature-reviewer Yuan1z0825 The nature-reviewer skill runs a Nature-style referee assessment of a scientific manuscript: three independent reviewer reports plus a post-review synthesis. Useful before you submit. CX Codex +1 15,400installs paper-search ykdojo paper-search searches academic papers via OpenAlex using keywords, DOI URLs, or work identifiers. Accesses over 250 million entries without requiring an API key. CX Codex +1 ★ 67repo stars literature-search-openalex google-deepmind literature-search-openalex queries the OpenAlex database to find research papers, download open-access PDFs, and collect citation metrics via a local CLI. Handy for resolving DOIs and tracking author publications. CX Codex +1 3,400installs formula-derivation wanshuiyin formula-derivation structures research notes and equations into a derivation package. Helps organize assumptions and records proof steps in DERIVATION_PACKAGE.md. CX Codex +1 589installs

From the same set85

The whole set →
assess A skill for Claude Code assesses health data through PLSI maps. It runs after new data arrives or when asked about biological age, risk markers, or trends. CX Codex +1 ★ 93repo stars apple-health This Claude Code skill connects Apple Health and sends metrics to PLSI. It activates for connection requests or imports covering a requested date range. CX Codex +1 ★ 93repo stars run This Claude Code skill preregisters a research hypothesis, runs its analysis, and prepares a finding. It starts after a researcher selects a hypothesis and PLSI relays the registration receipt and Challenger objections. CX Codex +1 ★ 93repo stars sleep This Claude Code skill reads sleep data and builds a plan around the user's request. It activates for requests to improve sleep or interpret sleep measurements. CX Codex +1 ★ 93repo stars roster This Claude Code skill maintains a physician’s patient roster and tracks each person’s status. It activates when a patient is added, paused, closed, or removed, or shares data with the physician. CX Codex +1 ★ 93repo stars arrow The arrow Claude Code skill turns a health history into a timeline of past events, current state, and forecasts. It runs when someone shares their story or asks to see their main risks on one chart. CX Codex +1 ★ 93repo stars hallmarks This Claude Code skill maps a gene, pathway, or candidate to aging hallmarks and supporting evidence. It activates for requests to assess those links and possible biomarkers. CX Codex +1 ★ 93repo stars company Builds sourced research dossiers on pharma and biotech companies. It runs for a company name or ticker, or before pharma/outlook when the dossier is older than 7 days. CX Codex +1 ★ 93repo stars

Project sponsors

Companies that keep this analytics open