Skip to main content
skill CX Codex

kol — Claude Code skill: find leaders in a topic

The kol Claude Code skill identifies researchers and groups from papers and registered trials. It runs on requests to find leading teams, collaborators, or reviewers for a topic.

MIT ★ 93 updated 2026-11-15

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

What kol does

The skill gathers paper authors and trial investigators linked to a topic. It searches public PubMed and ClinicalTrials.gov records, then ranks five to ten people or groups by recent, topic-specific work.

Each result includes the affiliation as published and verified identifiers. The output goes to <PLSI_HOME>/work/<thread>/kol.md, with the ranking rule in the summary. Searching and verification use the plsi evidence search and plsi evidence verify commands.

Only public professional records are used. The skill excludes contact details and private information, and it does not contact anyone. Its output reports counts rather than judging an individual’s quality.

What it helps with

  • find leading research groups on a topic
  • identify potential collaborators from papers and trials
  • shortlist reviewers by topic-specific work
  • compare recent research activity across groups

Example prompts for the agent

  • Find leading groups working on genome editing.
  • List possible collaborators researching rare-disease therapies.
  • Find reviewers using publications and registered trials on immunology.

How to install kol

1Skills CLI (Vercel)

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

2Manually: put the files in place

~/.claude/skills/kol/SKILL.md

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

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

Questions about kol

How do I install kol in Claude Code?

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

What does kol do?

It finds paper authors and investigators from registered trials for a given topic, ranks people or groups, and saves the results in kol.md.

What does kol need to work?

It uses the plsi evidence search and plsi evidence verify commands, along with public records of papers and registered trials.

Source text

SKILL.md · MIT
---
name: kol
description: Use as PLSI Landscape when the researcher wants to know who works on a topic - key opinion leaders and groups ranked from public publication and trial records only, for collaboration or review.
---

# PLSI key opinion leaders

**Status: draft**.

## When to use

- "Who are the leading groups on <topic>?", "possible collaborators or reviewers for <topic>".

## Steps

1. **Collect** authors and investigators from public records only: papers and registered trials on the topic.

   ```bash
   plsi evidence search --source pubmed --query "<topic>" --limit 20
   plsi evidence search --source ctgov --query "<topic>" --limit 20
   ```

2. **Rank** 5-10 people or groups by recent, topic-specific output (papers as first or last author in the last 5
   years, trials as investigator), with their affiliation as published and 2-3 verified identifiers each
   (`plsi evidence verify --kind <pmid|nct> --id <id>`).

3. **Return one `result`** with `<PLSI_HOME>/work/<thread>/kol.md` and the ranking rule in `summary`.

## Rules

- Public professional records only: no contact details, social profiles or private information, and never contact
  anyone. Output counts, not a quality judgement of a person.

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

Similar skills

All skills for Science and research →

From the same set85

The whole set →
prose Drafts academic or report prose from research notes and recorded PLSI state. It activates when PLSI requests a report section, manuscript draft, or plain-language summary. CX Codex +1 ★ 93repo stars literature The literature Claude Code skill maps research on aging topics. It searches papers and registered trials, verifies source identifiers, and records disagreements. CX Codex +1 ★ 93repo stars 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 good-hypothesis 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. 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

Project sponsors

Companies that keep this analytics open