mcpField
R
research-agent-skills

research-agent-skills

github.com/kalarislabsAgent workflows7351 installsUpdated 3d ago
Repository

About research-agent-skills

research-agent-skills is an index that helps research agents select specialist skills maintained by Kalaris Labs. It guides skill choice by domain and deliverable, encourages checking availability, and emphasizes grounding claims in verified sources.

Key features

  1. 01Selects specialist skills by task
  2. 02Guidance for cross-domain research
  3. 03Checks skill availability before handoff
  4. 04Promotes source-checked claims

Use cases

  1. 01Choosing skills for a literature review
  2. 02Finding a skill set for cross-field work
  3. 03Checking specialist files before assigning work

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/kalarislabs/research-agent-skills --skill research-agent-skills

After installing, type/research-agent-skillsin Claude Code to confirm it loaded.

Bundled filesreferences/catalog.md

Details

From the project README

Research Agent Skills by Kalaris Labs

This is the collection index for the specialist research skills maintained by Kalaris Labs. It helps an agent choose the right skill for a research task.

Choose a skill

  1. Identify the research deliverable and domain. Examples include a literature review in medicine, an ML experiment, a chemistry analysis, or a physics figure.
  2. Read only the relevant section of the bundled skill index. Select the smallest set of specialist skills that covers the task.
  3. Read the selected specialists' SKILL.md files if they are available in the current agent environment. Otherwise, identify the skill names for the researcher and refer them to the repository's installation documentation.
  4. Keep claims and citations tied to checked sources. A skill's presence does not establish that an analysis or scientific claim is correct.

Use the specialist skill directly for ordinary single-domain work. This entry is useful when the request spans skills or concerns collection setup.

Before selecting skills, check:

  • Which research field and deliverable does the researcher need?
  • Is one specialist enough, or does the work cross fields?
  • Are the selected specialist folders available in this environment?

Verify the handoff

State which specialist skills you selected and why. Check that each selected skill folder contains SKILL.md before claiming it is available. This index does not replace any specialist's scripts or references.

Comments

Markdown supported