Triage a research paper

Five questions answered in plain English so you know if it’s worth a full read.

For

Founders, PMs

Time per use

4 min

Format

.md and .skill

How to use it

1.
Open ChatGPT or Claude.
Either works. The skill is just text.
2.
Inspect the real preview, then unlock the full file.
One click; no install, no setup.
3.
Paste it as your first message.
The assistant now knows how to do this one job.
4.
Give it your specifics, get the result.
Roughly 4 min, every time you need it.

Skill filer03-triage-a-research-paper.skill.md1.0 KB

Run once

Advanced

Install permanently ↓

Mobile apps: if ChatGPT or Claude opens blank, tap the message box and paste. Skillbook copies first.

Fill the blanks first.

Add context before you run it. These fields update the preview and ChatGPT/Claude buttons instantly.

Research Question

IncludeWhat should this help you understand, decide, or verify?

Source Material

IncludePaste links, excerpts, notes, documents, screenshots described in text, or source names.

Decision Context

IncludeWho will use the answer, what decision is at stake, and what would make the output useful?

Constraints

IncludeDate range, geography, sources to prefer or avoid, citation needs, or known bias.

Install as agent behavior

Permanent agent install needs the full body.

This page is only showing a preview. Unlock the full skill to install it in Claude Code, Claude Projects, or a Custom GPT.

Unlock full skill →

# Triage a research paper

You are a skeptical research translator. I will give you a paper, abstract, link, or PDF text. Help me decide whether it deserves a full read.

## Ask first

- What decision am I using this paper to inform?
- What field is this in?
- Am I looking for truth, novelty, product ideas, investment signal, or citation material?

## Output

1. **Plain-English thesis:** one paragraph.
2. **Why this might matter:** three bullets tied to the user's decision.
3. **Evidence quality:** sample size, method, controls, baselines, and whether the claim outruns the data.
4. **What is actually new:** not what the authors hype, what changed relative to prior work.
5. **Reasons to distrust it:** conflicts, weak comparisons, missing data, overgeneralization.
6. **Triage verdict:** skip, skim, read carefully, or send to an expert.

## Rules

[Preview stops here. Unlock the Pro library for the full rules, guardrails, examples, and copyable file.]

The rest is in the Pro library.

This preview is cut from a real Pro workflow. Unlock the founding Pro library for the full file, rules, examples, and installable skill.

Full Pro file includes

✓ Input checklist
✓ Step-by-step workflow
✓ Quality bar
✓ Guardrails
✓ Output format
✓ Example run
✓ Install formats

Unlock the library →

Other things on the Research shelf

Build a competitor teardown