Research Brief: Agent Skill (SKILL.md) for Claude Code, Codex and Cursor
Researches a question on the web and writes a one-page brief with a source for every claim.
Prompt
Installs to .agents/skills/research-brief-agent-skill-skill-md-for-claude-code-codex-and-cu/
mkdir -p .agents/skills/research-brief-agent-skill-skill-md-for-claude-code-codex-and-cu && curl -sL "https://prompts-gpt.com/prompts/research-brief-agent-skill-skill-md-for-claude-code-codex-and-cursor/raw" -o .agents/skills/research-brief-agent-skill-skill-md-for-claude-code-codex-and-cu/SKILL.md---
name: research-brief
description: Researches a question on the web and writes a one-page brief with a source for every claim. Use when asked to research, compare options, or summarize what's known about a topic.
---
# Research brief
## Steps
1. Restate the question and list 3–5 sub-questions that would answer it.
2. Search for each sub-question. Prefer primary sources (docs, filings, papers, official posts) over aggregators.
3. Read the best 2–3 sources per sub-question. Note dates; flag anything older than 12 months.
4. Write the brief: a three-sentence answer, a findings section with one bullet per claim and its link, then open questions.
## Rules
- Every factual claim gets a link. No link, no claim.
- Say "unverified" when only one secondary source supports something.
- Keep it to one page.
See [references/TEMPLATE.md](references/TEMPLATE.md) for the layout.Example output
Save as .claude/skills/research-brief/SKILL.md in one project (or ~/.claude/skills/research-brief/ for all of them); Codex reads .agents/skills/research-brief/SKILL.md. Then ask for the job in plain words and the agent loads it. Or install with: npx skills add prompts-gpt/skills --skill research-brief. It references references/TEMPLATE.md: create those next to SKILL.md (full text on prompts-gpt.com/skills/research-brief).
Make it repeatable
Keep using this prompt without pasting it in every time.
Prompt details
- By
- Prompts-GPT editors
- Published
Did this prompt work?
Keep exploring
More like this
Grill The Plan: Agent Skill (SKILL.md) for Claude Code, Codex and Cursor
Interviews you about a plan one question at a time, with a recommended answer for each, until every design decision is resolved, then writes a decision log and a one-page plan.
Build a Verification Checklist for AI Answers and Their Citations
Paste any AI-generated answer and get a table of every claim and citation, rated by risk, with red flags and the exact check needed to verify each one.
Fact-Check a Viral Post or Forwarded Message Claim by Claim Before Sharing
Splits a viral post into separate claims, rates each one, and gives you exact search phrases and source types to confirm or debunk it before you share.
Trace a Quote or Claim Back to Its Original Source Step by Step
You get a step-by-step research trail with exact search strings, misattribution red flags, and clear criteria for deciding whether a quote is confirmed, misattributed or unverifiable.
Build a Literature Review Matrix from Pasted Abstracts with Gaps and Contradictions
Paste your abstracts and get a study-by-study table of method, sample, finding and limitation, plus themes, disagreements between studies, and untested research questions.
Design a Bias-Checked Survey Where Every Question Informs a Decision
You get a short questionnaire in a table, with each question tied to a decision, a bias check for leading, double-barreled or loaded wording, and a list of cut questions.
- Draft a Research Methodology Section with Justified Design and Validity Threats
- Long PDF to Key Claims With Page References and Evidence Strength
- Source Credibility Check with Claim-by-Claim Verification Plan
- Research Question Narrower for Student Assignments
- Paper Breakdown for Students with Seminar Questions
- Pre-Interview Company Brief with Dated News and Smart Questions