How do I install the Gpt Pro Paper Brainstormer skill?

Run npx skillmds@latest add willoscar/gpt-pro-paper-brainstormer in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Gpt Pro Paper Brainstormer safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Gpt Pro Paper Brainstormer?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Gpt Pro Paper Brainstormer free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Gpt Pro Paper Brainstormer?

WILLOSCAR (@willoscar) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Gpt Pro Paper Brainstormer by willoscar

Name: Gpt Pro Paper Brainstormer
Author: WILLOSCAR

Gpt Pro Paper Brainstormer

Use GPT Pro for research-paper brainstorming, claim sharpening, novelty analysis, related-work positioning, reviewer objections, and experiment story design. Best for algorithm/research ideas where Codex alone is too implementation-biased.

WILLOSCAR Updated Sep 17, 2026

File contents

GPT Pro Paper Brainstormer

Gather only the evidence needed to test the research claim, then ask GPT Pro to act as a skeptical research advisor.

Workflow

Clarify the raw idea and target venue level if known.
Preview the route through $gpt-pro-project-workspace. Preserve the returned Project and Thread identity, or use the standalone path when no shared Project context is needed.
Use $bundle-algorithm-context if code, experiments, docs, or logs matter.
Read references/paper_brainstorm_prompt.md, then use $gpt-pro-question-window to ask GPT Pro.
Capture the raw response and record a separate Codex verdict on the same bridge-thread-id.
Codex synthesizes:
- Strongest paper claim.
- Weakest/most vulnerable claim.
- Required experiments.
- Whether this is paper-worthy, workshop-worthy, or just engineering.

Completion criterion: claims and related-work references are marked as verified or unverified, the required experiments are concrete, and the publishability judgment is preserved separately from Codex's local verdict.

Prompt dimensions

Ask GPT Pro to cover:

One-sentence paper claim.
Problem pain and why now.
Novelty type: algorithm, data, benchmark, system, analysis, application.
Nearest likely related work clusters.
What is actually new vs rebranding.
Strongest title/abstract angle.
Experimental story.
Killer baseline and ablations.
Reviewer objections.
Minimal evidence needed to make the claim believable.
A brutally honest publishability judgment.

Codex-side caution

GPT Pro may invent related work or overstate novelty. After GPT Pro responds, Codex should mark related-work items as unverified unless it has searched or the user supplied citations.

---name: gpt-pro-paper-brainstormerdescription: Use GPT Pro for research-paper brainstorming, claim sharpening, novelty analysis, related-work positioning, reviewer objections, and experiment story design. Best for algorithm/research ideas where Codex alone is too implementation-biased.---# GPT Pro Paper BrainstormerGather only the evidence needed to test the research claim, then ask GPT Pro to act as a skeptical research advisor.## Workflow1. Clarify the raw idea and target venue level if known.2. Preview the route through `$gpt-pro-project-workspace`. Preserve the returned Project and Thread identity, or use the standalone path when no shared Project context is needed.3. Use `$bundle-algorithm-context` if code, experiments, docs, or logs matter.4. Read [references/paper_brainstorm_prompt.md](references/paper_brainstorm_prompt.md), then use `$gpt-pro-question-window` to ask GPT Pro.5. Capture the raw response and record a separate Codex verdict on the same `bridge-thread-id`.6. Codex synthesizes: - Strongest paper claim. - Weakest/most vulnerable claim. - Required experiments. - Whether this is paper-worthy, workshop-worthy, or just engineering.Completion criterion: claims and related-work references are marked as verified or unverified, the required experiments are concrete, and the publishability judgment is preserved separately from Codex's local verdict.## Prompt dimensionsAsk GPT Pro to cover:- One-sentence paper claim.- Problem pain and why now.- Novelty type: algorithm, data, benchmark, system, analysis, application.- Nearest likely related work clusters.- What is actually new vs rebranding.- Strongest title/abstract angle.- Experimental story.- Killer baseline and ablations.- Reviewer objections.- Minimal evidence needed to make the claim believable.- A brutally honest publishability judgment.## Codex-side cautionGPT Pro may invent related work or overstate novelty. After GPT Pro responds, Codex should mark related-work items as unverified unless it has searched or the user supplied citations.

Frequently asked questions