# Prompts for Science and research

Prompts for Science and research: what each one does, an install command and example prompts.

37 cards

- HTML: https://affpapa.org/en/nevibecode/prompts/topic/science
- Instructions for agents: https://affpapa.org/en/nevibecode/agents.md

- [LLM Researcher](https://affpapa.org/en/nevibecode/prompts/llm-researcher.md) — prompt · aiqwe · ChatGPT, Claude.ai, Claude Code · ★ 178201 repo stars — LLM Researcher — a prompt that puts the model in the role of a large language model researcher: hand it a paper or a term, then ask your questions.
- [Scientific Data Visualizer](https://affpapa.org/en/nevibecode/prompts/scientific-data-visualizer.md) — prompt · devisasari · ChatGPT, Claude.ai, Claude Code · ★ 178201 repo stars — Scientific Data Visualizer is a prompt for ChatGPT and Claude.ai that configures the model as a scientific data visualization specialist.
- [spawn_agent](https://affpapa.org/en/nevibecode/prompts/spawn-agent.md) — prompt · wangzan101 · Claude Code, ChatGPT · ★ 9488 repo stars — The spawn_agent Claude Code prompt sends a child agent to investigate a bounded question.
- [verify_claim](https://affpapa.org/en/nevibecode/prompts/verify-claim.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The verify_claim Claude Code prompt checks a claim from a clinical research report against primary sources.
- [trial_checklist_worker](https://affpapa.org/en/nevibecode/prompts/trial-checklist-worker.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The trial_checklist_worker Claude Code prompt analyzes one clinical trial against a fixed question group.
- [论文精读](https://affpapa.org/en/nevibecode/prompts/item-036ec3b0.md) — prompt · cnfjlhj · Claude Code, ChatGPT · ★ 475 repo stars — 论文精读 is a Claude Code prompt for reading English academic papers paragraph by paragraph, preserving the original text and providing a scholarly Chinese translation and analytical commentary.
- [seeds](https://affpapa.org/en/nevibecode/prompts/seeds.md) — prompt · saideao · Claude Code, ChatGPT · ★ 159 repo stars — The seeds Claude Code prompt derives fresh research directions from gaps in the literature.
- [plan_queries](https://affpapa.org/en/nevibecode/prompts/plan-queries.md) — prompt · saideao · Claude Code, ChatGPT · ★ 159 repo stars — The plan_queries Claude Code prompt turns a rough research idea into English search queries.
- [02a-empirical-reality-check](https://affpapa.org/en/nevibecode/prompts/02a-empirical-reality-check.md) — prompt · franklee16 · Claude Code, ChatGPT · ★ 240 repo stars — 02a-empirical-reality-check audits real-world market assumptions prior to economic modeling, validating institutional claims against live web sources.
- [10-manuscript-skeleton](https://affpapa.org/en/nevibecode/prompts/10-manuscript-skeleton.md) — prompt · franklee16 · Claude Code, ChatGPT · ★ 240 repo stars — The 10-manuscript-skeleton prompt turns earlier economics research outputs into a manuscript outline, covering the abstract, model, results, proofs, discussion, and revisions.
- [trial_checklist_condense](https://affpapa.org/en/nevibecode/prompts/trial-checklist-condense.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The trial_checklist_condense Claude Code prompt condenses one clinical trial’s item-level analysis into a report and a searchable card.
- [sim_spec](https://affpapa.org/en/nevibecode/prompts/sim-spec.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The sim_spec Claude Code prompt turns assembled trial evidence into a parameter sheet for a Monte Carlo model.
- [write_proposal](https://affpapa.org/en/nevibecode/prompts/write-proposal.md) — prompt · saideao · Claude Code, ChatGPT · ★ 159 repo stars — write_proposal is a prompt for Claude Code and ChatGPT that turns a research idea into a proposal for review by other models, outlining an experiment and open questions.
- [screen](https://affpapa.org/en/nevibecode/prompts/screen.md) — prompt · saideao · Claude Code, ChatGPT · ★ 159 repo stars — This prompt for Claude Code screens papers using their titles and abstracts.
- [18-writeup](https://affpapa.org/en/nevibecode/prompts/18-writeup.md) — prompt · franklee16 · Claude Code, ChatGPT · ★ 240 repo stars — 18-writeup drafts academic research papers in LaTeX across 12 focused passes, grounding every claim in workspace evidence without guessing.
- [sim_finalize](https://affpapa.org/en/nevibecode/prompts/sim-finalize.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The sim_finalize prompt for Claude Code prepares a report on an accepted clinical-trial simulation.
- [sim_critic](https://affpapa.org/en/nevibecode/prompts/sim-critic.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The sim_critic Claude Code prompt audits a Monte Carlo clinical-trial model against its evidence, code, results, and report.
- [mine_gaps](https://affpapa.org/en/nevibecode/prompts/mine-gaps.md) — prompt · saideao · Claude Code, ChatGPT · ★ 159 repo stars — The mine_gaps Claude Code prompt maps a research field and identifies gaps supported by paper notes.
- [meta_review](https://affpapa.org/en/nevibecode/prompts/meta-review.md) — prompt · saideao · Claude Code, ChatGPT · ★ 159 repo stars — The meta_review prompt for Claude Code and ChatGPT assesses whether a proposed research project can be carried out.
- [sim_build](https://affpapa.org/en/nevibecode/prompts/sim-build.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The sim_build Claude Code prompt builds and documents a Monte Carlo simulation of clinical trial outcomes.
- [sim_brief](https://affpapa.org/en/nevibecode/prompts/sim-brief.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The sim_brief Claude Code prompt guides a clinical-trial simulation and its report.
- [chair](https://affpapa.org/en/nevibecode/prompts/chair.md) — prompt · saideao · Claude Code, ChatGPT · ★ 159 repo stars — The chair Claude Code prompt combines independent reviews of a research proposal into one meta-review.
- [researcher](https://affpapa.org/en/nevibecode/prompts/researcher.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — researcher is a Claude Code prompt for answering one research question about an indication.
- [research_planner](https://affpapa.org/en/nevibecode/prompts/research-planner.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The research_planner Claude Code prompt plans the next research round for a report on a medical indication.
- [narrative_writer](https://affpapa.org/en/nevibecode/prompts/narrative-writer.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The narrative_writer prompt for Claude Code and ChatGPT builds a narrative section for a clinical-trial forecast report.
- [narrative_editor](https://affpapa.org/en/nevibecode/prompts/narrative-editor.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The narrative_editor Claude Code prompt drafts Summary and Methods sections for a clinical-trial forecast.
- [integrator](https://affpapa.org/en/nevibecode/prompts/integrator.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — integrator is a Claude Code and ChatGPT prompt that synthesizes evidence and new research answers into a cited report section, tracking source disagreements and open questions.
- [forecast_scope](https://affpapa.org/en/nevibecode/prompts/forecast-scope.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The forecast_scope Claude Code prompt sets up a probability-of-technical-success forecast for a registered clinical trial.
- [followup_triage](https://affpapa.org/en/nevibecode/prompts/followup-triage.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The followup_triage prompt for Claude Code and ChatGPT sorts researchers’ follow-up questions for another research round.
- [copyedit_section](https://affpapa.org/en/nevibecode/prompts/copyedit-section.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — copyedit_section — a Claude Code prompt revises clinical-trial forecast sections.
- [condense_trials](https://affpapa.org/en/nevibecode/prompts/condense-trials.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The condense_trials prompt for Claude Code turns clinical-trial cards into a single digest.
- [condense_part](https://affpapa.org/en/nevibecode/prompts/condense-part.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — condense_part is a Claude Code prompt that trims a clinical forecast report section to a word limit.
- [classify_trial](https://affpapa.org/en/nevibecode/prompts/classify-trial.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The classify_trial Claude Code prompt classifies clinical trial records for a specified indication.
- [card_checker](https://affpapa.org/en/nevibecode/prompts/card-checker.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The card_checker Claude Code prompt checks key figures against the sources cited in an answer.
- [apply_ledger](https://affpapa.org/en/nevibecode/prompts/apply-ledger.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The apply_ledger Claude Code prompt applies independent fact-check findings to a report section.
- [appendix_writer](https://affpapa.org/en/nevibecode/prompts/appendix-writer.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — appendix_writer — a prompt for Claude Code and ChatGPT that compiles technical simulation appendices for clinical trials.
- [style_guide](https://affpapa.org/en/nevibecode/prompts/style-guide.md) — prompt (official Anthropic) · anthropics · Claude Code, ChatGPT · ★ 654 repo stars — The style_guide Claude Code prompt sets the style and structure for clinical trial reports.

## Refine
[research](https://affpapa.org/en/nevibecode/tag/research.md) · [clinical-trials](https://affpapa.org/en/nevibecode/tag/clinical-trials.md) · [literature-review](https://affpapa.org/en/nevibecode/tag/literature-review.md) · [simulation](https://affpapa.org/en/nevibecode/tag/simulation.md) · [academic-writing](https://affpapa.org/en/nevibecode/tag/academic-writing.md) · [economics](https://affpapa.org/en/nevibecode/tag/economics.md) · [fact-checking](https://affpapa.org/en/nevibecode/tag/fact-checking.md) · [markdown](https://affpapa.org/en/nevibecode/tag/markdown.md) · [academic](https://affpapa.org/en/nevibecode/tag/academic.md) · [arxiv](https://affpapa.org/en/nevibecode/tag/arxiv.md) · [charts](https://affpapa.org/en/nevibecode/tag/charts.md) · [citations](https://affpapa.org/en/nevibecode/tag/citations.md)

## Narrow this list
Parameters: `?platform=<claude-code|codex|cursor|copilot|gemini-cli|windsurf|…>`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
