The scientist's guide to prompting.
Most people treat AI like a search engine. That is a mistake. To get real value from these tools you need to see prompting as a hierarchy that ranges from simple questions to multi-page workflows simulating an expert employee. This page lays out the levels and ships a library of reusable mega-prompts the lab uses for manuscript review, grant writing, coding, and teaching.
The hierarchy of complexity
"The search replacement"
Goal: quick info retrieval.
Example: "What is a Hidden Markov Model?"
Value: low. It saves a Google search but adds no intellectual depth.
"The intern"
Goal: execute a specific job.
Example: "Edit this paragraph to be punchier. Do not change the meaning."
Value: medium. Saves time on tedious tasks like coding snippets or abstract edits.
"The mega-prompt"
Goal: simulate a senior colleague.
Example: uploading a full manuscript with a five-page rubric and requesting a section-by-section critique against specific journal guidelines.
Value: high. This is where AI genuinely transforms research productivity.
The mega-prompt library
A repository of algorithmic workflows: multi-stage instructions that force AI models to simulate expert roles. How to use them: follow each link to view the prompt text. Paste the entire block into a large-context model (a top-tier ChatGPT, Claude, or Gemini). Follow any upload instructions carefully. Where available pick the "thinking" variant, and prefer paid tiers for more compute. TAMU affiliates have access via chat.tamu.ai.
Research and writing Scientific method engines Manuscript review, reviewer responses, lay summaries, grants.
- The Manuscript Audit Acts as an expert editor. Reviews the paper and explains what needs to change. Think of it as a kind peer reviewer.
- The "Response to Reviewers" Diplomat (coming soon) Takes raw, angry author comments and Reviewer 2's critique, then outputs a table with the sandwich method (Agree, Refute with evidence, Fix).
- The Lay Summary Translator (coming soon) Converts dense genomic abstracts into 8th-grade-reading-level press releases, flagging jargon like "heterozygosity."
- The DDIG / Small Grant Architect (coming soon) Builds the narrative arc for a Dissertation Improvement Grant, ensuring the budget justification aligns with experiments.
- The Literature Gap Analyzer (coming soon) Takes 5 to 10 abstracts and identifies the knowledge conflict a new paper would resolve.
Code and data science Reproducibility engines Coding style, R packages, bioinformatics pipelines, figure polish.
- The Coding Assistant Fine-tunes LLM behavior for coding. Pushes base R, encourages the model to catch subtle errors, and stops it from assuming the user is a novice.
- The R Package Standardizer (coming soon) Refactors a loose folder of R scripts into a formal R package structure (DESCRIPTION, NAMESPACE, Roxygen2 docs).
- The Bioinformatics Pipeline Auditor (coming soon) Reviews Bash or Nextflow pipelines for reproducibility gaps (missing versions, hard-coded paths).
- The ggplot2 Publication Polish (coming soon) Enforces Evolution or Systematic Biology formatting (font sizes, colorblind palettes, axis limits).
- The SQL / Database Schema Builder (coming soon) Designs a normalized relational schema for field-collection data to prevent data rot.
- The Phylogenetic Methods Critic (coming soon) Checks Methods sections for missing parameters in Bayesian or likelihood analyses (priors, burn-in, bootstrap replicates).
Teaching and mentoring Pedagogy engines Syllabi, rubrics, Socratic tutors, letters of rec.
- The CUREs Class Syllabus Generator (coming soon) A 14-week backward-design workflow aligning weekly wet-lab deliverables with Bloom's Taxonomy learning objectives.
- The Rubric Constructor (coming soon) Generates a fair, point-based rubric for subjective assignments (posters) to standardize TA grading.
- The Socratic Tutor Generator Consumes a topic (e.g., "Coalescent Theory") and produces a script that quizzes the student iteratively instead of giving answers.
- The Letter of Rec Drafter (coming soon) Drafts non-generic letters that highlight specific traits (resilience, troubleshooting) for med school vs. grad school based on your notes.
Graduate student survival Stress-test engines Quals simulators, IACUC, thesis formatting, poster pass.
- The Quals Committee Simulator Acts as the PhD committee, with knowledge of backgrounds, and simulates a committee meeting.
- The IACUC / IRB Protocol Writer (coming soon) Drafts "Search for Alternatives" and "Justification of Animal Numbers" sections from a brief experiment description.
- The Thesis Formatting Automator (coming soon) Checks a document against the specific formatting guidelines of the TAMU Office of Graduate Studies.
- The Poster Narrative Streamliner (coming soon) Cuts text-heavy conference posters down to bullet points and visual cues, focusing on the three-second hook.
Career and administration Bureaucracy engines Industry resumes, interview prep, cover letters, conflict email.
- The CV to Industry Resume Translator Translates academic "Dissertation Research" into industry-speak "Project Management" and "Data Analytics" for biotech jobs.
- The Talk Heckler Generates the five most likely gotcha questions a senior faculty member would ask during a tenure-track job interview.
- The Conflict Resolution Emailer (coming soon) Drafts professional, boundary-setting emails to decline committee requests or address authorship disputes without burning bridges.
- The Cover Letter Tailor Analyzes a specific journal's aims and scope and rewrites the "Why this journal" paragraph to match the house buzzwords.
Lab management Safety engines SOPs, equipment grant justifications, safety audits.
- The SOP Generator (coming soon) Converts messy lab-notebook scribbles into a formal, step-by-step Standard Operating Procedure with safety warnings.
- The Equipment Grant Justification (coming soon) Writes the "Need" section for instrumentation grants, focusing on broader departmental impact.
- The Safety Audit Checklist (coming soon) Generates a custom lab safety inspection checklist based on the specific chemicals and organisms in your inventory.
Prompting is a hierarchy. Level 1 saves a Google search. Level 3 gives you a second opinion from a simulated senior colleague at 2 a.m. the night before submission.
Contribute
Community library Add a mega-prompt that saved your thesis Email the lab; we will fold it into the library.
Have a mega-prompt that saved your thesis or turned a bad afternoon into a good one? Send it to blackmon@tamu.edu and we will add it to the library with credit.