Appendix B. Prompt bank
Appendix B. Prompt bank
This prompt bank brings together the same example prompts used throughout the guide, organized by task for easy reference. Each prompt links back to the section that explains when and how to use it. Choose a prompt and adapt it to your project, naming the relevant files and adding any research decisions the agent needs to follow. You can refer to files already in the project without pasting their contents.
Download all prompts as Markdown
Set up and maintain a project: Start a new research project · Organize an existing project · Write CLAUDE.md for a project · Resume a project · Finish a session and update project context · Set global user instructions · Create a project-scaffolding skill
Define the study and gather evidence: Compare research approaches · Make the research specification explicit · Search and verify the literature · Synthesize the papers actually read · Bring approved data into the project
Build and check the analysis: Build a modular analysis workflow · Test the workflow before running the full batch · Investigate an unexpected result · Plan and run known-truth checks · Implement the analysis independently · Compare completed implementations
Use LLMs in the research: Develop an LLM labeling method · Evaluate LLM labels on a held-out test set · Assess sensitivity to prompts and LLMs · Run research tasks in fresh headless sessions
Write and revise: Trace numbers into the manuscript · Draft and assess a manuscript section · Draft a response from your decisions
Reproduce and share: Test the proposed handoff files · Review a proposed deposit
Set up and maintain a project
Start a new research project
Point the agent to: the project purpose, intended output, folder where the project should be created, and any research-group conventions.
Explanation and checks: Chapter 6: Organize your research projects.
Set up a project for the research described below. Use the existing workspace and research group conventions where available. Propose a structure suited to the deliverable, then create the agreed folders and project context files. Preserve existing files and list research decisions still needed from me.
Organize an existing project
Point the agent to: the existing project folder and any known current or protected files.
Explanation and checks: Chapter 6: Organize your research projects.
Inspect this project and propose a clearer structure. Identify current and uncertain files before moving anything. After I approve the plan, make a recovery copy, reorganize the files, update affected paths, and save an old-to-new file map. Preserve original inputs and check that the affected outputs still reproduce.
Write CLAUDE.md for a project
Point the agent to: the project files, existing instructions, and agreed research decisions.
Explanation and checks: Chapter 7: Give the agent context for your project.
Read this project and draft a concise
CLAUDE.mdfor future sessions. Identify its purpose, current files, agreed research decisions, and unresolved questions. Point to the other project context files and include instructions to keep them current. Preserve existing authored guidance and show me the proposed changes.
Resume a project
Point the agent to: the project folder and its project context files.
Explanation and checks: Chapter 7: Give the agent context for your project.
Read
CLAUDE.md(orAGENTS.md),STATUS.md, andTASKS.md, plus any other project context files relevant to the next task. Then inspect the inputs and outputs needed for that task. Summarize the current work, flag any disagreement between the project context files and the work saved on disk, and identify the next action.
Finish a session and update project context
Point the agent to: the current session’s work, checked outputs, and unresolved questions.
Explanation and checks: Chapter 7: Give the agent context for your project.
Update
TASKS.mdandSTATUS.mdfrom the work and outputs actually checked. For scientific changes I approved, updateSPECIFICATION.mdand add dated entries at the top ofMETHODOLOGY.mdexplaining the decisions, reasons, and specification changes. Preserve earlier entries. Leave unfinished work and failures explicit, with enough information for the next session to continue.
Create a project-scaffolding skill
Point the agent to: an agreed project layout, setup instructions, and the folder where the agent should save the skill.
Explanation and checks: Chapter 9: Use skills for recurring tasks.
Write a reusable
SKILL.mdfor the project setup we have agreed. Have it ask for the new project’s purpose and where its folder should be created, follow the relevant layout conventions, preserve existing files, and leave missing research decisions as questions. Include checks of the created folders and records. Try it on a new project folder and report the result.
Define the study and gather evidence
Compare research approaches
Point the agent to: the research question, available data, constraints, and any verified sources.
Explanation and checks: Chapter 10: The example research project.
Using the research question, available data, and constraints below, compare plausible analysis approaches. Explain what each would estimate, the assumptions it requires, and what evidence supports or challenges it. Separate verified sources from suggestions to investigate. Identify decisions needed from me before turning the chosen approach into an analysis specification.
Make the research specification explicit
Point the agent to: your research decisions and the questions that still need resolution.
Explanation and checks: Chapter 10: The example research project.
Write
SPECIFICATION.mdfrom my research decisions: estimands, target population and analysis sample, comparisons, estimator, sample rules, inputs, uncertainty, and outputs. State any averaging or standardization explicitly. Include prescribed checks and tolerances. Flag unresolved choices for my review before fitting.
Search and verify the literature
Point the agent to: the research question, eligibility criteria, and any existing search protocol.
Explanation and checks: Chapter 11: Find and assess research literature.
Search OpenAlex, PubMed, and other relevant research databases using the question and criteria in
SPECIFICATION.md. Use Crossref, other DOI registries, or publisher records to verify each journal article’s DOI, title, authors, and year. Flag mismatches and papers without a verified DOI. Record the services searched, exact queries, dates, screening decisions, and access gaps. Save verified references separately from unverified leads, and distinguish abstracts from full texts you actually read.
Synthesize the papers actually read
Point the agent to: verified papers, records of what was read, and the question to address.
Explanation and checks: Chapter 11: Find and assess research literature.
Using the verified papers and reading records, summarize the evidence relevant to our research question and proposed method. Link each substantive claim to the source and passage that supports it. Distinguish study design, population, estimand, and limitations; report disagreements and missing evidence. Do not infer full-text findings from an abstract or fill gaps from memory.
Bring approved data into the project
Point the agent to: approved inputs, their documentation, and the current scientific specification.
Explanation and checks: Chapter 12: Bring data into the project.
Inspect the research data and documentation. Record each source, version or acquisition date, permitted use, and checksum. Preserve the originals. Write checks for the variables, identifiers, units, ranges, and missingness rules in
SPECIFICATION.md. Report discrepancies before using the data in an analysis. Do not substitute synthetic observations for missing research inputs.
Build and check the analysis
Build a modular analysis workflow
Point the agent to: SPECIFICATION.md, the research data and documentation, and any existing analysis code and results.
Explanation and checks: Chapter 13: Build a modular analysis workflow.
Read
SPECIFICATION.mdand propose independently runnable analysis steps, identifying the inputs and saved outputs for each. Implement the structure using shared functions where appropriate. If analysis code already exists, first run it and save its code and results for comparison. After reorganizing it, use the same inputs to compare sample membership, estimates, and uncertainty intervals. Investigate and report unexpected differences before proceeding.
Test the workflow before running the full batch
Point the agent to: the workflow code, input data and documentation, SPECIFICATION.md, and the intended full batch.
Explanation and checks: Chapter 13: Build a modular analysis workflow.
Run a small, complete test of this workflow before starting the full batch. Check that every step receives the expected inputs and saves usable outputs. Add automatic checks based on
SPECIFICATION.mdand the data documentation. Fix implementation errors and repeat the test. Once it passes, run the full batch and report any failures.
Investigate an unexpected result
Point the agent to: the unexpected result, specification, current code, and saved outputs.
Explanation and checks: Chapter 13: Build a modular analysis workflow.
Investigate the unexpected result identified below using
SPECIFICATION.md, the current code, and saved outputs. Examine possible explanations in the data, code, and statistical model, and report the evidence for each. Preserve the original analysis. Propose any justified sensitivity analysis for my decision. After approval, updateSPECIFICATION.md, record the decision and reason inMETHODOLOGY.md, and compare the original and revised results for the specified quantities.
Plan and run known-truth checks
Point the agent to: the specification and scientific scenarios or performance questions to examine.
Explanation and checks: Chapter 14: Test the analysis against known truth.
Using
SPECIFICATION.md, propose simulation scenarios relevant to this study and performance measures for the prescribed estimator. Explain how each dataset will be generated and how the true quantities will be calculated independently of the fitting code. Check that the generator produces plausible values and variability. After I approve the simulation specification, test one complete run, then evaluate repeated datasets in each scenario without changing the estimator. Save estimates, intervals, and failed runs; report performance and its Monte Carlo uncertainty. Keep simulation files separate from the primary analysis and propose any methodological changes for my decision.
Implement the analysis independently
Point the agent to: the fixed specification, data dictionary, approved input files, and assigned language.
Ask the current agent to prepare two fresh headless sessions, each receiving the prompt below without access to the other implementation or its results. Share original data when checking processing; an already verified dataset can be shared for a narrower analysis check.
Explanation and checks: Chapter 15: Check the agent with independent implementations.
Working only from the supplied
SPECIFICATION.md, data dictionary, and approved input files, independently implement the prescribed analysis in the assigned language. Do not consult another implementation’s code or results, or use intermediate files it produced beyond the shared inputs explicitly approved for this check. Stop and ask about missing inputs or ambiguous requirements. Save the code, input-file checksums, included record identifiers, derived variables, model terms, and labeled full-precision estimates and uncertainty calculations.
Compare completed implementations
Point the agent to: both completed implementations, their outputs, and the common specification.
Ask the current agent to launch a separate fresh headless session for this comparison and give it the prompt below.
Explanation and checks: Chapter 15: Check the agent with independent implementations.
Compare the completed implementations against the shared
SPECIFICATION.mdand agreed tolerances. Work from input-file checksums and included records through exclusions, derived variables, model terms, fitted results, and reported quantities and uncertainty. Use full-precision values. Save an agreement-and-discrepancy table and identify the earliest stage at which each difference appears. Investigate its cause against the specification and source data; do not treat either implementation as the answer key or change outputs merely to make them agree. Report unresolved issues and proposed corrections, distinguishing code errors from scientific decisions that need my approval.
Use LLMs in the research
Develop an LLM labeling method
Point the agent to: the research question, development material, reviewed human examples, candidate LLMs, and participant or document identifiers for keeping related excerpts together.
Explanation and checks: Chapter 16: Use LLM outputs as research data.
Using the research question, development material, and reviewed human examples, help develop a rubric and prompt for the labeling task. Identify ambiguous cases and category definitions that need my decision. Compare the agreed candidate prompts and LLMs on development material only, reporting category-specific errors and cases requiring human review. Keep all excerpts from the same participant or document together when assigning material to development and test sets. Do not inspect the test set while selecting the method. Save the candidate versions and comparisons, then record the chosen rubric, prompt, LLM settings, and final-test criteria in
SPECIFICATION.mdafter my approval.
Evaluate LLM labels on a held-out test set
Point the agent to: the fixed rubric, prompt, LLM settings, held-out test excerpts, groups to compare, and acceptance criteria. Keep the reviewed human labels unavailable to the LLM during labeling.
Explanation and checks: Chapter 16: Use LLM outputs as research data.
Apply the fixed rubric, prompt, and LLM settings to the held-out test excerpts without supplying their human labels to the LLM. Save each raw response, the label extracted from it, failed requests, and cases requiring human review. Then compare the labels with the reviewed human reference. Report a confusion matrix, uncertainty in error rates, differences across the specified groups, and remaining human review. Assess the acceptance criteria supplied before the run. Do not revise the labeling method using this test set or omit difficult cases.
Assess sensitivity to prompts and LLMs
Point the agent to: the fixed research question and rubric, agreed variations to compare, designated development or final-analysis material, and the code producing research estimates.
Explanation and checks: Chapter 16: Use LLM outputs as research data.
Using the agreed comparisons, keep the research question and category definitions fixed while varying prompt wording, example order, LLM choice, or generation settings. Repeat requests with unchanged settings to assess ordinary run-to-run variation. Report which labels change and how those changes affect the research estimates, including relevant group comparisons. Compare errors where human reference labels are available. Use development material when the comparisons will guide method selection; keep prespecified analyses of final estimates separate. Save every configuration and response. Do not select a method because it produces a preferred research finding, and do not interpret stable labels as evidence of accuracy.
Run research tasks in fresh headless sessions
Point the agent to: the research protocol, fixed instructions, assigned input for each case, and permitted files, tools, and services.
Explanation and checks: Chapter 16: Use LLM outputs as research data.
Prepare one fresh headless session per case, using the supplied research protocol and fixed instructions. Give each session its assigned input without conversation history from other cases. Configure and check which files, tools, and services it can access; report any access you cannot verify. Run a few cases through requesting and saving responses before launching the full collection. Save each case’s inputs, raw response, failures, retries, LLM identifiers, and settings. Keep response collection separate from analysis so the saved outputs can be analyzed again without new LLM calls.
Write and revise
Trace numbers into the manuscript
Point the agent to: the rendered manuscript and saved results, including tables and figure sources.
Explanation and checks: Chapter 18: Write and revise the manuscript.
Create a chain of evidence linking each main manuscript result to its saved source file, exact entry, and analysis run. Record where it appears, including the abstract, tables, and captions, and save source checksums to detect changes. Compare the final document with those results, checking contrasts, samples, values, units, signs, intervals, and rounding. Propose updates to affected passages and identify unsupported claims for my decision.
Draft and assess a manuscript section
Point the agent to: the section to draft, research decisions, verified sources, results, and writing guidance.
Explanation and checks: Chapter 18: Write and revise the manuscript.
Draft this section from the supplied research decisions, verified sources, and saved results. Follow my writing conventions. Mark unsupported claims, numbers, and references as gaps. Identify weaknesses in the argument and propose alternatives separately for my consideration. Describe the analysis that actually ran; do not present planned work as completed or change the scientific interpretation without agreement.
Draft a response from your decisions
Point the agent to: reviewer comments, your decisions, and the revised manuscript and analysis records.
Explanation and checks: Chapter 18: Write and revise the manuscript.
Draft the reviewer response from the supplied comments, my decisions, the revised manuscript, and completed analysis outputs. Quote each comment, lead with the substantive answer, and cite the actual locations of changes. Distinguish analyses from wording edits. Do not add concessions I did not make or claim unfinished work is complete. Flag unresolved comments and decisions.
Reproduce and share
Test the proposed handoff files
Point the agent to: the proposed archive/ folder or zipped copy, its README and input list, the saved results to reproduce, and comparison tolerances.
Explanation and checks: Chapter 19: Reproduce and hand off the research.
Copy
archive/into a temporary test directory outside the working project, or extract the exact zip file proposed for sharing there. Set up a separate software environment and a fresh headless agent session whose file access excludes the working project. Have that agent follow the suppliedREADMEusing only the supplied files, listed inputs, and documented commands. Restore the recorded software versions without upgrading them. Compare rebuilt outputs with the supplied results using the agreed tolerances. Report missing files or instructions rather than filling gaps from the working project. Record failures and untested steps; do not alter the analysis or comparison criteria to force agreement.
Review a proposed deposit
Point the agent to: the exact files proposed for sharing, the manuscript, reproduction report, and sharing requirements.
Explanation and checks: Chapter 19: Reproduce and hand off the research.
Review the exact contents of
archive/proposed for sharing against the manuscript, reproduction report, and sharing requirements. Identify confidential material, credentials, personal paths, missing files, and incomplete access instructions, including in any supplied version history. Check contributors, licenses, AI disclosure, and the manuscript version. Explain how proposed exclusions affect reproduction. Propose corrections without uploading, deleting files, or rewriting history.