How to Write a Data Availability Statement from a Repository List
Availability statements invent Zenodo DOIs. Identifiers only from the list.
The matching generator is the Data Availability Statement from a Repository List (No Invented DOIs or URLs) (Data Availability Statement From Repository List No Invented Dois Urls) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Map each dataset to public, restricted, or not deposited
Write a data availability statement from a pasted repository list. Never invent DOIs, accession numbers, or URLs. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Repository list (name, dataset title, identifier if any, access): [Repos]
Embargo notes I lock (or NONE): [Embargo]
License names I may print (exact list or NONE): [Licenses]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]
Max datasets: [Max]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Print a DOI only when it is in Repos
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Honesty ledger: repo count, Embargo status, Licenses status, Lang, Max. Forbidden: invented DOIs, URLs, accessions.
- Dataset map: identifier present or NOT IN INPUTS; access public/restricted/not-deposited from Repos.
- Statement: up to Max datasets. Identifier lines only if present. License line only if Licenses not NONE.
- Embargo note: quote Embargo or write NOT IN INPUTS.
- Refuse list: invented Zenodo DOIs, invented GitHub URLs, invented Dryad accessions.
- Diff notes: Banned/Never cuts.
- Access note: restricted datasets must not be described as open.
- Compliance pass: Banned/Never hits. Dataset count vs Max. Gaps list of five. Format as Format.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Do not call restricted data open
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- DAS from Repos only. Not BibTeX and not a README.
- Never invent DOIs, URLs, or accession numbers.
- Stay at or under Max datasets.
- No emojis.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Leave embargo blank when Embargo is NONE
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (data availability statement, no invented dois, repository list das) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.