How to Write JetBrains AI Assistant Guidelines from a Repo Map
IDE assistants wander when the standing brief is a Copilot file dropped into IntelliJ. The assistant invents a Gradle task. Tests go unrun. You wanted JetBrains AI Assistant, not a generic coding prompt.
The matching generator is the JetBrains AI Assistant Guidelines from a Repo Map 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).
Name the IDE and refuse the other files
Turn a repo map into JetBrains AI Assistant guidelines and a refuse list. 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:
Repo: [Repo]
IDE: [IDE]
Build: [Build]
Tree: [Tree]
Commands: [Commands]
Libs: [Libs]
Never: [Never]
Style: [Style]
Owners: [Owners]
Banned: [Banned]
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.
Map packages from the tree you pasted
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:
- Tool lock.
- Guidelines from Tree.
- Commands only.
- Style only.
- Never list.
- Test policy.
- Three snippets.
- Compliance pass.
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.
Allow only commands that already work
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:
- Named IDE only.
- No copilot-instructions.md.
- No invented tasks.
- No credentials.
- Under 400 lines.
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.
Put a never list next to CODEOWNERS
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 (jetbrains ai assistant guidelines, intellij ai assistant repo map, ai assistant refuse list) 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.