Home/Blog/How to Write Cursor Rules .mdc from a Repo Brief
Blog

How to Write Cursor Rules .mdc from a Repo Brief

P
promptstudio
How to Write Cursor Rules .mdc from a Repo Brief

Cursor rules invent bun and Playwright. Lock globs. PM UNKNOWN stays unknown.

The matching generator is the Cursor Rules .mdc from a Repo Brief (No Invented Tools) 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).

Frontmatter globs and alwaysApply

Write Cursor rules in .mdc style from a repo brief. Do not invent tools, paths, or package managers not listed. 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:

Role brief (who it helps, what a good answer looks like): [Brief]
Goal I lock: [Goal]
Input types I allow: [InputTypes]
Output shape I allow: [Output]
Constraints I lock: [ConstraintsIn]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]
Product I lock: [Product or Cursor rules .mdc]

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.

Body constraints from the brief

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:

  1. Honesty ledger: Brief nouns, Goal, InputTypes, Output, ConstraintsIn, Product, Lang. Forbidden: rulesini rules, ChatGPT Projects, API keys, extra tools.
  2. Role block: one paragraph from Brief. Product quoted.
  3. Goal block: quote Goal. Do not add extra success metrics.
  4. Input block: only InputTypes. If a file type is missing, write NOT IN INPUTS.
  5. Output block: quote Output. Do not invent a JSON schema the brief lacks.
  6. Constraints: copy ConstraintsIn. Do not add extra nevers unless Brief names them.
  7. Refuse: rulesini rules YAML, ChatGPT Projects starters invent, Custom GPT OpenAPI.
  8. Compliance pass: quote Banned and Never hits. Cut them. 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.

PM UNKNOWN when unlocked

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:

  • Cursor rules .mdc instructions from Brief. Not a rulesini rules and not a ChatGPT Project.
  • Only InputTypes named in Inputs.
  • Never invent API keys or extra tools.
  • 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.

Refuse secret keys

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 (cursor rules mdc, repo brief cursor rules, no invented tools) 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.