How to Build an OpenWebUI System Prompt Pack from a Role Library
OpenWebUI packs fail when they invent a model SKU and a bypass pack. Safety lines belong in every system prompt.
The matching generator is the OpenWebUI System Prompt Pack from a Role Library 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).
One pack per Roles entry
Build OpenWebUI system prompt packs from a role library you paste. No invented model SKUs or admin credentials. 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 library entries: [Roles]
OpenWebUI version I lock (or UNKNOWN): [Version]
Safety rules I require in every pack: [Safety]
Tools each role may call (or NONE): [Tools]
Words I must not use: [Banned]
What I must never invent: [Never]
Tone defaults: [Tone]
Output format: [Format]
Max system prompt words: [Max]
Starter user messages needed: [Starters]
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.
Inject Safety into every system prompt
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: Roles, Version, Safety, Tools, Tone, Max, Starters. Forbidden: SKUs, admin credentials, bypass packs.
- One pack per Roles entry: title, system prompt, starter.
- Inject Safety lines into every system prompt.
- Tools allow list only if not NONE.
- Word count under Max; print counts.
- Refuse: bypass packs and credential exfil requests.
- Version note: UNKNOWN vs locked.
- Compliance pass: cut Banned and Never. 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.
Print word counts against Max
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:
- OpenWebUI system prompt packs from Roles. Not bypass packs.
- Never invent model SKUs or admin credentials.
- Honor Max word budget with counts.
- Include Safety in every pack.
- 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 bypass packs and credential exfil
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 (openwebui system prompt pack, openwebui role library, no invented model skus) 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.