How to Turn Ticket Macros into a Help-Center Article

Help articles fail when they promise a 24/7 chat line or a 14-day refund that no macro authorizes. The model fills the gaps. A customer screenshots the page. Policy then has to match fiction.

The matching generator is the Help-Center Article from Ticket Macros (No Invented Policies) 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).

Treat macros as the only policy

Turn approved ticket macros into a help-center article with steps, limits, and a refuse list. No invented SLAs, refunds, or product rules. 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:

Product and surface (web, iOS, Android): [Product]
Article job (what the reader is trying to do): [Job]
Approved macros (paste verbatim): [Macros]
Audience and plan names I may use: [Audience]
In-product labels as they appear: [Labels]
Limits I can prove (counts, file types, hours): [Limits]
Out of scope / escalate when: [Escalate]
Words and promises I must not use: [Banned]
Locale and reading level: [Locale]
Last verified date: [Verified]

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.

Write steps with labels you actually have

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: every number, plan name, button label, hour window, and file type in Macros and Limits. Forbidden: anything else.
2. Title (60 chars max) and one-sentence search blurb. Print counts. No 'easy' or fake time-to-fix.
3. When this article applies / does not apply. Only Audience and Escalate.
4. Steps: numbered, one action each, using Labels exactly. If a step is not in Macros, mark MISSING and do not invent the click path.
5. Limits box: quote Limits. If a limit is missing, write not specified.
6. Still stuck: only Escalate. No invented chat hours.
7. Agent note (internal): which macros this article replaces. Do not add policy.
8. Compliance pass: quote leaks of Banned, invented SLA, or refund language. Cut them.

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.

Put limits in a box, not in cheerful prose

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:

• Macros are the policy. UI you did not see is MISSING, not guessed.
• Never invent a 24/7 promise, refund day count, or uptime percent.
• Keep Locale. Do not switch to a different language.
• Do not add screenshots you were not given.
• Last verified date is Verified. Do not change it.

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.

Escalate only the way the macros escalate

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 (help center from ticket macros, support article no invented policy, macro to help article) 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.