How to Write a Kobo Store Book Description with Allowed HTML
Kobo descriptions rot when they mint a 5-star block and a #1 rank. The brief had a harbor cozy and a tea tin. Stop there.
The matching generator is the Kobo Store Book Description with Allowed HTML from a Manuscript Brief (No Invented Reviews or Ranks) (Kobo Store Book Description Allowed Html From Manuscript Brief No Invented Reviews) 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).
Lock the HTML allowlist before any hook sentence
Write a Kobo store book description using only allowed HTML from a manuscript brief. No invented reviews, ranks, or bestseller claims. 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:
Manuscript brief (title, genre, logline, tropes, ending type): [Brief]
Series status I allow (standalone/book N of M or UNKNOWN): [Series]
Word count as pasted (or UNKNOWN): [Words]
Allowed HTML tags I lock: [Tags or b i br p]
Words I must not use: [Banned]
What I must never invent (reviews, ranks, awards): [Never]
Max characters for the store description: [Cap or 4000]
Output format: [Format]
Language: [Lang]
Audience I may name: [Audience]
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.
Keep series UNKNOWN if book 2 was not named
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: Brief nouns, Series, Words, Tags, Cap, Lang, Audience. Forbidden: reviews, ranks, #1, New York Times, invented blurbs.
- Tag allowlist: print Tags. Any tag not listed is forbidden in the draft.
- Description HTML: hook from logline, tropes from Brief only, series line only if Series is known. Stay under Cap. Use only Tags.
- Plain-text twin: same copy with HTML stripped. Print character counts for HTML and plain.
- Refuse list: reader quotes, star ratings, Kobo rank, Amazon rank, Goodreads score, award names not in Brief.
- Series handling: if Series is UNKNOWN, write SERIES UNKNOWN and do not invent book 2.
- Never: do not write 'bestselling' or paste a fake 5-star block.
- Compliance pass: quote Banned and Never hits. Cut them. Print counts vs Cap. 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.
Refuse reviews ranks and award lines
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:
- Kobo store description from Brief. Not a KDP A+ module and not an Amazon listing.
- Use only Tags. No script, no heading tags, no inline CSS unless listed.
- Never invent reviews, ranks, awards, or reader quotes.
- Stay under Cap characters.
- 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.
Print character counts against the cap
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 (kobo store book description, kobo allowed html tags, no invented kobo ranks) 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.