How to Draft a Sphinx RST Page from a Locked TOC Stub

Sphinx pages fail when they mint .. toctree:: install.rst and .. _network-windows:. Quote the stub labels. Leave REF UNKNOWN.

The matching generator is the reStructuredText Sphinx Page from a TOC Stub (No Invented toctree or Labels) (Restructuredtext Sphinx Page From A Toc Stub No Invented Toctree Or Labels) 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 TOC labels before you write a :ref:

Draft a Sphinx RST page from a locked TOC stub. No invented toctree entries, labels, or include paths. 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:

TOC stub I lock (page title, section titles, labels I allow): [Stub]
Fact pack I may quote: [Facts]
Sphinx / docutils version I lock (or UNKNOWN): [Version]
toctree glob I allow (or NONE): [Toctree]
Words I must not use: [Banned]
What I must never invent (toctree entries, labels, include paths): [Never]
Output format: [Format]
Language: [Lang]
Max body paragraphs: [Max]
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.

Map each stub label to KEEP or leftover OTHER

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: Stub titles, labels, Facts nouns, Version, Toctree, Lang, Max, Audience. Forbidden: invented toctree, invented label, invented include.
2. Label map: each Stub label to KEEP. Labels not in Stub stay leftover OTHER. Do not mint .. _new-label:.
3. Page body: title from Stub. Sections only from Stub. Paragraphs quote Facts or write NOT IN INPUTS.
4. Cross-refs: :ref: only to labels in Stub. If a needed target is missing, write REF UNKNOWN.
5. Refuse list: AsciiDoc = heading, DITA , Markdown # headings, toctree of a page not in Toctree.
6. toctree: quote Toctree or write NONE. Do not invent install.rst.
7. Never: do not add a footnote with a DOI. Do not invent .. include:: paths.
8. Compliance pass: quote Banned and Never hits. Cut them. Count body paragraphs vs Max. 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 AsciiDoc headings and invented include paths

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:

• Sphinx RST page from Stub and Facts only. Not AsciiDoc and not Markdown.
• Never invent toctree entries, labels, or include paths.
• Stay at or under Max body paragraphs.
• 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.

Count body paragraphs against Max

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 (sphinx rst page, no invented toctree, toc stub lock) 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.