-
Outcome
Stable mixed-direction Hebrew output
Prevents dense RTL/LTR paragraphs from becoming visually unstable by isolating LTR fragments and splitting mixed-direction content into stable lines, bullets, or code blocks.
-
Component type
Prompt component
A reusable instruction block that controls output layout and directionality, not task logic or factual verification.
-
Best for
Hebrew technical responses
Use when Hebrew prose includes English technical terms, product names, filenames, paths, commands, URLs, identifiers, numbers, Markdown, or HTML snippets.
Scope and best-fit use
Use this component to stabilize Hebrew RTL output that includes LTR technical fragments. It does not translate text, verify claims, or change technical names.
-
Use when
Hebrew output mixes RTL and LTR content
Use it when a Hebrew answer includes English terms, code, URLs, file paths, commands, identifiers, numbers, punctuation, Markdown, or HTML and the visual order may become hard to read.
-
Do not use when
The output is single-direction or pure code
Do not add this component when the answer is entirely English, entirely Hebrew without LTR fragments, or a pure code/configuration block where text direction is not the issue.
Copy-ready prompt
Copy this component into the instruction layer or at the top of a Hebrew-output workflow prompt when mixed RTL/LTR formatting must stay readable.
RTL/LTR BIDI-SAFE HEBREW OUTPUT
Use this policy when responding in Hebrew and the answer includes English, code, URLs, paths, filenames, commands, numbers, product names, Markdown, HTML, or technical identifiers.
Direction rules:
- Treat Hebrew prose as RTL content.
- Treat English, code, URLs, paths, filenames, commands, numbers, and identifiers as LTR fragments.
- Keep Hebrew explanatory prose in stable RTL flow.
- Do not create dense paragraphs that repeatedly alternate between RTL Hebrew and LTR fragments.
Formatting rules:
- Wrap short LTR technical tokens in inline code.
- Put long LTR fragments, commands, paths, URLs, filenames, code, and multi-word English phrases in fenced code blocks when readability may break.
- If a Hebrew sentence contains more than two LTR fragments, split it into bullets, separate lines, or a small table.
- Do not attach RTL punctuation directly to unwrapped LTR text.
- Keep Hebrew explanations outside BEFORE / AFTER blocks, code blocks, config blocks, and copy/paste blocks.
- Preserve all technical names exactly. Change only formatting, line breaks, and layout.
HTML output rules:
- Use `dir="rtl"` for Hebrew containers when generating HTML.
- Use `dir="ltr"` for explicit LTR inline fragments when needed.
- Use `<bdi>` for unknown-direction inline content.
Plain-text limitation:
- In plain Markdown or plain text, full BiDi rendering is not guaranteed across all renderers. Prefer line splitting, inline code, fenced code blocks, and minimal mixed-direction punctuation.