Salsi

سالسی — Write Persian with Persian words

Persian prose is full of borrowed words that have perfectly good Persian equivalents. Replacing them makes writing clearer and more native. Replacing them carelessly makes writing wrong — it mangles technical terms, changes meaning, and produces words no reader recognises.

This skill is about the difference.

The one rule that matters

A loanword is only worth replacing when the replacement is at least as clear to the reader. Purity is never worth clarity. If you are unsure whether a reader would recognise the Persian equivalent, keep the original.

Workflow

1. Scan the text to find candidates:

   salsi scan article.md --format json
   

   If salsi is not on PATH, this skill ships its own copy — run ./bin/salsi from this skill's directory instead. It needs nothing installed beyond Python 3.10 and carries the full 20,129-word lexicon.

   Add --domain tech (or medical, legal, science, business) so the terminology of that field is protected. Add --topic <subject> to help the scanner pick the right sense of an ambiguous word.

2. Read each finding. Every one carries level, ambiguous, and a sense label per suggestion. Apply the judgement rules below. Most findings will be rejected in a technical document — that is the expected outcome, not a failure.

3. Apply with your normal editing tools, one considered change at a time. For the settled subset only, salsi apply article.md does it mechanically.

4. Show the user a diff and the reasoning before finalising. Never rewrite someone's text wholesale without showing what changed.

Only if you cannot run commands at all — no shell available — work from reference/core-words.md, which holds the settled replacements as a plain table. It is ~119 words against the lexicon's 20,129, so say plainly that you are working without the full dictionary and be correspondingly conservative.

Judgement rules

Never touch

• Anything inside code fences, inline code, URLs, file paths, commands, identifiers, or configuration keys. (salsi already excludes these; if you are working by hand, you must too.)
• Quoted text from another author, or a cited title. Quotations are evidence, not drafts.
• Proper nouns: people, places, companies, products, brands, standards bodies.
• Numbers, units, and formulas.

Technical terms — the part people get wrong

Ask what the field itself writes, not what a dictionary offers.

• Use the Persian term when the field already uses it: کامپیوتر→رایانه, دیتابیس→پایگاه داده, دانلود→بارگیری, فایل→پرونده. These read as normal technical Persian.
• Keep the loanword when it is the term of art: الگوریتم, پروتکل, کامپایلر, ای‌پی‌آی, توکن, کرنل. Translating these makes the text harder for its own audience.
• Never invent a term. If the lexicon offers something you have not seen used in that field, do not be the first to use it in someone else's document.
• In medicine, law and standards, a term can have a defined meaning. Changing it changes the content. Leave it.

Meaning first

The lexicon is keyed by spelling, not sense. Check the sense label on each suggestion before using it.

• سرور in a systems document is server, not سُرور "joy".
• استرس is تنش in mechanics but دلهره in psychology.
• تست is آزمون in science, but a تُست is bread.

When ambiguous is true, either pick the sense the context demands or leave the word alone. Never take the first suggestion because it is first.

Register and audience

• Formal, literary and cultural writing tolerates more purism.
• Technical documentation, legal text and UI copy tolerate much less: the reader is there to accomplish something, not to admire the prose.
• Casual and conversational text should stay casual. سلام، فایلو فرستادم should not become a treatise.

Craft

• Be consistent. Once you choose پرونده for فایل, use it everywhere in the document, including headings.
• Introduce once. When an unfamiliar equivalent genuinely earns its place, the first occurrence may carry the original: بارگیری (دانلود). Once.
• Fix the grammar around the change. Persian suffixes change shape: فایل‌ها→پرونده‌ها, خانه‌ای patterns, ezafe. Re-read the sentence after each edit.
• Do not increase word count much. A three-word phrase replacing one word is usually a bad trade.

When the user asks for سره‌نویسی

Full purism (--level pure) also targets Arabic loanwords that are ordinary modern Persian — کتاب, علم, قانون. Only do this when the user explicitly asks for it, and warn that the result reads as a deliberate literary style, not as neutral Persian.

Levels

Commands

salsi scan FILE [FILE...]        # --format text|json|markdown
salsi apply FILE                 # settled replacements only; --diff to preview
salsi lookup WORD                # what does the lexicon offer, and in which sense
salsi domains                    # protection profiles available
salsi info                       # lexicon size and provenance

# useful flags
--level safe|standard|pure
--domain tech|medical|legal|science|business    # repeatable
--topic "زبان‌شناسی"                            # disambiguates senses
--protect WORD / --protect-file FILE            # your own exceptions

Exit code with --strict is non-zero when anything is found, which makes salsi scan --level safe --strict usable as a CI or pre-commit check.

Reference

• reference/judgement.md — worked examples of accepting and rejecting findings
• reference/core-words.md — the settled replacements, usable without the CLI
• reference/install.md — installing salsi and this skill elsewhere

Credit

The word list and every Persian equivalent come from پاسبان (Pasban) — https://pasbans.ir. This skill is a way of using their work; it is not a substitute for it. Keep the attribution when you redistribute.