Salsi logo

Salsi

Community
pooooooriya
salsi

Write Persian with Persian words. Use when writing, editing, translating or reviewing Persian (Farsi) prose — articles, documentation, posts, essays, UI copy — to replace loanwords with Persian equivalents while leaving technical terminology, proper nouns and code untouched. Also use when the user asks for پارسی سره, سره‌نویسی, فارسی‌سازی, or "make this text more Persian".

Overview

Publisherpooooooriya
Repositorysalsi
Skill namesalsi
Stars
91
Forks
5
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by pooooooriya on GitHub. Read the source before you install it.

Installation

Install the Salsi AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/pooooooriya/salsi/tree/main/skills/salsi
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/pooooooriya/salsi.git /tmp/salsi
mkdir -p .claude/skills
cp -r /tmp/salsi/skills/salsi .claude/skills/salsi
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Salsi in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Salsi on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Salsi is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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:

    bash
    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

LevelWhat it offersUse it for
safeOnly the curated, settled replacementsAutomation, first pass, anything you cannot review
standard (default)Everything except naturalised and protected wordsNormal editing with review
pureThe full lexiconسره‌نویسی, only on request

Commands

bash
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.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Salsi AI skill do?

Write Persian with Persian words. Use when writing, editing, translating or reviewing Persian (Farsi) prose — articles, documentation, posts, essays, UI copy — to replace loanwords with Persian equivalents while leaving technical terminology, proper nouns and code untouched. Also use when the user asks for پارسی سره, سره‌نویسی, فارسی‌سازی, or "make this text more Persian".

Why use Salsi on TypingMind?

Because you install it once and use it with any model. Salsi is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Salsi in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pooooooriya/salsi/tree/main/skills/salsi. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Salsi?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Salsi?

As many as you like. As long as a model supports skills, you can use Salsi with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Salsi AI skill free?

Yes. It is published on GitHub by pooooooriya under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇