Repository avatar
Other Tools
v0.3.0
active

negaresh

io.github.Aricept094/negaresh

Persian (Farsi) writing rules and checks: natural sentences, grammar, orthography.

Documentation

negaresh (نگارش)

ci PyPI License: MIT

A Persian (Farsi) writing guide for AI assistants and editors. It has three parts that work together or alone:

  • A rule set: 163 rules for Iranian standard Persian. They cover sentence structure and natural word order, verb tense and mood, paragraph flow, removing translated or machine-like Persian, grammar, usage, punctuation, numbers and citations, Academy orthography (نیم‌فاصله), and meaning preservation. Each rule has a test and examples; 157 of them cite the book and page they come from (some also cite a journal article), and the other 6 are marked as editorial practice.
  • A skill (standard Agent Skills SKILL.md folder) for Claude, Codex and other agents: how to write, copyedit, proofread or naturalize (روان‌سازی) a Persian text with the rules.
  • An MCP server (stdio and Streamable HTTP) for Claude, ChatGPT, Codex, Gemini CLI, Cursor, VS Code and any MCP client: deterministic checks (Arabic letters, digits, spacing, half-spaces, quotes, variant spellings, listed calques, and sentence shapes typical of machine Persian), rule search, and validation of edits before they are applied.

راهنمای نگارش فارسی برای دستیارهای هوش مصنوعی و ویراستاران. این راهنما ۱۶۳ قاعده دارد دربارهٔ ساخت جمله، ترتیب طبیعی اجزا، زمان و وجه فعل، پیوند بندها، زدودن نثر ترجمه‌ای و ماشینی، دستور، کاربرد، نشانه‌گذاری و دستور خط فرهنگستان. یک مهارت (skill) برای Claude و یک سرور MCP محلی برای بررسی‌های مکانیکی هم دارد.

Sources

The rules were built from five books: the Academy's «دستور خطّ فارسی» (1401), Anvari and Ahmadi-Givi's «دستور زبان فارسی» 1 and 2, Arzhang's «دستور زبان فارسی امروز», and Samiee's «نگارش و ویرایش». The author bought the books, scanned them with OCR, extracted the rules, and rewrote and tuned them to the author's needs. The books are not included, and the skill and server cannot read or search them; the skill applies the rules, not the books.

Some rules also cite journal articles and editing columns: corpus studies of written and spoken Persian and of translated Persian, and published before-and-after edits. Their findings are summarized in the author's own words. A human editor checked each cited finding against the article. Full titles of the books and articles are in NOTICE.md.

What it does

TaskAsk forWhat happens
Write«این را به فارسی بنویس» / "write this in Persian"The model writes with a real subject and a finite verb for each action, no stock frames, natural order and tense.
Copyedit«ویرایش کن»Grammar, usage and spelling are fixed. Sentences with machine or translated shapes get a proposed rebuild.
Naturalize«روانش کن»، «طبیعی‌ترش کن»، «ترجمه‌ای است»Sentences and paragraphs are rebuilt from their meaning. Facts, hedges, actors, numbers and names are kept.
Proofread«غلط‌گیری کن»Characters, spacing, half-spaces, spelling and punctuation only.
Ask«این درست است؟»The rule is found and cited.

Requirements

  • For the MCP server: Python 3.11 or later and uv (uvx must be on the PATH). The server needs no network access while it runs.
  • The skill and the rule set need nothing.

Install

The server is on PyPI and in the official MCP Registry as io.github.Aricept094/negaresh. The command is the same everywhere:

uvx negaresh serve

Claude Code (plugin: skill and MCP server together)

In Claude Code:

/plugin marketplace add Aricept094/negaresh
/plugin install negaresh@negaresh

Or from a terminal:

claude plugin marketplace add Aricept094/negaresh
claude plugin install negaresh@negaresh

Claude Desktop

Add the server to claude_desktop_config.json (Settings → Developer → Edit Config) and restart the app:

{
  "mcpServers": {
    "negaresh": {
      "command": "uvx",
      "args": ["negaresh", "serve"]
    }
  }
}

For the skill, upload negaresh-skill.zip from the latest release under Settings → Capabilities → Skills.

Claude.ai

Upload negaresh-skill.zip from the latest release under Settings → Capabilities → Skills. The skill works without the server.

ChatGPT

Two ways, both in clients/chatgpt: an MCP connector in developer mode (run the server with --http behind an HTTPS tunnel), or a custom GPT with the rule files as knowledge.

Codex CLI

codex mcp add negaresh -- uvx negaresh serve

For the skill, copy skills/negaresh to ~/.codex/skills/negaresh.

Gemini CLI

gemini extensions install https://github.com/Aricept094/negaresh

Cursor

Install in Cursor, or add the JSON block above to ~/.cursor/mcp.json.

VS Code

Install in VS Code, or:

code --add-mcp "{\"name\":\"negaresh\",\"command\":\"uvx\",\"args\":[\"negaresh\",\"serve\"]}"

Any other MCP client

  • stdio: uvx negaresh serve
  • Streamable HTTP: uvx negaresh serve --http --port 8000, then connect to http://127.0.0.1:8000/mcp. Use --allowed-host <name> for a proxy or tunnel host.
  • With pip: pip install negaresh, then negaresh serve.
  • Development version from GitHub: uvx --from git+https://github.com/Aricept094/negaresh negaresh serve.

Skill only (any client that reads Agent Skills)

The skill is a standard SKILL.md folder: skills/negaresh. Copy it into the client's skills folder (~/.claude/skills/, ~/.codex/skills/, or the client's own location).

Rule set only

  • corpus/rules/*.json: the rules as JSON (one array per category).
  • docs/RULEBOOK.md: the full rule book in Persian.
  • corpus/lexicon/: variant spellings, listed expressions and sentence-shape patterns.

MCP tools

ToolUse
search_rulesFind rules by Persian or English words.
get_ruleOne rule in full.
get_profileConventions for a kind of text (academic, journalistic, literary, ...).
check_mechanicsChecks M01 to M16. It returns findings with exact offsets, candidate patches, and a low-risk auto_patch_set.
validate_patchesChecks that a set of edits applies cleanly and leaves URLs, code and other protected text unchanged.
search, fetchOver HTTP only: the search-and-read pair that ChatGPT connectors use.

All tools are read-only. The server stores no text on disk. Each call takes up to 12,000 Unicode code points.

Command line

negaresh doctor
negaresh check draft.txt --profile academic
negaresh search "نیم‌فاصله می"

Rule families

PrefixFamilyRulesMain sources
ORTOrthography and spacing44Academy «دستور خطّ فارسی» (1401)
GRMGrammar, word order, tense and mood39Anvari and Ahmadi-Givi 1 and 2; Arzhang; Samiee; corpus studies
USGUsage and calques23the three grammars; Samiee
STYStyle and sentence building19Samiee; editorial synthesis; translation studies
PUNPunctuation and characters18Samiee
TRMNumbers, dates, citations, notes, names9Samiee
INTMeaning preservation6Samiee; editorial synthesis
DSCParagraphs and discourse5Samiee

Each rule has a severity (error, convention, advisory) and an evidence class. sourced rules name the book and page they come from, and some also name a journal article; editorial_synthesis rules are editorial practice with no book behind them. The evidence class tells you how to cite a rule; the severity tells you how firmly to apply it.

Edit the rules

  1. Edit the JSON in corpus/rules/.
  2. Run python tools/build.py. It validates the corpus and regenerates the bundle, the skill references and the rule book.
  3. Run pytest.

Do not edit generated files: src/negaresh/data/corpus.json, skills/negaresh/references/rules-*.md, docs/RULEBOOK.md.

To make the release files (wheel, skill zip, clean folder): python tools/package.py.

Limits

  • The mechanical checker sees characters, listed expressions and a few sentence shapes. No finding does not mean that the prose is natural. Sentence and paragraph rebuilding is done by the model with the rules.
  • The «می» half-space check uses a closed list of verb stems.

Licence

MIT. See LICENSE.

PYPI
negaresh
Install Command
pip install negaresh