Skip to content

armgit / ECC

Public Imported from GitHub
0

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

feat: integrate Bengali language support

haelyra2cc58dfa45cc
diff --cc .claude-plugin/marketplace.json
index 0e81da30d,d3b462efd..66a4ace6f
--- a/.claude-plugin/marketplace.json
+++ b/.claude-plugin/marketplace.json
@@@ -11,8 -11,8 +11,8 @@@
{
"name": "ecc",
"source": "./",
- "description": "Harness-native ECC operator layer - 67 agents, 281 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses",
- "version": "2.1.0",
- "description": "Harness-native ECC operator layer - 68 agents, 287 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses",
++ "description": "Harness-native ECC operator layer - 69 agents, 288 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses",
+ "version": "2.2.0",
"author": {
"name": "Affaan Mustafa",
"email": "[email protected]"
diff --cc .claude-plugin/plugin.json
index 2b30da1d5,8a7908d45..758d9d201
--- a/.claude-plugin/plugin.json
+++ b/.claude-plugin/plugin.json
@@@ -1,7 -1,7 +1,7 @@@
{
"name": "ecc",
- "version": "2.1.0",
- "description": "Harness-native ECC plugin for engineering teams - 67 agents, 281 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses",
+ "version": "2.2.0",
- "description": "Harness-native ECC plugin for engineering teams - 68 agents, 287 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses",
++ "description": "Harness-native ECC plugin for engineering teams - 69 agents, 288 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses",
"author": {
"name": "Affaan Mustafa",
"url": "https://x.com/affaanmustafa"
diff --cc AGENTS.md
index c2676f82a,563b4e799..40390684d
--- a/AGENTS.md
+++ b/AGENTS.md
@@@ -1,8 -1,8 +1,8 @@@
# Everything Claude Code (ECC) — Agent Instructions
- This is a **production-ready AI coding plugin** providing 67 specialized agents, 281 skills, 94 commands, and automated hook workflows for software development.
-This is a **production-ready AI coding plugin** providing 68 specialized agents, 287 skills, 94 commands, and automated hook workflows for software development.
++This is a **production-ready AI coding plugin** providing 69 specialized agents, 288 skills, 94 commands, and automated hook workflows for software development.
- **Version:** 2.1.0
+ **Version:** 2.2.0
## Core Principles
@@@ -20,6 -20,6 +20,7 @@@
| architect | System design and scalability | Architectural decisions |
| tdd-guide | Test-driven development | New features, bug fixes |
| code-reviewer | Code quality and maintainability | After writing/modifying code |
++| bengali-reviewer | Bengali text review | Unicode, normalization, grapheme, search, and locale correctness |
| security-reviewer | Vulnerability detection | Before commits, sensitive code |
| spec-miner | Brownfield spec extraction | Onboarding brownfield projects to spec-driven development |
| build-error-resolver | Fix build/type errors | When build fails |
@@@ -53,6 -54,6 +55,7 @@@
Use agents proactively without user prompt:
- Complex feature requests → **planner**
- Code just written/modified → **code-reviewer**
++- Bengali text handling changes → **bengali-reviewer**
- Bug fix or new feature → **tdd-guide**
- Architectural decision → **architect**
- Security-sensitive code → **security-reviewer**
@@@ -151,8 -153,8 +155,8 @@@ Troubleshoot failures: check test isola
## Project Structure
```
- agents/ — 67 specialized subagents
- skills/ — 281 workflow skills and domain knowledge
-agents/ — 68 specialized subagents
-skills/ — 287 workflow skills and domain knowledge
++agents/ — 69 specialized subagents
++skills/ — 288 workflow skills and domain knowledge
commands/ — 94 slash commands
hooks/ — Trigger-based automations
rules/ — Always-follow guidelines (common + per-language)
diff --cc README.md
index ad4ec0de2,1529f2c28..9fbc3fc0f
--- a/README.md
+++ b/README.md
@@@ -115,14 -128,14 +129,14 @@@ Instead of rebuilding that process in e
> Optimize the context window. Persist everything else.
- ECC is MIT-licensed open source. It works best with Claude Code today, with first-class Codex support and adapters for Cursor, OpenCode, Gemini, Zed, GitHub Copilot, Antigravity, Qwen, and other harnesses.
+ ECC is MIT-licensed open source. It works best with Claude Code today, has a supported Codex sync path, and provides capability-limited adapters for Cursor, OpenCode, Gemini, Zed, GitHub Copilot, Antigravity, Qwen, and other harnesses. See the [support status matrix](#platform-support) before assuming feature parity.
- Access to 67 agents, 281 skills, and 94 legacy command shims, plus hooks, rules, memory, continuous learning, and AgentShield security scanning. The agents are specialized for planning, review, build repair, security, architecture, and domain work.
-Access to 68 agents, 287 skills, and 94 legacy command shims, plus hooks, rules, memory, continuous learning, and AgentShield security scanning. The agents are specialized for planning, review, build repair, security, architecture, and domain work.
++Access to 69 agents, 288 skills, and 94 legacy command shims, plus hooks, rules, memory, continuous learning, and AgentShield security scanning. The agents are specialized for planning, review, build repair, security, architecture, and domain work.
| Included | Count | What it gives you |
| ---------------- | ----------: | ------------------------------------------------------------------------------------ |
- | Agents | 67 agents | Planning, review, build repair, security, architecture, and domain work |
- | Skills | 281 skills | TDD, research, security, docs, frontend, data, ML, operations, and more |
-| Agents | 68 agents | Planning, review, build repair, security, architecture, and domain work |
-| Skills | 287 skills | TDD, research, security, docs, frontend, data, ML, operations, and more |
++| Agents | 69 agents | Planning, review, build repair, security, architecture, and domain work |
++| Skills | 288 skills | TDD, research, security, docs, frontend, data, ML, operations, and more |
| Commands | 94 commands | Convenient entry points while ECC moves to a skills-first surface |
| Hooks and memory | Runtime | Enforcement, session summaries, continuous learning, instincts, and context controls |
| Rules | Selective | Always-loaded standards you choose by language or project |
@@@ -908,8 -987,8 +988,8 @@@ This repo is the raw code. The guides e
```text
ECC/
- |-- agents/ # 67 specialized subagents for delegation
- |-- skills/ # 281 reusable workflows loaded on demand
-|-- agents/ # 68 specialized subagents for delegation
++|-- agents/ # 69 specialized subagents for delegation
+ |-- skills/ # 287 reusable workflows loaded on demand
|-- commands/ # 94 maintained slash-command shims
|-- rules/ # opt-in common and language standards
|-- hooks/ # runtime automation and enforcement
diff --cc README.zh-CN.md
index 8598725c9,1d4b4a435..0270d0e0b
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@@ -23,7 -23,7 +23,7 @@@
**Language / 语言 / 語言 / Dil / Язык / Ngôn ngữ**
--[**English**](README.md) | [Português (Brasil)](docs/pt-BR/README.md) | [简体中文](README.zh-CN.md) | [繁體中文](docs/zh-TW/README.md) | [日本語](docs/ja-JP/README.md) | [한국어](docs/ko-KR/README.md) | [Türkçe](docs/tr/README.md) | [Русский](docs/ru/README.md) | [Tiếng Việt](docs/vi-VN/README.md) | [ไทย](docs/th/README.md) | [Deutsch](docs/de-DE/README.md)
++[**English**](README.md) | [Português (Brasil)](docs/pt-BR/README.md) | [简体中文](README.zh-CN.md) | [繁體中文](docs/zh-TW/README.md) | [日本語](docs/ja-JP/README.md) | [한국어](docs/ko-KR/README.md) | [Türkçe](docs/tr/README.md) | [Русский](docs/ru/README.md) | [Tiếng Việt](docs/vi-VN/README.md) | [ไทย](docs/th/README.md) | [Deutsch](docs/de-DE/README.md) | [বাংলা](docs/bn/README.md)
</div>
@@@ -192,7 -196,7 +196,7 @@@ Copy-Item -Recurse rules/typescript "$H
/plugin list ecc@ecc
```
- **完成!** 你现在可以使用 67 个代理、281 个技能和 94 个命令。
-**完成!** 你现在可以使用 68 个代理、287 个技能和 94 个命令。
++**完成!** 你现在可以使用 69 个代理、288 个技能和 94 个命令。
### multi-* 命令需要额外配置
diff --cc agent.yaml
index 3154f3421,035db0637..b126a8eb8
--- a/agent.yaml
+++ b/agent.yaml
@@@ -24,6 -24,6 +24,7 @@@ skills
- autonomous-loops
- backend-patterns
- benchmark
++ - bengali-nlp
- blueprint
- browser-qa
- bun-runtime
diff --cc docs/tr/AGENTS.md
index 91e13dc68,c9c3df215..b909a074e
--- a/docs/tr/AGENTS.md
+++ b/docs/tr/AGENTS.md
@@@ -1,8 -1,8 +1,8 @@@
# Everything Claude Code (ECC) — Agent Talimatları
- Bu, yazılım geliştirme için 28 özel agent, 116 skill, 59 command ve otomatik hook iş akışları sağlayan **üretime hazır bir AI kodlama eklentisidir**.
-Bu, yazılım geliştirme için 68 özel agent, 287 skill, 94 command ve otomatik hook iş akışları sağlayan **üretime hazır bir AI kodlama eklentisidir**.
++Bu, yazılım geliştirme için 69 özel agent, 288 skill, 94 command ve otomatik hook iş akışları sağlayan **üretime hazır bir AI kodlama eklentisidir**.
- **Sürüm:** 2.1.0
+ **Sürüm:** 2.2.0
## Temel İlkeler
@@@ -141,9 -141,9 +141,9 @@@ Başarısızlık sorunlarını giderin
## Proje Yapısı
```
- agents/ — 28 özel subagent
- skills/ — 115 iş akışı skillleri ve alan bilgisi
- commands/ — 59 slash command
-agents/ — 68 özel subagent
-skills/ — 287 iş akışı skillleri ve alan bilgisi
++agents/ — 69 özel subagent
++skills/ — 288 iş akışı skillleri ve alan bilgisi
+ commands/ — 94 slash command
hooks/ — Tetikleyici tabanlı otomasyonlar
rules/ — Her zaman uyulması gereken kurallar (ortak + dile özel)
scripts/ — Platformlar arası Node.js yardımcı programları
diff --cc docs/tr/README.md
index 2ad359a77,ac43c7b8c..716a05ec2
--- a/docs/tr/README.md
+++ b/docs/tr/README.md
@@@ -23,7 -23,7 +23,7 @@@
**Dil / Language / 语言 / 語言 / Язык / Ngôn ngữ**
--[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [**Türkçe**](README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md) | [ไทย](../th/README.md) | [Deutsch](../de-DE/README.md)
++[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [**Türkçe**](README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md) | [ไทย](../th/README.md) | [Deutsch](../de-DE/README.md) | [বাংলা](../bn/README.md)
</div>
diff --cc docs/zh-CN/AGENTS.md
index 886b783b0,d829a26a4..fe826a93c
--- a/docs/zh-CN/AGENTS.md
+++ b/docs/zh-CN/AGENTS.md
@@@ -1,8 -1,8 +1,8 @@@
# Everything Claude Code (ECC) — 智能体指令
- 这是一个**生产就绪的 AI 编码插件**,提供 67 个专业代理、281 项技能、94 条命令以及自动化钩子工作流,用于软件开发。
-这是一个**生产就绪的 AI 编码插件**,提供 68 个专业代理、287 项技能、94 条命令以及自动化钩子工作流,用于软件开发。
++这是一个**生产就绪的 AI 编码插件**,提供 69 个专业代理、288 项技能、94 条命令以及自动化钩子工作流,用于软件开发。
- **版本:** 2.1.0
+ **版本:** 2.2.0
## 核心原则
@@@ -146,8 -146,8 +146,8 @@@
## 项目结构
```
- agents/ — 67 个专业子代理
- skills/ — 281 个工作流技能和领域知识
-agents/ — 68 个专业子代理
-skills/ — 287 个工作流技能和领域知识
++agents/ — 69 个专业子代理
++skills/ — 288 个工作流技能和领域知识
commands/ — 94 个斜杠命令
hooks/ — 基于触发的自动化
rules/ — 始终遵循的指导方针(通用 + 每种语言)
diff --cc docs/zh-CN/README.md
index 0f7b4dbda,83c0c92be..af405eb22
--- a/docs/zh-CN/README.md
+++ b/docs/zh-CN/README.md
@@@ -1,4 -1,4 +1,4 @@@
--**语言:** [English](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md) | [ไทย](../th/README.md)
++**语言:** [English](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md) | [ไทย](../th/README.md) | [বাংলা](../bn/README.md)
# Everything Claude Code
@@@ -256,7 -260,7 +260,7 @@@ Copy-Item -Recurse rules/typescript "$H
/plugin list ecc@ecc
```
- **搞定!** 你现在可以使用 67 个智能体、281 项技能和 94 个命令了。
-**搞定!** 你现在可以使用 68 个智能体、287 项技能和 94 个命令了。
++**搞定!** 你现在可以使用 69 个智能体、288 项技能和 94 个命令了。
***
@@@ -1168,9 -1172,9 +1172,9 @@@ opencod
| 功能特性 | Claude Code | OpenCode | 状态 |
|---------|---------------|----------|--------|
- | 智能体 | PASS: 67 个 | PASS: 12 个 | **Claude Code 领先** |
-| 智能体 | PASS: 68 个 | PASS: 12 个 | **Claude Code 领先** |
++| 智能体 | PASS: 69 个 | PASS: 12 个 | **Claude Code 领先** |
| 命令 | PASS: 94 个 | PASS: 35 个 | **Claude Code 领先** |
- | 技能 | PASS: 281 项 | PASS: 37 项 | **Claude Code 领先** |
-| 技能 | PASS: 287 项 | PASS: 37 项 | **Claude Code 领先** |
++| 技能 | PASS: 288 项 | PASS: 37 项 | **Claude Code 领先** |
| 钩子 | PASS: 8 种事件类型 | PASS: 11 种事件 | **OpenCode 更多!** |
| 规则 | PASS: 29 条 | PASS: 13 条指令 | **Claude Code 领先** |
| MCP 服务器 | PASS: 14 个 | PASS: 完整 | **完全对等** |
@@@ -1276,11 -1280,11 +1280,11 @@@ ECC 是**第一个最大化利用每个
| 功能特性 | Claude Code | Cursor IDE | Codex CLI | OpenCode |
|---------|-----------------------|------------|-----------|----------|
- | **智能体** | 67 | 共享 (AGENTS.md) | 共享 (AGENTS.md) | 12 |
-| **智能体** | 68 | 共享 (AGENTS.md) | 共享 (AGENTS.md) | 12 |
++| **智能体** | 69 | 共享 (AGENTS.md) | 共享 (AGENTS.md) | 12 |
| **命令** | 94 | 共享 | 基于指令 | 35 |
- | **技能** | 281 | 共享 | 10 (原生格式) | 37 |
- | **钩子事件** | 8 种类型 | 15 种类型 | 暂无 | 11 种类型 |
- | **钩子脚本** | 20+ 个脚本 | 16 个脚本 (DRY 适配器) | N/A | 插件钩子 |
-| **技能** | 287 | 共享 | 10 (原生格式) | 37 |
++| **技能** | 288 | 共享 | 10 (原生格式) | 37 |
+ | **钩子事件** | 8 种类型 | 15 种类型 | SessionStart(1 种类型) | 11 种类型 |
+ | **钩子脚本** | 20+ 个脚本 | 16 个脚本 (DRY 适配器) | 1 个 SessionStart 引导脚本 | 插件钩子 |
| **规则** | 34 (通用 + 语言) | 34 (YAML 前页) | 基于指令 | 13 条指令 |
| **自定义工具** | 通过钩子 | 通过钩子 | N/A | 6 个原生工具 |
| **MCP 服务器** | 14 | 共享 (mcp.json) | 4 (基于命令) | 完整 |
diff --cc docs/zh-TW/README.md
index 7d9b6adbb,7d9b6adbb..9835636d1
--- a/docs/zh-TW/README.md
+++ b/docs/zh-TW/README.md
@@@ -13,7 -13,7 +13,7 @@@
**Language / 语言 / 語言 / Dil / Язык / Ngôn ngữ**
--[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | **繁體中文** | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md) | [ไทย](../th/README.md) | [Deutsch](../de-DE/README.md)
++[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | **繁體中文** | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md) | [ไทย](../th/README.md) | [Deutsch](../de-DE/README.md) | [বাংলা](../bn/README.md)
</div>
diff --cc manifests/install-components.json
index 70409a86d,a5f976a94..83690799c
--- a/manifests/install-components.json
+++ b/manifests/install-components.json
@@@ -558,6 -558,6 +558,14 @@@
"framework-language"
]
},
++ {
++ "id": "skill:bengali-nlp",
++ "family": "skill",
++ "description": "Bengali Unicode, normalization, tokenization, search, and NLP guidance.",
++ "modules": [
++ "framework-language"
++ ]
++ },
{
"id": "skill:security-review",
"family": "skill",
@@@ -646,6 -646,6 +654,14 @@@
"docs-zh-tw"
]
},
++ {
++ "id": "locale:bn",
++ "family": "locale",
++ "description": "Bengali (bn) translated reference documentation installed to ~/.claude/docs/bn/.",
++ "modules": [
++ "docs-bn"
++ ]
++ },
{
"id": "locale:de-de",
"family": "locale",
diff --cc manifests/install-modules.json
index 6ba1d3093,f1249b935..21dbdaa70
--- a/manifests/install-modules.json
+++ b/manifests/install-modules.json
@@@ -152,6 -152,6 +152,7 @@@
"skills/angular-developer",
"skills/api-design",
"skills/backend-patterns",
++ "skills/bengali-nlp",
"skills/coding-standards",
"skills/compose-multiplatform-patterns",
"skills/contract-first",
@@@ -1073,6 -1079,6 +1080,22 @@@
"cost": "heavy",
"stability": "stable"
},
++ {
++ "id": "docs-bn",
++ "kind": "docs",
++ "description": "Bengali (bn) translated reference documentation.",
++ "paths": [
++ "docs/bn"
++ ],
++ "targets": [
++ "claude",
++ "claude-project"
++ ],
++ "dependencies": [],
++ "defaultInstall": false,
++ "cost": "light",
++ "stability": "stable"
++ },
{
"id": "docs-de-de",
"kind": "docs",
diff --cc package.json
index 6107d724a,6e28aa5da..847d491be
--- a/package.json
+++ b/package.json
@@@ -65,6 -65,6 +65,7 @@@
"assets/images/sponsors/",
"agents/",
"commands/",
++ "docs/bn/",
"docs/de-DE/",
"docs/CODEX-NAVIGATION-GUIDE.md",
"docs/COMMAND-AGENT-MAP.md",
@@@ -147,6 -151,6 +152,7 @@@
"skills/automation-audit-ops/",
"skills/autonomous-loops/",
"skills/backend-patterns/",
++ "skills/bengali-nlp/",
"skills/blender-motion-state-inspection/",
"skills/blueprint/",
"skills/brand-voice/",
diff --cc skills/bengali-nlp/SKILL.md
index faa40ad84,000000000..87441782e
mode 100644,000000..100644
--- a/skills/bengali-nlp/SKILL.md
+++ b/skills/bengali-nlp/SKILL.md
@@@ -1,375 -1,0 +1,375 @@@
+---
+name: bengali-nlp
+description: Bengali (Bangla) text processing patterns including Unicode normalization, script detection, tokenization, conjunct handling, and Bangla-specific NLP best practices for AI applications.
+metadata:
+ origin: ECC
+---
+
+# Bengali (Bangla) NLP Patterns
+
+Best practices for processing, storing, and displaying Bengali text in software applications and AI systems.
+
+## When to Activate
+
+- Working with Bengali/Bangla text data
+- Building apps targeting Bengali-speaking users
+- Processing NCTB (National Curriculum and Textbook Board) educational content
+- Implementing Bengali search, autocomplete, or text input
+- Training or fine-tuning LLMs on Bengali data
+- Building Bengali chatbots or conversational AI
+- Handling mixed Bengali-English (Banglish) text
+
+## Bengali Unicode and Script Handling
+
+### Unicode Range
+
+Bengali script occupies U+0980–U+09FF. Key character classes:
+
+```
+U+0981–U+0983 Chandrabindu, Anusvara, Visarga
+U+0985–U+0994 Independent vowels (অ আ ই ঈ উ ঊ ঋ ঌ এ ঐ ও ঔ)
+U+0995–U+09B0 Consonants (ক–র)
+U+09B2 ল
+U+09B6–U+09B9 শ ষ স হ
+U+09BC Nukta
+U+09BE–U+09C8 Dependent vowel signs (কার): া ি ী ু ূ ৃ ে ৈ
+U+09CB–U+09CC Dependent vowel signs: ো ৌ
+U+09CD Hasanta (virama) — forms conjuncts
+U+09CE Khanda Ta (ৎ)
+U+09D7 AU length mark
+U+09E0–U+09E3 Extended vowels
+U+09E6–U+09EF Bengali digits: ০১২৩৪৫৬৭৮৯
+U+09F0–U+09FA Currency and other signs (৳ ৲)
+```
+
+### Normalization
+
+Always normalize Bengali text to NFC before comparison, storage, or search:
+
+```python
+import unicodedata
+
+def normalize_bangla(text: str) -> str:
+ """Normalize Bengali text to NFC form."""
+ return unicodedata.normalize("NFC", text)
+
+# NFC composes characters: base + combining mark -> precomposed
+text_nfd = "বাংলা" # may be decomposed
+text_nfc = normalize_bangla(text_nfd)
+assert text_nfc == normalize_bangla(text_nfc) # idempotent
+```
+
+```javascript
+// JavaScript
+function normalizeBangla(text) {
+ return text.normalize('NFC');
+}
+```
+
+### Conjunct Consonants (যুক্তবর্ণ)
+
+Bengali conjuncts are formed with Hasanta (্) between consonants:
+
+```
+ক + ্ + ষ = ক্ষ (ksha)
+স + ্ + ত = স্ত (sta)
+ন + ্ + ত + ্ + র = ন্ত্র (ntra)
+```
+
+**Never split strings in the middle of a conjunct.** Use grapheme cluster boundaries:
+
+```python
+import regex # pip install regex
+
+def grapheme_length(text: str) -> int:
+ """Count user-perceived characters (grapheme clusters)."""
+ return len(regex.findall(r"\X", text))
+
+# "ক্ষ" is 1 grapheme but 3 code points (ক + ্ + ষ)
+assert grapheme_length("ক্ষ") == 1
+assert len("ক্ষ") == 3 # code point count — wrong for display
+```
+
+```javascript
+// JavaScript — use Intl.Segmenter for grapheme-safe operations
+function graphemeLength(text) {
+ const segmenter = new Intl.Segmenter('bn', { granularity: 'grapheme' });
+ return [...segmenter.segment(text)].length;
+}
+```
+
+### Bengali Digits
+
+Handle both Bengali (০-৯) and ASCII (0-9) digits:
+
+```python
+BANGLA_DIGITS = "০১২৩৪৫৬৭৮৯"
+ASCII_DIGITS = "0123456789"
+
+def bangla_to_ascii_digits(text: str) -> str:
+ table = str.maketrans(BANGLA_DIGITS, ASCII_DIGITS)
+ return text.translate(table)
+
+def ascii_to_bangla_digits(text: str) -> str:
+ table = str.maketrans(ASCII_DIGITS, BANGLA_DIGITS)
+ return text.translate(table)
+```
+
+## Tokenization
+
+### Word Boundary Detection
+
+Bengali uses spaces between words, but compound words and postpositions can complicate tokenization:
+
+```python
+import re
+
+def tokenize_bangla(text: str) -> list[str]:
+ """Basic Bengali tokenizer — split on whitespace and punctuation."""
+ # Remove Bengali and ASCII punctuation
+ text = re.sub(r'[।,;:!?\-\'"()\[\]{}]', ' ', text)
+ return [token for token in text.split() if token]
+
+# For production, use a trained tokenizer:
+# - bnlp (pip install bnlp_toolkit)
+# - stanza with Bengali model
+# - spaCy with Bengali pipeline
+```
+
+### Using bnlp Toolkit
+
+```python
+from bnlp import NLTKTokenizer
+
+tokenizer = NLTKTokenizer()
+tokens = tokenizer.word_tokenize("আমি বাংলায় গান গাই।")
+# ['আমি', 'বাংলায়', 'গান', 'গাই', '।']
+```
+
+### Handling Postpositions and Case Markers
+
+Bengali postpositions attach to nouns. Tokenizers should be aware of common suffixes:
+
+```
+-এর (possessive), -তে (locative), -কে (accusative)
+-র (possessive after vowel), -য় (locative variant)
+```
+
+## Text Processing Patterns
+
+### Script Detection
+
+```python
+import re
+
+def is_bangla(text: str) -> bool:
+ """Check if text contains Bengali script characters."""
+ return bool(re.search(r'[\u0980-\u09FF]', text))
+
+def bangla_ratio(text: str) -> float:
+ """Return the ratio of Bengali characters in text."""
+ if not text:
+ return 0.0
+ bangla_chars = len(re.findall(r'[\u0980-\u09FF]', text))
+ return bangla_chars / len(text)
+```
+
+### Stop Words
+
+Common Bengali stop words to filter in search/NLP pipelines:
+
+```python
+BANGLA_STOP_WORDS = {
+ "এবং", "ও", "এ", "এই", "সেই", "তার", "যে", "একটি",
+ "করে", "হয়", "আর", "কিন্তু", "তবে", "যদি", "তাহলে",
+ "আমি", "তুমি", "সে", "আমরা", "তোমরা", "তারা",
+ "হবে", "ছিল", "আছে", "নেই", "থেকে", "জন্য", "সাথে",
+ "পর", "আগে", "উপর", "নিচে", "মধ্যে", "দিয়ে",
+ "কি", "কে", "কোন", "কোথায়", "কেন", "কিভাবে",
+ "না", "নয়", "হ্যাঁ", "অনেক", "কিছু", "সব", "প্রতি",
+}
+```
+
+### Sorting and Collation
+
+Bengali has a defined sort order (স্বরবর্ণ before ব্যঞ্জনবর্ণ). Use locale-aware sorting:
+
+```python
+# Preferred: use PyICU for reliable Bengali collation (pip install PyICU)
+try:
+ import icu
+ collator = icu.Collator.createInstance(icu.Locale("bn_BD"))
+ sorted_words = sorted(words, key=collator.getSortKey)
+except ImportError:
+ # Fallback: Unicode code point order (not linguistically perfect)
+ sorted_words = sorted(words)
+```
+
+```javascript
+// JavaScript — Intl.Collator handles Bengali sort order
+const collator = new Intl.Collator('bn-BD');
+const sortedWords = [...words].sort(collator.compare);
+```
+
+### Search with Normalization
+
+```python
+def bangla_search(query: str, corpus: list[str]) -> list[str]:
+ """Search Bengali text with normalization."""
+ query = unicodedata.normalize("NFC", query.strip().lower())
+ results = []
+ for doc in corpus:
+ normalized = unicodedata.normalize("NFC", doc.lower())
+ if query in normalized:
+ results.append(doc)
+ return results
+```
+
+## Bengali in AI/LLM Applications
+
+### Prompt Engineering for Bengali
+
+**Important:** Bengali text, Banglish input, and web-scraped content should be
+treated as untrusted user data. Always separate system instructions from
+user-provided content with clear delimiters, and validate before executing
+tool calls or destructive actions.
+
+```python
+# Use Bengali system prompts for Bengali-targeted apps
+system_prompt = (
+ "তুমি একজন সহায়ক AI সহকারী। বাংলায় উত্তর দাও। "
+ "সহজ ভাষায় ব্যাখ্যা করো যাতে সবাই বুঝতে পারে।"
+)
+
+# For mixed-language contexts, specify language explicitly
+system_prompt_mixed = (
+ "You are a helpful assistant. When the user writes in Bengali, "
+ "respond in Bengali. When they write in English, respond in English. "
+ "For technical terms, you may use English words within Bengali sentences."
+)
+
+# Always delimit user-provided content
+def build_prompt(system: str, user_input: str) -> str:
- return f"{system}
++ return f"""{system}
+---USER INPUT---
+{user_input}
- ---END INPUT---"
++---END INPUT---"""
+```
+
+### Handling Banglish (Mixed Bengali-English)
+
+Banglish is Bengali written in Latin script. Common in informal digital communication:
+
+```python
+import re
+
+def detect_banglish(text: str) -> bool:
+ """Heuristic: Latin script with Bengali transliteration patterns."""
+ if is_bangla(text):
+ return False # Already in Bengali script
+ # Common Banglish patterns
+ banglish_patterns = [
+ r'\bami\b', r'\btumi\b', r'\bapni\b', r'\bkemon\b',
+ r'\bkothay\b', r'\bkeno\b', r'\bdhonnobad\b',
+ r'\bash\w*lam\b', r'\bkor\w*chi\b', r'\bbol\w*chi\b',
+ ]
+ matches = sum(1 for p in banglish_patterns if re.search(p, text, re.I))
+ return matches >= 2
+```
+
+### Dataset Preparation
+
+```python
+def prepare_bangla_dataset(texts: list[str]) -> list[str]:
+ """Clean and normalize Bengali text for ML training."""
+ cleaned = []
+ for text in texts:
+ # Normalize Unicode
+ text = unicodedata.normalize("NFC", text)
+ # Remove unwanted zero-width characters but preserve ZWNJ/ZWJ (important for conjuncts)
+ text = re.sub(r'[\u200b\ufeff]', '', text)
+ # Normalize whitespace
+ text = re.sub(r'\s+', ' ', text).strip()
+ if text:
+ cleaned.append(text)
+ return cleaned
+```
+
+## Database and Storage
+
+```sql
+-- MySQL: use utf8mb4 for Bengali text columns
+CREATE TABLE bengali_content (
+ id INT PRIMARY KEY AUTO_INCREMENT,
+ title VARCHAR(255) CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci,
+ body TEXT CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci
+);
+
+-- PostgreSQL: Verify UTF-8 encoding and ICU collation availability:
+-- SELECT pg_encoding_to_char(encoding) FROM pg_database WHERE datname = current_database();
+-- SELECT collname FROM pg_collation WHERE collname LIKE 'bn%';
+-- If missing, create it (requires ICU-enabled PostgreSQL build):
+-- CREATE COLLATION IF NOT EXISTS "bn-BD-x-icu" (provider = icu, locale = 'bn-BD');
+CREATE TABLE bengali_content (
+ id SERIAL PRIMARY KEY,
+ title TEXT COLLATE "bn-BD-x-icu",
+ body TEXT
+);
+```
+
+## Common Anti-Patterns
+
+### Don't: Split on Code Points for Display Length
+
+```python
+# BAD — breaks conjuncts
+def truncate_bad(text, max_len):
+ return text[:max_len] # may cut inside ক্ষ
+
+# GOOD — respect grapheme boundaries
+import regex
+def truncate_good(text, max_graphemes):
+ graphemes = regex.findall(r"\X", text)
+ return "".join(graphemes[:max_graphemes])
+```
+
+### Don't: Skip Normalization Before Comparison
+
+```python
+# BAD — same visual text may not match
+if user_input == stored_text: ...
+
+# GOOD
+if unicodedata.normalize("NFC", user_input) == unicodedata.normalize("NFC", stored_text): ...
+```
+
+### Don't: Assume All Digits Are ASCII
+
+```python
+# BAD — misses Bengali digits
+if text.isdigit(): ...
+
+# GOOD — handles both
+import re
+if re.fullmatch(r'[0-9০-৯]+', text): ...
+```
+
+### Don't: Use ASCII Transliteration When Unicode Is Available
+
+```python
+# BAD — lossy and ambiguous
+title = "bangla bhasha"
+
+# GOOD — use proper Unicode
+title = "বাংলা ভাষা"
+```
+
+### Don't: Ignore Zero-Width Characters in Web-Scraped Text
+
+```python
+# BAD — invisible characters cause matching failures
+text = scraped_html.get_text()
+
+# GOOD — strip unwanted zero-width chars, preserving ZWNJ (U+200C) and ZWJ (U+200D)
+text = re.sub(r'[\u200b\ufeff]', '', scraped_html.get_text())
+```
diff --cc tests/ci/bengali-language-surface.test.js
index 000000000,000000000..3399f6d43
new file mode 100644
--- /dev/null
+++ b/tests/ci/bengali-language-surface.test.js
@@@ -1,0 -1,0 +1,115 @@@
++#!/usr/bin/env node
++
++const assert = require('assert');
++const fs = require('fs');
++const path = require('path');
++const { spawnSync } = require('child_process');
++
++const ROOT = path.join(__dirname, '..', '..');
++
++function read(relativePath) {
++ return fs.readFileSync(path.join(ROOT, relativePath), 'utf8');
++}
++
++function readJson(relativePath) {
++ return JSON.parse(read(relativePath));
++}
++
++function test(name, fn) {
++ try {
++ fn();
++ console.log(` ✓ ${name}`);
++ return true;
++ } catch (error) {
++ console.log(` ✗ ${name}`);
++ console.error(` ${error.message}`);
++ return false;
++ }
++}
++
++function findPython() {
++ for (const command of process.platform === 'win32' ? ['python', 'py'] : ['python3', 'python']) {
++ const args = command === 'py' ? ['-3', '--version'] : ['--version'];
++ const result = spawnSync(command, args, { encoding: 'utf8' });
++ if (result.status === 0) {
++ return { command, prefix: command === 'py' ? ['-3'] : [] };
++ }
++ }
++ return null;
++}
++
++function run() {
++ console.log('\n=== Testing Bengali language surfaces ===\n');
++
++ let passed = 0;
++ let failed = 0;
++
++ if (test('Bengali Python examples are syntactically valid', () => {
++ const skill = read('skills/bengali-nlp/SKILL.md');
++ const snippets = [...skill.matchAll(/```python\s*\n([\s\S]*?)```/g)].map(match => match[1]);
++ assert.ok(snippets.length > 0, 'Expected at least one Python example');
++
++ const python = findPython();
++ if (!python) {
++ console.log(' SKIP: Python interpreter is unavailable');
++ return;
++ }
++
++ snippets.forEach((snippet, index) => {
++ const result = spawnSync(
++ python.command,
++ [...python.prefix, '-c', "import sys; compile(sys.stdin.read(), '<bengali-nlp>', 'exec')"],
++ { input: snippet, encoding: 'utf8' },
++ );
++ assert.strictEqual(
++ result.status,
++ 0,
++ `Python example ${index + 1} does not compile:\n${result.stderr || result.stdout}`,
++ );
++ });
++ })) passed++; else failed++;
++
++ if (test('Bengali skill is exported and installable', () => {
++ const agentYaml = read('agent.yaml');
++ const modules = readJson('manifests/install-modules.json').modules;
++ const components = readJson('manifests/install-components.json').components;
++ const packageFiles = readJson('package.json').files;
++ const frameworkModule = modules.find(module => module.id === 'framework-language');
++ const skillComponent = components.find(component => component.id === 'skill:bengali-nlp');
++
++ assert.match(agentYaml, /^\s+- bengali-nlp\s*$/m);
++ assert.ok(frameworkModule?.paths.includes('skills/bengali-nlp'));
++ assert.ok(skillComponent?.modules.includes('framework-language'));
++ assert.ok(packageFiles.includes('skills/bengali-nlp/'));
++ })) passed++; else failed++;
++
++ if (test('Bengali reviewer is discoverable through the shared agent surface', () => {
++ const agentsGuide = read('AGENTS.md');
++ const modules = readJson('manifests/install-modules.json').modules;
++ const agentsModule = modules.find(module => module.id === 'agents-core');
++
++ assert.ok(fs.existsSync(path.join(ROOT, 'agents', 'bengali-reviewer.md')));
++ assert.match(agentsGuide, /^\| bengali-reviewer \|/m);
++ assert.ok(agentsModule?.paths.includes('agents'));
++ })) passed++; else failed++;
++
++ if (test('Bengali documentation has an installable locale route', () => {
++ const modules = readJson('manifests/install-modules.json').modules;
++ const components = readJson('manifests/install-components.json').components;
++ const packageFiles = readJson('package.json').files;
++ const docsModule = modules.find(module => module.id === 'docs-bn');
++ const localeComponent = components.find(component => component.id === 'locale:bn');
++
++ assert.ok(fs.existsSync(path.join(ROOT, 'docs', 'bn', 'README.md')));
++ assert.deepStrictEqual(docsModule?.paths, ['docs/bn']);
++ assert.ok(localeComponent?.modules.includes('docs-bn'));
++ assert.ok(packageFiles.includes('docs/bn/'));
++ assert.match(read('README.md'), /href="docs\/bn\/README\.md">বাংলা<\/a>/);
++ })) passed++; else failed++;
++
++ console.log(`\nPassed: ${passed}`);
++ console.log(`Failed: ${failed}`);
++ process.exit(failed > 0 ? 1 : 0);
++}
++
++run();