taw-kit-codex

Name: taw-kit-codex
Rating: 58 (1 reviews)
Author: tawgroup

tawgroup/taw-kit-codex

A comprehensive global Codex skill kit featuring 47 specialized skills, agent roles, and lifecycle hooks optimized for multi-language software development with native Vietnamese support.

7 4No licenseUpdated 2026-05-23

Fair

View on GitHub Open source file

Overview

The taw-kit-codex plugin brings a robust suite of development tools and agent orchestration directly to OpenAI Codex. Acting through a central natural-language orchestrator named taw, it handles everything from scaffolding web applications and mobile apps to backend refactoring, automated testing, git workflows, and remote deployment while offering seamless multi-language communication.

Capabilities

▸Multi-language intent classification and localization (Vietnamese and English)
▸Modular branch-based task execution and planning
▸Automated git commits and repository management
▸Sequential agent role execution for planning, coding, and review
▸Lifecycle hooks integration for session tracking and auto-checkpoints

Best for

Building full-stack web applications, mobile apps, or backend APIs from plain language prompts in Vietnamese or English., Executing safe, multi-step refactoring loops with pre- and post-refactor API verification., Running long-running task queues for systematic feature implementation and testing., Performing automated git commits, PR management, and repository security audits.

Works with

Codex

Evoa Score breakdown= Σ (score × weight)

Task usefulness20%88 → +17.6

実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析

Code quality15%90 → +13.5

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%85 → +12.8

リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ

Documentation12%38 → +4.6

ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量

Security15%50 → +7.5

危険・不審な挙動が無いか。 — AIによるセキュリティレビュー

Originality10%85 → +8.5

ありふれたラッパーではない独自性。 — AIによる独自性判定

Popularity8%30 → +2.4

コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）

Compatibility5%25 → +1.3

対応AIエージェントの広さ。 — AIによる対応エージェント判定

Weighted total68.1 / 100

ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。ランキングはこのScoreのみで決まり、広告で変わりません。算出方法の詳細 →

Security considerations

Executes shell commands, manages git states, and handles local database/environment modifications according to user prompts. Ensure proper authorization in production environments.