#
ENJA

Shelly

RYOITABASHI/Shelly

Shelly is a single-screen terminal IDE for Android that combines a native JNI terminal emulator with AI coding assistants and autonomous background agents.

48 7GPL-3.0Updated 2026-08-13
View on GitHubOpen source file

Overview

Shelly transforms an Android device into a self-contained local development environment and agent machine. Built using Expo, React Native, and TypeScript, it features a native JNI PTY terminal alongside tools like bash, Node.js, Python, and git. It bridges the gap between terminal operations and AI capabilities by allowing side-by-side execution, preventing the need for tedious copy-pasting between separate apps.

Capabilities

  • ▸Native JNI-based terminal emulation without Termux dependency
  • ▸Multi-pane layout supporting terminal, AI, browser, and markdown views
  • ▸Integrated secure API key storage using expo-secure-store
  • ▸Bundled development toolchain including bash, Python 3, Node.js, and git
  • ▸Autonomous agent scheduling and execution hooks

Best for

Running terminal commands and AI coding CLIs natively on Android devices., Fixing terminal errors interactively using side-by-side AI assistance., Managing development workflows and scheduled autonomous agents directly from mobile devices.

Works with

CodexClaude CodeGemini CLI
Evoa Score breakdown= Σ (score × weight)
74
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%85 → +12.8

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

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%33 → +4.0

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%95 → +9.5

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%45 → +3.6

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

Compatibility5%75 → +3.8

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 total73.7 / 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

API keys and sensitive credentials are handled and encrypted locally using secure storage modules on the device.

Categories

CodingDevOpsProductivityAutomation

Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.