#
ENJA

nsh

fluffypony/nsh

An AI-powered natural language shell assistant that translates prompts into commands, provides deep terminal context awareness, and includes a multi-step agentic loop.

495 187BSD-3-ClauseUpdated 2026-07-02
View on GitHubOpen source file

Overview

nsh operates directly inside your terminal across popular shells like zsh, bash, fish, and PowerShell, capturing history and scrollback in a local database. It leverages an LLM-driven multi-step tool loop to investigate issues, prefill commands for safe review, execute coding tasks, manage persistent memory tiers, and even provide secure remote P2P access.

Capabilities

  • ▸Natural language to shell command translation with prefill
  • ▸Multi-step agentic tool execution loop
  • ▸Project detection and context assembly from git and terminal scrollback
  • ▸Secret redaction and command risk assessment
  • ▸6-tier persistent memory system with automated reflection and decay
  • ▸End-to-end encrypted remote P2P access via iroh

Best for

Troubleshooting terminal errors using natural language queries, Writing and executing complex shell commands with safety checks, Running multi-step coding sub-agents for repository refactoring and bug fixes, Accessing desktop terminal sessions securely from a mobile companion app

Works with

Claude CodeCodexChatGPTGemini CLICursorGitHub CopilotOpenCode
Evoa Score breakdown= Σ (score × weight)
77
Task usefulness20%100 → +20.0

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%32 → +3.8

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%73 → +5.8

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

Compatibility5%100 → +5.0

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 total76.9 / 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

Implements extensive security mitigations including secret redaction for API keys/tokens, blocking sensitive directory access (~/.ssh, ~/.aws), tool output sandboxing against prompt injections, and command risk assessment levels.

Categories

CodingDevOpsAutomationProductivity

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.