skills.rest
hotung1027
hotung1027COMMUNITY
Explore all skills by this author →
GitHub

sandbox-terminal

Detect project toolchains and execute terminal commands with workspace-specific runners.

Updated Feb 7, 2026
One-click install
npx skills add https://github.com/hotung1027/dev.conf --skill sandbox-terminal
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sandbox-terminal
Source: https://github.com/hotung1027/dev.conf/tree/main/agents/skills/sandbox-terminal
Command: npx skills add https://github.com/hotung1027/dev.conf --skill sandbox-terminal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill guides AI agents to safely, efficiently, and correctly use terminal commands in any workspace. It ensures actions stay within the environment, avoids secrets leakage, and defers to workspace-specific steering docs for concrete commands.

Core Features & Use Cases

  • Safe, token-efficient terminal usage: agents learn to run commands without disrupting the workspace and with minimal output.
  • Environment detection and runner resolution: detects the project root and selects the correct runner (e.g., uv run, poetry run, pnpm, etc.) before execution.
  • Workspace overrides and portability: consults {{workspace}}/.github/ for organization-specific rules and scripts, enabling portable automation across workspaces.

Quick Start

Activate when the user asks to run a command, install dependencies, run tests, start servers, lint, build, create scripts, debug terminal errors, or compose CI/CD pipelines. The agent should first perform environment detection, then check for workspace steering docs, and finally execute the user's request using the appropriate runner.

Frequently Asked Questions about sandbox-terminal

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run terminal commands safely with an AI agent without leaking secrets?▼

Safe terminal command execution for AI agents requires prefixing commands with the correct runner detected via an Environment Detection Protocol, ensuring actions stay within the workspace and preventing secrets leakage.

How do I automatically detect the correct package runner before executing terminal commands?▼

Environment detection and runner resolution identifies the project root to select the appropriate runner, such as uv run, poetry run, or pnpm, before executing terminal commands for safe task orchestration.

Can I use workspace steering docs to override terminal commands for different projects?▼

Yes, workspace overrides consult organization-specific rules and scripts stored in the workspace's .github directory, enabling portable automation and correct command execution across different workspaces.

What is token-efficient terminal usage for AI agents and why is it needed?▼

Token-efficient terminal usage minimizes command output to reduce token consumption, allowing AI agents to run tests, lint code, and start servers without disrupting the workspace or exceeding context limits.

Do I need a root SKILL.md file to enable safe terminal automation?▼

Yes, safe terminal automation requires a root SKILL.md file containing a name and description, alongside an Environment Detection Protocol to prefix commands with the correct runner for execution.

Related Skills

julianromlijulianromli
141

using-git-worktrees

Create isolated git worktrees with project detection and baseline verification.

Community
Advanced
tianzecntianzecn
2

quality-gates

Automate quality gates and severity classification for multi-agent workflows.

Community
Advanced
sangrokjungsangrokjung
1

build-system

Detect project build systems and execute their build or test commands.

Community
Intermediate
hoainam183hoainam183

tmux

Manage persistent tmux sessions, windows, and panes via shell scripts.

Community
Intermediate