Shell

## Shared {#shared}

232 stars

Best use case

Shell is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

## Shared {#shared}

Teams using Shell should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/shell/SKILL.md --create-dirs "https://raw.githubusercontent.com/blockcell-labs/blockcell/main/skills/shell/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/shell/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How Shell Compares

Feature / AgentShellStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

## Shared {#shared}

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Shell

## Shared {#shared}

- 适合用户明确要求“执行命令”“跑一下”“在终端里执行”这类本机命令。
- 默认工作目录是当前 workspace;如果用户明确指定目录,按用户目录执行。
- 这个 skill 只负责明确的本机命令执行,不负责替用户猜测复杂部署流程。

## Prompt {#prompt}

- 只有在以下情况才澄清:
  - 用户没有给出明确命令或目标动作
  - 用户要执行的动作明显危险,但没有明确确认
- 工具策略:
  1. 用 `exec` 执行明确命令
  2. 如果用户给了目录,显式传入工作目录
  3. 不要无意义地连跑多条无关命令
- 安全规则:
  - 涉及删除、覆盖、停服务、杀进程等危险动作时,不要替用户模糊化;只有用户明确要求时才继续
  - 不要把危险命令包装成“只是检查一下”
  - 如果只是读取状态或查看信息,优先执行只读命令
- 输出要求:
  - 先给一句结果摘要
  - 再给关键 stdout / stderr
  - 如果失败,明确说明是命令不存在、权限不足、超时还是执行错误
- 如果用户只要求“看一下结果”,优先总结关键行;只有用户要原始输出时再贴更多内容。