mcp-shellicar

Translate Bash command patterns into structured exec tool calls.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/shellicar/skills --skill mcp-shellicar
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-shellicar
Source: https://github.com/shellicar/skills/tree/main/skills/mcp-shellicar
Command: npx skills add https://github.com/shellicar/skills --skill mcp-shellicar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Many automation environments and agent sessions disallow running a shell, yet users and guides commonly express workflows as Bash command lines. This Skill documents how to convert those Bash patterns into structured exec tool calls that run programs directly via child_process.spawn without a shell.

Core Features & Use Cases

  • Translate single commands, pipelines, heredocs, stdin payloads, file redirects, environment variables, and working directory usages into a JSON steps/commands representation.
  • Explain and map chaining modes (bail_on_error, sequential, independent), background execution, merge_stderr, and capture-to-file semantics so agents behave like shell sequences without a shell.
  • Provide safety and validation guidance including a list of blocked destructive operations and gotchas about expansion, no persistent cd, ENOENT semantics, and stderr/pipeline behavior.
  • Use Case: Convert CI or agent scripts that use &&, ;, pipes, or heredocs into safe exec steps so automation runs consistently when shells are disallowed.

Quick Start

Convert a Bash command sequence (for example, pnpm build && pnpm test or grep -r TODO src/ | wc -l) into an exec steps JSON that uses program/args entries, appropriate chaining, and stdin/redirect fields.

Frequently Asked Questions about mcp-shellicar

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

FAQPage Schema
How do I convert Bash pipelines into safe exec calls without using a shell?

To convert Bash pipelines into safe exec calls, translate command sequences into structured JSON steps using program and args entries, specifying chaining modes and stdin redirects so child_process.spawn runs programs directly without a shell.

How do I handle heredocs and stdin redirects when translating Bash to child_process.spawn?

Handle heredocs and stdin redirects by mapping them into per-command stdin payload fields and file redirect configurations within the structured exec steps JSON, ensuring the target program receives input correctly without shell interpretation.

Can I use environment variables and working directory expansion in non-shell automation scripts?

Yes, you can use environment variables and working directory expansion by applying env and cwd expansion rules to resolve variables like $VAR and paths like ~ within the structured exec tool call representation for your automation tasks.

What is the best way to chain commands sequentially in CI pipelines when Bash is disallowed?

The best way to chain commands sequentially when Bash is disallowed is to use chaining modes like bail_on_error, sequential, or independent within your exec steps JSON, allowing agents to behave like shell sequences safely.

What are the limitations of translating Bash patterns to direct exec tool calls?

Limitations of translating Bash patterns to direct exec tool calls include no persistent cd, specific ENOENT semantics for missing programs, blocked destructive operations, and differences in stderr and pipeline behavior without shell interpretation.