mcp-shellicar
CommunityTranslate Bash patterns into safe exec calls
System Documentation
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.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: mcp-shellicar Download link: https://github.com/shellicar/skills/archive/main.zip#mcp-shellicar Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.