shell-scripting

65 stars 10 forks
79
C

Practical bash scripting guidance emphasising defensive programming, ShellCheck compliance, and simplicity. Use when writing shell scripts that need to be reliable and maintainable.

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install sammcj/agentic-coding/shell-scripting
skilz install sammcj/agentic-coding/shell-scripting --agent opencode
skilz install sammcj/agentic-coding/shell-scripting --agent codex
skilz install sammcj/agentic-coding/shell-scripting --agent gemini

First time? Install Skilz: pip install skilz

Works with 14 AI coding assistants

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/sammcj/agentic-coding
2. Copy the agent skill directory:
cp -r agentic-coding/Claude/skills/shell-scripting ~/.claude/skills/

Need detailed installation help? Check our platform-specific guides:

Related Agentic Skills

Agentic Skill Details

Stars
65
Forks
10
Type
Technical
Meta-Domain
cloud infrastructure
Primary Domain
linux
Market Score
79

Agent Skill Grade

C
Score: 79/100 Click to see breakdown

Score Breakdown

Spec Compliance
12/15
PDA Architecture
18/30
Ease of Use
21/25
Writing Style
8/10
Utility
17/20
Modifiers: +3

Areas to Improve

  • No reference file architecture
  • Missing table of contents
  • Verbose code examples

Recommendations

  • Address 1 high-severity issues first
  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 2026-01-05

Developer Feedback

I took a look at your shell-scripting skill and wanted to share some thoughts.

Links:

The TL;DR

You're at 79/100, which puts you in solid C territory. This is based on Anthropic's 5-pillar skill best practices. Your strongest area is Utility (17/20) — the defensive programming patterns and ShellCheck integration genuinely solve real problems. The weakest area is Progressive Disclosure Architecture (18/30), which is the main thing holding you back from a B grade.

What's Working Well

  • Practical defensive patterns — Your mandatory foundations (set -euo pipefail, error handling) address real gaps in how most people write shell scripts. The ShellCheck integration as a validation loop is solid.
  • Clear structure within the single file — Section headers are logical, patterns are numbered, and the Quick Reference Checklist gives people a concrete path forward. That's good teaching.
  • Solid examples — You show complete, runnable templates (simple script, main-function pattern). The Wrong/Correct pairs demonstrate actual anti-patterns developers encounter.
  • Good bonus points — The grep-friendly structure and quality pre-commit checklist earned you extra points. Those details matter.

The Big One: Split This Into Multiple Files

Here's the issue: your skill is 574 lines in a single SKILL.md file. That violates progressive disclosure architecture, which Claude skills are supposed to follow. You pack Mandatory Foundations, Core Safety Patterns, Intermediate Patterns, Advanced patterns, and Anti-Patterns all into one file.

Why it matters: New users get overwhelmed. Advanced users have to scroll through basics. Token economy suffers — you're forcing people to load everythin...

Report Security Issue

Found a security vulnerability in this agent skill?