forge-lang-bash

61
D

Bash/Shell scripting standards including shellcheck, shfmt, and bats testing. Use when working with shell scripts (.sh, .bash).

Also in: testing

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 martimramos/claude-forge/forge-lang-bash
skilz install martimramos/claude-forge/forge-lang-bash --agent opencode
skilz install martimramos/claude-forge/forge-lang-bash --agent codex
skilz install martimramos/claude-forge/forge-lang-bash --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ 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/martimramos/claude-forge
2. Copy the agent skill directory:
cp -r claude-forge/skills/languages/bash ~/.claude/skills/

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

Related Agentic Skills

Agentic Skill Details

Repository
claude-forge
Type
Technical
Meta-Domain
cloud infrastructure
Primary Domain
linux
Market Score
61

Agent Skill Grade

D
Score: 61/100 Click to see breakdown

Score Breakdown

Spec Compliance
11/15
PDA Architecture
18/30
Ease of Use
18/25
Writing Style
8/10
Utility
13/20
Modifiers: -7

Areas to Improve

  • Missing TOC for 165-line file
  • Templates should be in references
  • Missing explicit trigger terms in description

Recommendations

  • 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 bash skill and wanted to share some thoughts.

Links:

The TL;DR

You're at 61/100, which puts you in D territory. This is based on Anthropic's agentic skill best practices. The good news: your writing style is solid (8/10) — the explanations are clear and direct. The challenge: the skill needs better progressive disclosure architecture (18/30) and utility (13/20). You're addressing real bash problems, but the structure and discoverability need work.

What's Working Well

  • Writing is clear and technical — No fluff, instructions are straightforward. You nail the imperative voice in code comments.
  • File triggers are present — Detecting .sh and .bash files is good, though you could lean harder into action-based triggers.
  • Solid templates for common tasks — Your script template and bats test template give users a real starting point.
  • TDD cycle is structured — The testing section has clear steps, which is exactly what developers need.

The Big One: Templates Are Bloating Your File

Your SKILL.md is 165 lines, but roughly 50+ of those are embedded code templates. This violates progressive disclosure architecture — you're forcing users to scroll through boilerplate when they just need the concept.

The Fix: Create a references/ directory and move those templates out:

  • references/script-template.sh — Your bash script example
  • references/test-template.bats — Your bats testing template

Then in SKILL.md, replace the full templates with one-liners like:

See [script template](references/script-template.sh) for a starting point

Impact: This alone gets you +4 points and makes the skill feel less overwhelming.

Other Things W...

Report Security Issue

Found a security vulnerability in this agent skill?