Bash Script Generator logo

Bash Script Generator

Community
akin-ozer
bash-script-generator

Create, generate, write, or scaffold bash/shell scripts (.sh), automation, or CLI tools.

Overview

Publisherakin-ozer
Repositorycc-devops-skills
Skill namebash-script-generator
Stars
326
Forks
39
Bundled files
9
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by akin-ozer on GitHub. Read the source before you install it.

Installation

Install the Bash Script Generator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/akin-ozer/cc-devops-skills/tree/main/devops-skills-plugin/skills/bash-script-generator
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/akin-ozer/cc-devops-skills.git /tmp/cc-devops-skills
mkdir -p .claude/skills
cp -r /tmp/cc-devops-skills/devops-skills-plugin/skills/bash-script-generator .claude/skills/bash-script-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bash Script Generator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bash Script Generator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bash Script Generator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Bash Script Generator

Overview

Generate production-ready Bash scripts with clear requirements capture, deterministic generation flow, and validation-first iteration.

Trigger Phrases

Use this skill when the user asks to:

  • Create, generate, write, or build a Bash/shell script
  • Convert manual CLI steps into an automation script
  • Build a text-processing script using grep, awk, or sed
  • Create an operations helper script, cron script, or CI utility script

Do not use this skill for validating an existing script only. Use devops-skills:bash-script-validator for validation-only requests.

Execution Model

Follow stages in order. Do not skip a stage; use the documented fallback when blocked.

Stage 0: Preflight

  1. Confirm scope and target output path.
  2. Confirm shell target:
  • Default: bash
  • If portability is requested: POSIX sh
  1. Check capabilities and pick fallback path:
CapabilityDefault PathFallback Path
Requirement clarificationAskUserQuestion toolAsk same questions in normal chat; mark unresolved items as assumptions
Script scaffoldbash scripts/generate_script_template.sh ...Copy assets/templates/standard-template.sh manually or hand-craft minimal scaffold
Validationdevops-skills:bash-script-validatorLocal checks: bash -n, shellcheck if available, sh -n for POSIX mode

If a fallback path is used, state it explicitly in the final summary.

Stage 1: Capture Requirements

Collect only what is needed to generate the script correctly:

  • Input source and format
  • Output destination and format
  • Error handling behavior (fail-fast/retry/continue)
  • Security constraints (sensitive data, privilege level)
  • Performance constraints (large files, parallelism)
  • Portability requirement (Bash-only vs POSIX)

Then create a Captured Requirements table with stable IDs.

markdown
## Captured Requirements

| Requirement ID | Description | Source | Implementation Plan |
|---|---|---|---|
| REQ-001 | Parse nginx logs from file input | User | `parse_args()` + `validate_file()` + `awk` parser |
| REQ-002 | Output top 10 errors | User | `analyze_errors()` + `sort | uniq -c | head -10` |
| REQ-003 | Handle large files efficiently | Assumption | Single-pass `awk`; avoid multi-pass loops |

Rules:

  • Every major design decision maps to at least one REQ-*.
  • Keep assumptions explicit and minimal.

Stage 2: Choose Generation Path

Use this deterministic decision tree:

text
Need multi-command architecture, unusual control flow, or strict non-template conventions?
├─ Yes -> Custom generation
└─ No
   Need standard CLI skeleton (usage/logging/arg parsing/cleanup)?
   ├─ Yes -> Template-first generation
   └─ No -> Custom generation

Template-first is the default for single-purpose CLI utilities.

Stage 3: Load Only Relevant References

Use progressive disclosure. Read only docs needed for the current request.

NeedReference
Tool choice (grep vs awk vs sed)docs/text-processing-guide.md
Script structure and argument patternsdocs/script-patterns.md
Strict mode, shell differences, safetydocs/bash-scripting-guide.md
Naming, organization, and quality baselinedocs/generation-best-practices.md

Citation format (required):

  • [Ref: docs/<file>.md -> <section>]

Stage 4: Generate Script

Path A: Template-first (default)
  1. Generate scaffold:
bash
bash scripts/generate_script_template.sh standard output-script.sh
  1. Replace placeholders and add business logic.
  2. Keep logging to stderr and data output to stdout unless requirements say otherwise.
  3. Add comments only where logic is non-obvious.
Path B: Custom generation

Build a script with at least:

  • Shebang and strict mode
  • usage()
  • parse_args()
  • Input validation and dependency checks
  • Main workflow function(s)
  • Predictable exit codes

Stage 5: Validate and Iterate

Default validation path:

  1. Invoke devops-skills:bash-script-validator
  2. Apply fixes
  3. Re-run validation
  4. Repeat until checks pass or blocker is identified

Fallback validation path (when validator skill is unavailable):

bash
# Deterministic local gate for this skill:
bash scripts/run_ci_checks.sh --skip-shellcheck

# CI gate (shellcheck required):
bash scripts/run_ci_checks.sh --require-shellcheck

If any check is skipped, include Skipped check, Reason, and Risk in the output.

Stage 6: Final Response Contract

Always return:

  1. Generated script path
  2. Requirements traceability (REQ-* -> implementation)
  3. Validation results with rerun status
  4. Citations in standard format
  5. Any assumptions/fallbacks used

Canonical Example Flows

Example A: Full Flow (Template-first)

  1. Clarify missing data format and output expectations.
  2. Capture REQ-* table.
  3. Choose template-first path.
  4. Generate scaffold with scripts/generate_script_template.sh.
  5. Implement logic and map functions to REQ-*.
  6. Validate with devops-skills:bash-script-validator and rerun until clean.
  7. Return final summary with citations.

Example B: Constrained Environment Flow

Use this when AskUserQuestion, validator skill, or shellcheck is unavailable:

  1. Ask clarifying questions in chat.
  2. Mark unresolved items as assumptions in Captured Requirements.
  3. Generate from template script or template file copy fallback.
  4. Run bash -n (and sh -n if relevant).
  5. If shellcheck is missing, report skip with risk and mitigation.

Done Criteria

The task is complete only when all items are true:

  • Trigger matched and scope confirmed
  • Captured Requirements table exists with REQ-* IDs
  • Template-first vs custom decision is documented
  • Script is generated with deterministic structure
  • Validation executed and rerun policy applied
  • Any skipped checks include explicit reason and risk
  • Final response includes traceability, citations, and assumptions

Helper Scripts and Assets

  • Script generator: scripts/generate_script_template.sh
  • Deterministic CI gate: scripts/run_ci_checks.sh
  • Regression test suite: scripts/test_generator.sh
  • Standard scaffold: assets/templates/standard-template.sh
  • Example output style: examples/log-analyzer.sh

Reference Docs

  • docs/bash-scripting-guide.md
  • docs/script-patterns.md
  • docs/generation-best-practices.md
  • docs/text-processing-guide.md

External References

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Bash Script Generator AI skill do?

Create, generate, write, or scaffold bash/shell scripts (.sh), automation, or CLI tools.

Why use Bash Script Generator on TypingMind?

Because you install it once and use it with any model. Bash Script Generator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bash Script Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/akin-ozer/cc-devops-skills/tree/main/devops-skills-plugin/skills/bash-script-generator. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Bash Script Generator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bash Script Generator?

As many as you like. As long as a model supports skills, you can use Bash Script Generator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bash Script Generator AI skill free?

Yes. It is published on GitHub by akin-ozer under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇