Bash Script Validator logo

Bash Script Validator

Community
akin-ozer
bash-script-validator

Validate, lint, audit, or fix bash/shell/.sh scripts via ShellCheck.

Overview

Publisherakin-ozer
Repositorycc-devops-skills
Skill namebash-script-validator
Stars
326
Forks
39
Bundled files
16
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.

  • 16 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 Validator 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-validator
  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-validator .claude/skills/bash-script-validator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bash Script Validator 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 Validator 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 Validator 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 Validator

Overview

This skill validates Bash and POSIX shell scripts with layered checks:

  1. Syntax validation (bash -n or sh -n)
  2. ShellCheck static analysis (system binary or wrapper fallback)
  3. Custom security, portability, and optimization checks

Use the default flow below, then branch to fallbacks only when the environment is constrained.

Trigger Guidance

Use this skill when the request includes script quality, linting, syntax checking, or shell portability work.

Trigger Phrases

  • "Validate this bash script"
  • "Lint this .sh file"
  • "Find security issues in this shell script"
  • "Why does this script fail ShellCheck?"
  • "Make this script POSIX compliant"
  • "Review this shell script before CI"

Non-Trigger Examples

  • General Linux command questions with no script file
  • Kubernetes, Terraform, or pipeline validation tasks that do not involve shell scripts
  • Pure prose editing tasks

Deterministic Execution Model

Run commands from this skill directory:

bash
cd devops-skills-plugin/skills/bash-script-validator

Step 1: Preflight

  1. Confirm target path exists and is readable.
  2. Confirm bash is available.
  3. Determine whether fixes can be applied directly (write access) or only suggested (read-only).

Step 2: Run Baseline Validation (Default Path)

bash
bash scripts/validate.sh <script-path>

For deterministic stage behavior, set the ShellCheck provider explicitly:

bash
# Modes: auto (default), system, wrapper, disabled
VALIDATOR_SHELLCHECK_MODE=system bash scripts/validate.sh <script-path>

Record:

  • Detected shell type
  • Exit code (0 clean, 1 warnings, 2 errors)
  • All reported issue lines and ShellCheck codes (SC####) when present

Step 3: Load Only Needed References

Progressive disclosure by issue type:

  • ShellCheck code explanations: docs/shellcheck-reference.md
  • General fix patterns and security mistakes: docs/common-mistakes.md
  • Bash-only behavior: docs/bash-reference.md
  • POSIX portability or bashism fixes: docs/shell-reference.md
  • Text-processing optimization issues: docs/grep-reference.md, docs/awk-reference.md, docs/sed-reference.md, docs/regex-reference.md (only when directly relevant)

Step 4: Provide or Apply Fixes

For each issue, include:

  1. Exact location from validator output (line number and snippet)
  2. Root cause
  3. Corrected code
  4. Why the change is safer or more portable
  5. Subsection-level citation (format below)

If the request includes patching files and write access is available, apply fixes in small batches grouped by issue type.

Step 5: Rerun Policy (Mandatory After Changes)

After each batch of edits, rerun the validator:

bash
bash scripts/validate.sh <script-path>

Rerun loop rules:

  1. Continue until no new errors are introduced.
  2. If warnings remain by design, document why they are intentionally accepted.
  3. If constraints prevent full resolution, report unresolved items with a clear next action.
  4. Always report the latest rerun exit code and remaining issue count.

Fallback Behavior

Use these branches only when the default flow cannot run as-is.

ConstraintFallback actionReporting requirement
shellcheck missing, wrapper availableLet scripts/validate.sh use scripts/shellcheck_wrapper.sh --cache automaticallyState that wrapper mode was used
shellcheck and wrapper unavailableRun syntax + custom checks only (validator does this)Explicitly call out reduced coverage and missing ShellCheck analysis
Python unavailable for wrapperSkip wrapper path, keep syntax + custom checksState why ShellCheck could not run
Target file is read-onlyProvide precise patch suggestions without editingMark response as "advisory only"
Target file missing or unreadableStop and request a valid file pathDo not fabricate results
Binary/non-text inputStop validationReport unsupported input type

Citation Guidance for Fixes

Use subsection-level citations for every non-trivial fix.

Required citation format:

text
Reference: docs/<file>.md -> <Section> -> <Subsection>

Examples:

  • Reference: docs/common-mistakes.md -> 1. Unquoted Variables -> Solution
  • Reference: docs/shellcheck-reference.md -> SC2164: Use || exit After cd
  • Reference: docs/shell-reference.md -> POSIX Best Practices -> 5. Avoid Bashisms

Citation rules:

  1. Cite the most specific section that justifies the fix.
  2. For ShellCheck findings, include both the SC#### code and the matching section.
  3. If no exact subsection exists, cite the closest section and state that the fix is inferred from that guidance.

Response Template

Use this structure for deterministic output:

  • Validation Results
  • Command: bash scripts/validate.sh <script-path>
  • Detected shell: <shell>
  • Exit code: <code>
  • Summary: <errors> errors, <warnings> warnings, <info> info
  • Issue: <short label> (Line <n>)
  • Problem:
    bash
    <problematic snippet>
  • Fix:
    bash
    <corrected snippet>
  • Why: <short explanation>
  • Reference: docs/<file>.md -> <Section> -> <Subsection>
  • Rerun command: bash scripts/validate.sh <script-path>
  • Exit code after fixes: <code>
  • Remaining issues: <count or none>

Example Flows

Fully Automated Environment

bash
# 1) Baseline validation
bash scripts/validate.sh examples/bad-bash.sh

# 2) Apply fixes to target script
# 3) Rerun validation
bash scripts/validate.sh examples/bad-bash.sh

Expected behavior: full syntax + ShellCheck + custom-check coverage, with iterative reruns until stable.

Deterministic CI Gate

bash
# Requires a system shellcheck binary.
bash scripts/run_ci_checks.sh

This runner enforces VALIDATOR_REQUIRE_SHELLCHECK=1 and VALIDATOR_SHELLCHECK_MODE=system so CI fails if the ShellCheck stage is skipped or unavailable.

Constrained Environment (No ShellCheck Runtime)

bash
# shellcheck unavailable and wrapper cannot run
bash scripts/validate.sh examples/bad-shell.sh

Expected behavior: syntax + custom checks still run. Report reduced coverage and list what must be revalidated once ShellCheck is available.

Validator Script Details

Scripts

  • scripts/validate.sh: primary validator entrypoint
  • scripts/shellcheck_wrapper.sh: optional ShellCheck fallback using a cached Python virtual environment

Detection and Ordering

Validation order in scripts/validate.sh:

  1. File checks (exists/readable/text)
  2. Shebang-based shell detection
  3. Syntax check
  4. ShellCheck (or fallback/skip behavior)
  5. Custom checks
  6. Summary with exit code

Exit Codes

  • 0: no issues found
  • 1: warnings found
  • 2: errors found

References

Load only what is needed:

  • docs/bash-reference.md
  • docs/shell-reference.md
  • docs/shellcheck-reference.md
  • docs/common-mistakes.md
  • docs/grep-reference.md
  • docs/awk-reference.md
  • docs/sed-reference.md
  • docs/regex-reference.md

Done Criteria

This skill update is complete when all are true:

  1. Trigger guidance is explicit (positive and non-trigger examples).
  2. Default workflow is deterministic and ordered.
  3. Fallback behavior is explicit for missing tooling and constrained environments.
  4. Fix explanations include subsection-level citations.
  5. Post-fix rerun policy is mandatory and reported with exit codes.
  6. Documentation supports both fully automated and constrained execution paths.

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 Validator AI skill do?

Validate, lint, audit, or fix bash/shell/.sh scripts via ShellCheck.

Why use Bash Script Validator on TypingMind?

Because you install it once and use it with any model. Bash Script Validator 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 Validator 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-validator. 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 Validator?

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 Validator?

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

Is the Bash Script Validator 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 👇