CtrlK
BlogDocsLog inGet started
Tessl Logo

shell-script-reviewer

Reviews Bash, Zsh, and Fish shell scripts for bugs, security vulnerabilities, portability issues, and style violations against the Google Shell Style Guide, ShellCheck, BashPitfalls, and shell-specific idiom conventions. Use when the user asks to review, audit, lint, or improve a .sh/.bash/.zsh/.fish file, or pastes shell script content for feedback.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

92%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a high-quality, well-structured skill that provides comprehensive, actionable guidance for shell script review across multiple dialects. Its strengths are the clear multi-step workflow with validation checkpoints, excellent progressive disclosure via reference files, and concrete executable commands throughout. The only minor weakness is slight verbosity in a few explanatory passages, but this is justified by the complexity of the multi-dialect review task.

DimensionReasoningScore

Conciseness

The skill is largely efficient and avoids explaining basic concepts Claude already knows. There are minor areas of verbosity—such as the repeated emphasis on the error-handling stance and some explanatory phrasing that could be tightened—but overall it respects token budget well for a complex, multi-dialect review skill.

4 / 5

Actionability

The skill provides fully concrete, executable guidance: specific script paths for detection and static analysis, exact commands for shfmt and shellcheck, a detailed output skeleton with before/after code snippets, and clear handling of edge cases (pasted content, --fix flag, directory recursion). Every step is copy-paste actionable.

5 / 5

Workflow Clarity

The five-step workflow is clearly sequenced (detect dialect → run static analysis → manual review in priority order → structured output → escalation). Validation checkpoints are explicit: re-running static analysis after --fix, flagging disagreements as 'needs runtime verification' with BATS test recommendations, and the escalation rule provides a clear feedback loop for uncertain findings.

5 / 5

Progressive Disclosure

The skill is an excellent overview that delegates detailed content to six clearly-signaled reference files via a well-organized table with explicit 'when to read' guidance. References are one level deep, clearly named, and the instruction to 'load only the file(s) relevant' prevents unnecessary context loading. The structure is easy to navigate with clear section headers.

5 / 5

Total

19

/

20

Passed

Description

100%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that clearly communicates what the skill does, when to use it, and what distinguishes it from other skills. It uses third person voice, includes comprehensive trigger terms with file extensions and natural user phrases, and references specific standards that ground the skill's scope. It serves as a strong example of a well-crafted skill description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: reviewing for bugs, security vulnerabilities, portability issues, and style violations. Also names specific standards (Google Shell Style Guide, ShellCheck, BashPitfalls, shell-specific idiom conventions), providing comprehensive coverage of what the skill does.

5 / 5

Completeness

Clearly answers both 'what' (reviews shell scripts for bugs, security vulnerabilities, portability issues, and style violations against named standards) and 'when' (explicit 'Use when' clause with concrete trigger phrases like 'review, audit, lint, or improve' and mentions pasting shell script content for feedback).

5 / 5

Trigger Term Quality

Excellent coverage of natural trigger terms: 'review', 'audit', 'lint', 'improve', shell types (Bash, Zsh, Fish), file extensions (.sh, .bash, .zsh, .fish), 'shell script', 'feedback', 'bugs', 'security vulnerabilities'. These are terms users would naturally use when requesting shell script review.

5 / 5

Distinctiveness Conflict Risk

Highly distinctive with a clear niche: shell script review specifically. The mention of specific shell types (Bash, Zsh, Fish), specific file extensions, and specific standards (Google Shell Style Guide, ShellCheck, BashPitfalls) makes it very unlikely to conflict with general code review or other language-specific skills.

5 / 5

Total

20

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

9

/

11

Passed

Repository
rikdc/ai-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.