bash-scripting

Bash scripting workflow for creating production-ready shell scripts with defensive patterns, error handling, and testing.

Quality

44%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/bash-scripting/SKILL.md

Quality

Content

35%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 skill is a high-level workflow orchestrator that delegates all substantive content to other skills via vague 'Copy-Paste Prompts'. It lacks concrete, executable guidance—the only real code is a basic bash template. The repetitive phase structure inflates token count without adding proportional value, and the action items are generic checklists that Claude doesn't need spelled out.

Suggestions

Replace vague 'Copy-Paste Prompts' with actual concrete examples: show a real trap handler, a real retry pattern, a real Bats test case—not just instructions to invoke another skill.

Consolidate the 7 phases into a more concise workflow with inline code examples for the most critical patterns (strict mode, error handling, logging), cutting the repetitive Skills/Actions/Prompts sub-structure.

Add explicit validation checkpoints between phases (e.g., 'Run ShellCheck after Phase 3 before proceeding to error handling') with concrete commands.

Remove the 'When to Use This Workflow' section and generic action items like 'Define script purpose' and 'Identify inputs/outputs' that Claude already understands.

Dimension	Reasoning	Score
Conciseness	The skill is heavily padded with repetitive structure (each phase has identical sub-sections: 'Skills to Invoke', 'Actions', 'Copy-Paste Prompts') and lists obvious steps Claude already knows (e.g., 'Define script purpose', 'Identify inputs/outputs'). The 'When to Use This Workflow' section lists generic use cases that don't add value. Much of the content is boilerplate filler.	2 / 5
Actionability	The 'Copy-Paste Prompts' are just vague meta-instructions to invoke other skills (e.g., 'Use @bash-pro to design production-ready bash script') rather than concrete, executable guidance. The action items are high-level checklists ('Add trap handlers', 'Implement retry logic') without any actual code or specific commands. The only concrete, executable content is the script template at the bottom, which is a basic boilerplate.	2 / 5
Workflow Clarity	The phases are clearly sequenced and logically ordered, and there's a quality gates checklist at the end. However, there are no validation checkpoints between phases, no feedback loops for error recovery, and the steps within each phase are vague action items rather than concrete instructions. For a workflow involving script creation (which can involve destructive operations like deployment/backup scripts), the lack of explicit validation steps between phases is a gap.	3 / 5
Progressive Disclosure	The skill references many external skills (@bash-pro, @bash-defensive-patterns, @bats-testing-patterns, etc.) and related bundles, which suggests a multi-file structure. However, no bundle files are provided, so it's impossible to verify these references resolve. The SKILL.md itself is somewhat monolithic—7 nearly identical phase sections that could be condensed. The structure is present but not well-optimized.	3 / 5
	Total	10 / 20 Passed

Description

53%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.

The description identifies a clear domain (bash/shell scripting) and mentions several quality-oriented aspects, but it reads more like a category label than an actionable skill description. It lacks an explicit 'Use when...' clause and could benefit from more specific concrete actions and natural trigger terms users would employ.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases like 'Use when the user asks to write a bash script, create a shell script, or needs help with .sh files, shell automation, or command-line scripting.'

List more specific concrete actions such as 'generates argument parsing, adds signal trap handlers, creates shellcheck-compliant scripts, writes bats test cases.'

Include common synonyms and file extensions like '.sh files', 'bash script', 'shell command', 'CLI script' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (bash scripting) and mentions a few concrete aspects like 'defensive patterns, error handling, and testing,' but these are more like categories than specific actions. It doesn't list concrete actions like 'creates argument parsers, adds trap handlers, generates test suites.'	3 / 5
Completeness	Provides a clear 'what' (creating production-ready shell scripts with defensive patterns, error handling, and testing) but has no explicit 'when' clause. There is no 'Use when...' guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant terms like 'bash scripting,' 'shell scripts,' 'error handling,' and 'testing,' but misses common natural phrases users might say such as 'bash script,' '.sh file,' 'write a script,' 'shell command,' or 'shebang.' Coverage of synonyms and variations is limited.	3 / 5
Distinctiveness Conflict Risk	Fairly distinct by specifying 'bash scripting' and 'shell scripts' with a focus on production-readiness and defensive patterns. Could have minor overlap with general coding or scripting skills, but the specific focus on bash/shell with error handling and testing makes it mostly distinguishable.	4 / 5
	Total	13 / 20 Passed

Validation

90%

Warnings & errors only

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

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/bash-scripting/SKILL.md
Commit: 57c135b

Reviewed: 23 hours ago

Table of Contents

Discovery Implementation Validation

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.