bash-hygiene

Review, create, and validate Bash scripts when shell work needs strict mode, quoting safety, portability, or interpreter-compatible behavior.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./Skills/agent-ops/bash-hygiene/SKILL.md

Quality

Content

71%Weight 40%Scale 1-5

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

The content is well-structured and lean with strong progressive disclosure pointing to real reference files, plus an explicit validation feedback loop. Its main weakness is actionability: it describes what to check but rarely shows executable code or commands.

Suggestions

Add a short executable example or shellcheck command invocation under Workflow so the quoting/strict-mode guidance is copy-paste ready.

Show one concrete safe-vs-unsafe quoting snippet (e.g. array-based args vs string-built command) to ground the "Prefer argument arrays" bullet.

Tighten or merge the Philosophy and Anti-Patterns sections to reclaim tokens without losing the routing/safety signal.

Dimension	Reasoning	Score
Conciseness	The body is lean bullet-style prose that assumes Claude's competence and never over-explains basic shell concepts; kept off 5 by advisory sections like Philosophy and Anti-Patterns that could be trimmed.	4 / 5
Actionability	Guidance names concrete checks ("Check strict mode, quoting, arrays, traps, paths" and "Run shellcheck") but provides no executable code or command examples showing safe quoting patterns, leaving key details implicit.	3 / 5
Workflow Clarity	The Workflow section is a clear sequenced list and the Validation section includes an explicit fail-fast feedback loop ("stop at first failed gate; do not proceed until it is fixed and rerun"), though steps remain high-level rather than exact commands.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview with clearly signaled one-level-deep references to real bundle files (references/contract.yaml, references/evals.yaml, references/task-profile.json), each mapped to a stated purpose.	5 / 5
	Total	16 / 20 Passed

Description

75%Weight 40%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 is specific and trigger-rich, clearly answering both what and when with concrete shell-safety terms. It is concise and distinct, sitting just below the top anchor due to high-level action verbs and missing synonyms.

Dimension	Reasoning	Score
Specificity	"Review, create, and validate Bash scripts" names the domain plus three concrete actions; not a 5 because the actions stay high-level rather than enumerating specific concrete capabilities.	4 / 5
Completeness	It states both what (review/create/validate Bash scripts) and an explicit when clause ("when shell work needs strict mode, quoting safety, portability, or interpreter-compatible behavior"), but the when is a conditional clause rather than a dedicated "Use when" sentence with user-mention triggers.	4 / 5
Trigger Term Quality	"Bash scripts", "strict mode", "quoting safety", "portability" are natural terms a user would say, but common synonyms like "shell scripts", "sh", and file extensions are missing.	4 / 5
Distinctiveness Conflict Risk	"Bash scripts" with shell-specific triggers is a clear niche with minimal conflict risk, though it could overlap slightly with general coding skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Skills/agent-ops/bash-hygiene/SKILL.md
Commit: 2f91362

Reviewed: 1 day 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.