linux-shell-scripting

This skill should be used when the user asks to "create bash scripts", "automate Linux tasks", "monitor system resources", "backup files", "manage users", or "write production shell scripts". It provides ready-to-use shell script templates for system administration.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/linux-shell-scripting/SKILL.md

Quality

Content

57%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.

A highly actionable catalog of executable, production-style bash templates, but it is a monolithic 500-line inlining that spends many tokens on trivial scripts and basics Claude already knows, and its destructive operations lack validation checkpoints. Splitting task-specific scripts into reference files and adding verification steps would materially improve it.

Suggestions

Trim or remove the Quick Reference tables and trivial one-liner scripts (Folder Size Checker, Network Interface Info, Common Script Patterns) — this is bash knowledge Claude already has and is pure token cost.

Add validation/dry-run checkpoints to destructive scripts: use 'find -mtime +N -print' before '-exec rm', 'rsync --dry-run' before '--delete', and verify the newest backup exists before rotating old ones out.

Split the 10 phases into one-level-deep reference files (e.g., references/backup-scripts.md, references/monitoring-scripts.md) and keep SKILL.md as a concise index with per-task pointers.

Dimension	Reasoning	Score
Conciseness	The ~500-line body inlines 20+ scripts, many of which restate boilerplate Claude already knows (e.g., Folder Size Checker is just 'du -sh \| sort', Network Interface Info is 'ip addr'), and the Quick Reference tables explain the shebang, 'chmod +x', and cron field format — pure padding. This matches 'noticeably verbose; several unnecessary explanations or padded sections' rather than the mostly-efficient anchor 3.	2 / 5
Actionability	Every section delivers complete, executable, copy-paste-ready bash scripts with variable definitions, comments, and sensible defaults (e.g., the encryption script handles encrypt/decrypt arguments with a usage guard). This matches 'fully executable; copy-paste ready code or commands'.	5 / 5
Workflow Clarity	The 'Core Workflow' is a categorized script library rather than a sequenced process, and destructive operations (backup rotation 'rm -r', data cleanup 'find -exec rm', 'rsync --delete') run with no validation or dry-run checkpoints — the rubric caps this at 3. It stays above anchor 2 because the phase organization and per-script comments do provide a coherent structure, and the Constraints section advises testing in non-production first.	3 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and all content lives in a single 500-line SKILL.md that clearly could be split into per-task reference files. Phase headers give it reasonable structure, matching 'some structure... content that should be separate is inline' rather than the minimal-structure anchor 2.	3 / 5
	Total	13 / 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.

A well-formed description with an explicit 'use when' clause, natural trigger phrases, and third-person voice. Its main weakness is that the capability statement is generic — naming the covered task categories (backups, monitoring, user management, log analysis) would push it to the top anchor.

Dimension	Reasoning	Score
Specificity	Concrete actions are named via trigger phrases ("create bash scripts", "backup files", "monitor system resources", "manage users"), but the capability statement itself ("ready-to-use shell script templates for system administration") stays generic and does not enumerate the task categories it covers. This matches 'lists several specific actions; minor gaps in coverage' rather than the comprehensive level 5, and is clearly above the minimal 1-2 action level.	4 / 5
Completeness	Both parts are explicitly present: 'when' via "should be used when the user asks to..." with concrete trigger phrases, and 'what' via "provides ready-to-use shell script templates". The 'when' is strong, but the 'what' could be more specific about which administration tasks are covered, matching anchor 4 ('when'/'what' could be more explicit) rather than the fully concrete anchor 5.	4 / 5
Trigger Term Quality	Natural phrases users would actually say ("automate Linux tasks", "monitor system resources", "write production shell scripts") give good keyword coverage. A few common variations are missing (.sh extensions, cron/scheduling, log analysis), so it falls just short of the comprehensive-synonym anchor 5 but above anchor 3's missing-variations profile.	4 / 5
Distinctiveness Conflict Risk	The bash/Linux system administration niche (backups, monitoring, user management) is mostly distinct with clear triggers. Minor overlap risk exists with generic automation or dedicated monitoring skills, fitting 'mostly distinct; minor overlap risk' rather than the minimal-conflict anchor 5.	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
skill_md_line_count	SKILL.md is long (505 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: zebbern/claude-code-guide
Path: skills/linux-shell-scripting/SKILL.md
Commit: a2e6ee3

Reviewed: 2 days 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.