CtrlK
BlogDocsLog inGet started
Tessl Logo

bash-pro

Master of defensive Bash scripting for production automation, CI/CD pipelines, and system utilities. Expert in safe, portable, and testable shell scripts.

27

Quality

18%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/antigravity-awesome-skills/skills/bash-pro/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

14%Scale 1-3

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

This skill reads as an exhaustive Bash reference manual rather than a focused, actionable skill document. It covers an enormous breadth of topics—many of which Claude already knows—without providing clear workflows, complete executable examples, or progressive disclosure. The content would benefit dramatically from being restructured into a concise overview with detailed sections split into bundle files.

Suggestions

Reduce the SKILL.md to a concise overview (under 80 lines) with a complete script template showing strict mode, argument parsing, cleanup traps, and logging in one executable example, then move detailed sections (tools, advanced techniques, CI/CD, security) into separate bundle files.

Replace the vague 4-step Instructions with a concrete workflow including validation checkpoints, e.g.: '1. Create script with strict mode header → 2. Add argument parsing with getopts → 3. Run ShellCheck: `shellcheck --enable=all script.sh` → 4. Fix issues and re-run → 5. Add Bats tests → 6. Verify tests pass before committing.'

Remove content Claude already knows (basic parameter expansion, brace expansion, conditional execution, what tools like jq and curl do) and focus only on project-specific conventions, non-obvious patterns, and opinionated decisions.

Add a complete, copy-paste-ready script template that demonstrates the key patterns (strict mode, argument parsing, logging, cleanup traps, error handling) working together in a real example.

DimensionReasoningScore

Conciseness

Extremely verbose at 300+ lines with extensive lists of bullet points covering topics Claude already knows well (basic Bash features, parameter expansion, brace expansion, conditional execution). Many sections read like a Bash textbook rather than adding novel, targeted guidance. Significant redundancy across sections (e.g., error trapping mentioned in multiple places).

1 / 3

Actionability

Contains many concrete code snippets and specific commands (e.g., strict mode, mktemp patterns, find -print0 idioms), but most are isolated one-liners rather than executable, complete examples. No full script template or copy-paste-ready starter is provided. The 'Instructions' section is only 4 vague steps without concrete implementation details.

2 / 3

Workflow Clarity

The 4-step Instructions section is extremely vague ('Define script inputs, outputs, and failure modes', 'Implement core logic with defensive patterns') with no concrete sequencing, validation checkpoints, or feedback loops. For a skill involving destructive operations (file manipulation, CI/CD pipelines), there are no explicit validation steps in any workflow. The content is organized as reference lists rather than actionable workflows.

1 / 3

Progressive Disclosure

Monolithic wall of text with no bundle files to offload detailed content. Sections like 'Advanced Techniques', 'Essential Tools', 'Modern Bash Features', 'References & Further Reading' could all be separate files. Everything is inlined into one massive document with no layered structure or navigation aids.

1 / 3

Total

5

/

12

Passed

Description

22%Scale 1-3

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 description reads more like a resume headline than a functional skill description. It relies on self-aggrandizing language ('Master of', 'Expert in') rather than concrete actions, lacks any explicit trigger guidance for when Claude should select this skill, and provides insufficient detail to distinguish it from other DevOps or scripting-related skills.

Suggestions

Replace vague claims with specific actions, e.g., 'Writes defensive Bash scripts with error handling, generates CI/CD pipeline configurations, creates portable shell utilities with input validation and logging.'

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for help writing Bash scripts, shell automation, CI/CD pipeline scripts, cron jobs, or .sh files.'

Remove first-person-style self-descriptions ('Master of', 'Expert in') and use third-person action verbs ('Generates', 'Creates', 'Validates').

DimensionReasoningScore

Specificity

The description uses vague, self-congratulatory language like 'Master of' and 'Expert in' without listing any concrete actions. Terms like 'defensive Bash scripting', 'production automation', and 'system utilities' are abstract domains, not specific capabilities like 'write error-handling wrappers' or 'generate CI/CD pipeline scripts'.

1 / 3

Completeness

The description vaguely addresses 'what' (Bash scripting for automation/CI/CD) but never answers 'when' — there is no 'Use when...' clause or equivalent explicit trigger guidance. Per the rubric, a missing 'Use when' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1.

1 / 3

Trigger Term Quality

Contains some relevant keywords users might say: 'Bash', 'CI/CD pipelines', 'shell scripts', 'automation'. However, it misses common variations like 'sh', '.sh files', 'cron jobs', 'deploy scripts', 'shellcheck', or specific actions users would request.

2 / 3

Distinctiveness Conflict Risk

The mention of 'Bash scripting' and 'CI/CD pipelines' provides some specificity, but 'production automation' and 'system utilities' are broad enough to overlap with general DevOps, infrastructure, or scripting skills. The lack of concrete triggers increases conflict risk.

2 / 3

Total

6

/

12

Passed

Validation

90%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
popey/claude-code-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.