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.

44

1.45x
Quality

18%

Does it follow best practices?

Impact

87%

1.45x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/bash-pro/SKILL.md

The canonical home for this skill is bash-pro in rmyndharis/antigravity-skills

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 is a comprehensive reference document but fails as actionable guidance. It reads like a Bash encyclopedia rather than a focused skill, explaining concepts Claude already knows while burying useful patterns in overwhelming lists. The lack of clear workflows, validation steps, and progressive disclosure makes it difficult to apply in practice.

Suggestions

Reduce content by 70-80% by removing explanations of basic concepts (what tools do, how Bash features work) and keeping only project-specific patterns and preferences

Create a clear, numbered workflow with explicit validation checkpoints (e.g., '1. Write script → 2. Run ShellCheck → 3. Fix issues → 4. Run tests → 5. Only commit when all pass')

Split detailed content into separate reference files: TOOLS.md for tool configurations, PATTERNS.md for code patterns, TESTING.md for Bats examples

Provide one complete, executable example script demonstrating the key patterns rather than dozens of code fragments

DimensionReasoningScore

Conciseness

Extremely verbose at 400+ lines with extensive explanations of concepts Claude already knows (what ShellCheck does, how arrays work, basic Bash features). Lists every possible tool, technique, and pattern rather than focusing on essential guidance.

1 / 3

Actionability

Contains many concrete code snippets and commands that are executable, but they're scattered throughout massive lists rather than organized into coherent workflows. Examples are fragments rather than complete, copy-paste-ready scripts.

2 / 3

Workflow Clarity

The 4-step instruction workflow is extremely vague ('Apply strict mode and safe argument parsing', 'Implement core logic with defensive patterns'). No validation checkpoints, no feedback loops for error recovery, and no clear sequence for the many techniques listed.

1 / 3

Progressive Disclosure

Monolithic wall of text with no references to external files. All content is inline regardless of complexity. The References section at the end links to external resources but the skill itself should split detailed content (like the extensive tool lists) into separate files.

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 relies heavily on self-promotional language ('Master of', 'Expert in') rather than concrete capabilities. It fails to specify what actions the skill performs and completely lacks trigger guidance for when Claude should use it. The description would benefit from listing specific operations and adding explicit 'Use when...' clauses.

Suggestions

Replace vague expertise claims with specific actions (e.g., 'Write error-handling shell scripts, create portable bash functions, debug script failures, set up CI/CD shell automation').

Add an explicit 'Use when...' clause with trigger terms like 'bash script', 'shell script', '.sh file', 'cron job', 'shell command', 'automate with bash'.

Remove first-person-adjacent phrasing ('Master of', 'Expert in') and use third person action verbs describing what the skill does.

DimensionReasoningScore

Specificity

Uses vague, abstract language like 'Master of' and 'Expert in' without listing concrete actions. No specific operations are described - only broad categories like 'production automation' and 'system utilities'.

1 / 3

Completeness

Describes a vague 'what' (defensive Bash scripting) but completely lacks any 'when' clause or explicit trigger guidance. No 'Use when...' or equivalent instruction for when Claude should select this skill.

1 / 3

Trigger Term Quality

Contains some relevant keywords users might say ('Bash scripting', 'CI/CD pipelines', 'shell scripts') but missing common variations like 'bash script', '.sh files', 'shell commands', 'cron jobs', or specific operations users would request.

2 / 3

Distinctiveness Conflict Risk

The focus on 'Bash scripting' and 'shell scripts' provides some distinction, but 'CI/CD pipelines' and 'system utilities' are broad enough to overlap with DevOps, automation, or general scripting skills.

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.

Validation10 / 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
administrakt0r/AI-Agents-Safe-Coding-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.