bash-pro

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

Quality

42%

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-pro/SKILL.md

Quality

Content

35%

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

The content is rich with executable Bash patterns but bloated and monolithic, re-explaining well-known concepts and tools, with a present-but-shallow workflow that lacks validation checkpoints and no progressive file structure.

Suggestions

Trim sections that restate Bash language features and tool descriptions Claude already knows; keep only non-obvious project-specific guidance to fix the conciseness score.

Promote a few representative one-liners into one or two complete, copy-paste runnable example scripts so actionability reaches 'copy-paste ready'.

Add an explicit validate/verify checkpoint in the Instructions workflow (e.g. 'Run shellcheck and bats; only proceed when both pass') for destructive-script operations.

Split the large tool catalogs, version-feature tables, and reference links into bundled reference files (e.g. TOOLS.md, REFERENCES.md) and point to them one level deep to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The ~300-line body is a monolithic bullet catalog that re-explains Bash language features and describes tools Claude already knows (ShellCheck, bats-core, bashly, basher) and even a reference list, with redundant patterns repeated across Approach, Advanced Techniques, and Common Pitfalls — matching the 'verbose; explains concepts Claude knows; padded' anchor.	1 / 3
Actionability	It offers many concrete, executable snippets (set -Eeuo pipefail, readarray -d '' files < <(find . -print0), version checks), but they are scattered one-liners and template fragments rather than complete, copy-paste-ready scripts, fitting 'some concrete guidance but incomplete; missing key details'.	2 / 3
Workflow Clarity	The Instructions section lists a clear 4-step sequence, but there is no explicit validation or verify-then-proceed checkpoint, and Bash scripts can be destructive, so per the guideline it is capped at 2 ('steps listed but validation gaps; checkpoints missing or implicit').	2 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets are empty) and everything is inline in one well-sectioned file; the only references are external web links, so it is organized but monolithic with reference material that should be split out — matching 'some structure but content that should be separate is inline'.	2 / 3
	Total	7 / 12 Passed

Description

50%

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 cleanly conveys the Bash defensive-scripting domain and its qualities, but stays at an attribute/expertise level rather than enumerating concrete actions and lacks an explicit 'Use when' trigger, capping most dimensions at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when writing, reviewing, or hardening Bash scripts for CI/CD, automation, or system utilities.' to lift completeness and distinctiveness.

Replace abstract expertise phrasing ('Master of...', 'Expert in...') with concrete action verbs the skill performs (e.g. 'Write, review, and harden Bash scripts; add strict mode, argument parsing, and Bats/ShellCheck checks').

Broaden trigger terms with common user phrasings like 'shell scripts', 'bash one-liners', and 'sh scripts' to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete domain ('defensive Bash scripting for production automation, CI/CD pipelines, and system utilities') and attributes ('safe, portable, and testable shell scripts'), but the actions are abstract ('Master of...', 'Expert in...') rather than the multiple concrete action verbs the score-3 anchor requires.	2 / 3
Completeness	It clearly answers 'what' but contains no explicit 'Use when...' trigger clause in the description field, so per the judging guideline completeness is capped at 2 ('has what, but when is missing or only implied').	2 / 3
Trigger Term Quality	Reasonably natural terms a user would say are present ('Bash scripting', 'CI/CD pipelines', 'system utilities', 'shell scripts'), but coverage misses common variations users actually utter (e.g. 'shell', 'bash one-liner', 'scripting'), matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The Bash/shell-scripting niche is fairly distinct, but without explicit triggers it could still overlap with a generic shell-scripting or CI/CD skill, matching 'somewhat specific but could still overlap with similar skills' rather than the explicit-trigger distinctiveness of a 3.	2 / 3
	Total	8 / 12 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: rmyndharis/antigravity-skills
Path: skills/bash-pro/SKILL.md
Commit: e63f7dd

Reviewed: about 4 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.