CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bash-pro

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

1.45x
Quality

61%

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 ./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

50%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 rich with genuinely concrete, executable Bash patterns and well-sectioned, but it is significantly over token budget: it reiterates basic Bash knowledge Claude already has, repeats guidance across sections, and inlines ~150 lines of tool/version/bibliography reference material that belongs in separate files. The workflow section provides a sequence but lacks validation checkpoints and feedback loops.

Suggestions

Cut restatements of basic Bash knowledge (brace expansion, && ||, heredoc behavior, $() vs backticks) and deduplicate guidance repeated across Approach, Safety, Advanced Techniques, and Common Pitfalls (mktemp/traps, mapfile, version checks).

Move the Essential Tools catalog, Dependency Management, Modern Bash 5.x feature lists, and external-links bibliography into references/ files (e.g., references/tools.md, references/modern-bash.md) linked one level deep from SKILL.md, keeping the body to core defensive patterns.

Strengthen the Instructions workflow with explicit validation checkpoints and a feedback loop, e.g., 'write script → run shellcheck && shfmt -d → fix findings → bats test/ → only then ship', rather than listing testing only as a final step.

DimensionReasoningScore

Conciseness

The ~300-line body restates substantial Bash knowledge Claude already has (e.g., 'Conditional Execution: cmd1 && cmd2 run cmd2 only if cmd1 succeeds', 'Brace Expansion: touch file{1..10}.txt', quote variables, prefer printf to echo, $() over backticks) and repeats the same guidance across sections — mktemp/cleanup traps appear in Approach, Safety, Advanced Techniques, and Common Pitfalls; mapfile/readarray and Bash version checks each appear three-plus times. This matches anchor 2 ('noticeably verbose; several unnecessary explanations or padded sections') — genuinely useful material exists, so it is not the severe padding of anchor 1, but the redundancy and basic-concept restatement go beyond anchor 3's 'some unnecessary explanation'.

2 / 5

Actionability

Abundant concrete, executable snippets: 'set -Eeuo pipefail', 'SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)"', 'find -print0 | while IFS= read -r -d '' file; do ...; done', 'readarray -d '' files < <(find . -print0)', a working log_info() function, and 'jq -n --arg key "$value"'. A few entries are elliptical (e.g., the uname case statement and sed -i GNU/BSD note use literal '...'), and there is no complete end-to-end example script, which keeps it at anchor 4 rather than 5's 'specific examples cover the common cases' with fully copy-paste-ready coverage.

4 / 5

Workflow Clarity

The Instructions section gives a rough 4-step sequence (define inputs/failure modes, apply strict mode and parsing, implement defensive logic, add Bats/ShellCheck tests), but the steps are high-level and generic — structurally equivalent to the anchor-3 example ('1. Unpack 2. Edit 3. Repack 4. Test the output') — with no explicit validation checkpoints or feedback loops (validate → fix → retry) during the work, despite the skill covering destructive operations (rm -rf --, timeout). Testing appears only as a final step with no error-recovery loop, so it cannot reach anchor 4.

3 / 5

Progressive Disclosure

The body has clear section headers (good structure, above anchor 2's 'no section headers' example), but it is a monolithic ~300-line file where reference-style material that clearly belongs in separate files — the Essential Tools catalog, Dependency Management, Modern Bash 5.x feature lists, and the external-links bibliography — is fully inlined. No bundle files exist (no references/, scripts/, or assets/ directories) and no paths point to deeper material, matching anchor 3: 'some structure... content that should be separate is inline'.

3 / 5

Total

12

/

20

Passed

Description

56%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 identifies its niche clearly and in third person with decent trigger keywords, but it is persona-styled ('Master of', 'Expert in') rather than action-stated and completely lacks a 'Use when...' trigger clause. Adding concrete verbs and explicit trigger conditions would bring it in line with the good examples.

Suggestions

Add an explicit trigger clause, e.g. 'Use when writing, reviewing, or debugging Bash scripts, hardening shell scripts for CI/CD, or when the user mentions shell scripting, .sh files, or Bash.'

Replace persona claims with concrete actions: 'Writes, reviews, and hardens Bash scripts: strict mode, safe argument parsing, mktemp/trap cleanup, Bats tests, and ShellCheck-clean output.'

Include common user phrasings and extensions ('shell script', 'sh', '.sh', 'bash script') to improve trigger-term coverage and distinctiveness.

DimensionReasoningScore

Specificity

The description names the domain ('defensive Bash scripting', 'production automation, CI/CD pipelines, and system utilities') but contains no concrete actions — 'Master of' and 'Expert in' are persona claims, not capabilities like 'write', 'review', or 'harden' shell scripts. It matches anchor 2 ('names the domain but actions are minimal or generic') rather than 3, which requires 1-2 concrete listed actions; it sits above anchor 1 because the domain is clearly and specifically identified.

2 / 5

Completeness

The 'what' is discernible (defensive/safe/portable/testable Bash scripting for automation, CI/CD, and system utilities), but the 'when' is entirely absent — there is no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. It is not a 2 because the 'what' is clearer and more domain-specific than the vague-what example ('Use when working with documents').

3 / 5

Trigger Term Quality

Solid natural keyword coverage: 'Bash', 'shell scripts', 'automation', 'CI/CD', 'system utilities' — phrases users would plausibly say. Missing common variations such as 'shell', 'sh', '.sh', or 'scripting' keeps it below anchor 5's 'comprehensive coverage including synonyms and file extensions', but it is well above anchor 3's single-keyword example ('Works with PDF files').

4 / 5

Distinctiveness Conflict Risk

Bash scripting for production automation is a clear niche with distinct triggers ('Bash', 'shell scripts', 'CI/CD'), unlikely to fire for unrelated skills. Minor overlap risk remains with general shell/POSIX or generic automation skills, matching anchor 4 ('mostly distinct; minor overlap risk with closely related skills') rather than 5's 'minimal conflict risk'. Voice is correctly third person ('Master of', 'Expert in'), so no voice penalty applies.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/bash-pro/SKILL.md

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.