CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

shell-scripting

Write, refactor, debug, and harden production-grade Bash and POSIX shell scripts. Use when creating automation scripts, deployment hooks, CLI utilities, system administration tools, data processing pipelines, or diagnosing shell errors and shellcheck warnings.

66

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

Highly actionable and well-structured: executable patterns throughout, a clear step sequence, a verification section, and a cleanly signaled one-level-deep reference. The main weakness is token efficiency - much of the body re-teaches shell fundamentals Claude already knows, which pads the skill considerably.

Suggestions

Move cheatsheet-style reference material that Claude already knows (file test operator lists, grep flag glossary, basic redirection mechanics, elementary parameter expansion) out of SKILL.md and into references/bash-patterns.md.

Trim tutorial explanations (e.g., the flag-by-flag table for set -euo pipefail, integer comparison operators) down to the pattern plus a one-line note, keeping the skill focused on the non-obvious defensive patterns (subshell trap, nullglob, sed -i portability, trap cleanup).

Add an explicit feedback loop in the Verification section: when bash -n or shellcheck reports issues, fix and re-run until clean, mirroring the validate-fix-retry structure.

DimensionReasoningScore

Conciseness

The body spends substantial space on fundamentals Claude already knows: a table explaining each `set -euo pipefail` flag, a full list of file test operators (`[[ -f ]]`, `[[ -d ]]`, ...), grep flag glossaries (-q, -E, -F, -v, -o), basic redirection mechanics (`command > output.log 2>&1`, here-docs), and elementary parameter expansion/integer-test operators. These are several padded tutorial sections rather than incidental over-explanation, matching the 'noticeably verbose' anchor; the genuinely non-obvious material (subshell variable trap, nullglob, sed -i portability, trap cleanup) is a minority of the file.

2 / 5

Actionability

Nearly every section ships copy-paste-ready, executable code: the strict-mode header, array idioms, getopts and hybrid argument parsers, the trap-based cleanup function, parallel-job orchestration, and the structured logging functions, covering the common cases for production shell scripting.

5 / 5

Workflow Clarity

Steps 1-11 are clearly sequenced and the Verification section provides explicit checkpoints with expected outputs (bash -n, shellcheck, bash -x, unset-variable and trap tests). It falls short of the top anchor because there is no explicit fix-and-retry feedback loop tying validation failures back into the workflow.

4 / 5

Progressive Disclosure

A single real companion reference (`references/bash-patterns.md`) is clearly signaled early and is one level deep, with a sensible split: methodology in SKILL.md, templates and one-liners in the reference. Minor gap: cheatsheet-style material inlined in the body (grep flags, test operator lists, redirection basics) overlaps what the reference file is for.

4 / 5

Total

15

/

20

Passed

Description

92%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 strong description: third-person voice, explicit what-and-when structure, concrete actions, and natural trigger phrases covering the main use cases. Only minor keyword variations are absent.

DimensionReasoningScore

Specificity

"Write, refactor, debug, and harden production-grade Bash and POSIX shell scripts" lists four concrete, comprehensive actions on a clearly named domain, matching the top anchor for multiple specific concrete actions.

5 / 5

Completeness

It explicitly answers both what ("Write, refactor, debug, and harden...") and when ("Use when creating automation scripts... or diagnosing shell errors and shellcheck warnings") with concrete trigger phrases.

5 / 5

Trigger Term Quality

"automation scripts, deployment hooks, CLI utilities, system administration tools, data processing pipelines, or diagnosing shell errors and shellcheck warnings" gives good natural-phrase coverage, but a few common variations users say (e.g. "cron jobs", "zsh", ".sh") are missing.

4 / 5

Distinctiveness Conflict Risk

"Bash and POSIX shell scripts" carves out a clear niche with distinct triggers like "shellcheck warnings"; overlap with other skills is minimal.

5 / 5

Total

19

/

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

skill_md_line_count

SKILL.md is long (732 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

administrakt0r/pro-skills-repo-administraktor

Path

skills/infrastructure-skills/shell-scripting/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.