CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

shell-script-development

This skill should be used when the user asks to "create a bash script", "write a shell script", or mentions shell scripting conventions.

63

Quality

79%

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/toolkit/skills/shell-script-development/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%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 body is an exemplary lean, single-purpose skill: concrete template, specific conventions, ready-to-use status patterns, and a memorable post-creation reminder, all within ~48 lines and free of filler. Its only dependency for context is that the frontmatter description — not the body — carries the burden of explaining what the skill is for.

DimensionReasoningScore

Conciseness

The body is ~48 lines with zero padding: a copy-paste template, a compact conventions table, four status-output one-liners, and a one-line chmod reminder. It assumes Claude's competence (no explanation of what bash, shebangs, or ANSI colors are), so every token earns its place — the 'lean and efficient' anchor.

5 / 5

Actionability

Everything is executable and copy-paste ready: a complete template with shebang, 'set -e -o pipefail', and color variables; a conventions table with concrete example names ('model', 'dir', 'count', 'green', 'red', 'nc'); and four ready-made echo commands covering the common status cases. The '# Script logic here' comment is an intentional template slot, not a gap.

5 / 5

Workflow Clarity

This is a simple, single-purpose skill under 50 lines, and the single action — apply the template and conventions when writing a script — is unambiguous, with a clear post-creation step ('chmod +x script.sh' before use) called out under 'Important'. No destructive or batch operations exist that would require validation checkpoints, so the simple-skill exception applies.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references, and none exist (no references/, scripts/, or assets/ directories — nothing in the body points to missing files). The four well-labeled sections (Template, Conventions, Status Output Patterns, Important) organize the content cleanly, which satisfies the under-50-lines rule for a top score.

5 / 5

Total

20

/

20

Passed

Description

47%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 has a clear, explicit trigger clause with naturally phrased quoted phrases, but it omits any statement of what the skill actually does. Adding a one-sentence capability summary (e.g., 'Create shell scripts following consistent conventions for safety settings, naming, and colored status output') before the trigger clause would fix the main weakness.

Suggestions

Lead with a 'what' statement in third person, e.g., 'Creates bash/shell scripts with consistent conventions: safe shell options, lowercase variable naming, and colored status output.'

Broaden trigger coverage with common variations such as '.sh files', 'bash scripting', or 'make a script'.

Keep the quoted natural trigger phrases — they are the description's strongest asset.

DimensionReasoningScore

Specificity

The description names the domain ("bash script", "shell script", "shell scripting conventions") but states no capabilities of the skill itself — it never says what the skill does (e.g., apply conventions, provide a template, follow safety patterns). This matches the anchor 'Names the domain but actions are minimal or generic'; it is above 1 because the quoted phrases are domain-specific rather than pure abstraction, but below 3 because there is no enumerated action the skill performs.

2 / 5

Completeness

The 'when' is explicit ('This skill should be used when the user asks to...'), but the 'what' is entirely absent — the skill's purpose (conventions, templates, status output patterns) is never stated. This is the mirror of anchor 3 ('only when present without what', per anchor 2's example 'Use when working with documents'). The explicit trigger guidance satisfies the 'Use when...' clause, but without a 'what' it cannot exceed 2.

2 / 5

Trigger Term Quality

Natural phrases users would actually say are quoted directly: "create a bash script", "write a shell script", "shell scripting conventions". This fits 'Good keyword coverage; a few natural terms missing' — absent are common variations such as '.sh', 'make a script', 'bash', or 'shell command'. Not 5 because that anchor requires comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

Triggers are narrowly scoped to bash/shell scripting, so it is 'mostly distinct; minor overlap risk' — it could still fire alongside a general 'scripting' or 'python scripting' skill since neither '.sh' nor 'bash' alone disambiguates all cases. It is above 3 because 'bash script'/'shell script' are clearly niche triggers, but below 5 because a sibling general-scripting-conventions skill would still overlap.

4 / 5

Total

12

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

dwmkerr/claude-toolkit

Path

plugins/toolkit/skills/shell-script-development/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.