CtrlK
BlogDocsLog inGet started
Tessl Logo

bash-linux

Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.

59

Quality

69%

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 ./.agents/skills/bash-linux/SKILL.md

The canonical home for this skill is bash-linux in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

68%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.

A well-organized, highly actionable bash cheat sheet with copy-paste commands and a solid script template. Its main weaknesses are spending tokens on basics Claude already knows and offering no validation guidance around destructive commands.

Suggestions

Trim entries for commands Claude already knows (ls -la, ps aux, grep -r, env) and concentrate the skill on less-common or error-prone patterns that add value beyond Claude's existing bash knowledge.

Add validation/checkpoint notes around destructive operations — e.g., verify a PID with ps before kill -9, back up files before sed -i, and prefer rm with explicit paths — so the destructive entries carry safety guidance.

Consider moving the PowerShell comparison table and the bulk command reference into a separate references file, keeping SKILL.md as a lean overview with the script template and key patterns inline.

DimensionReasoningScore

Conciseness

The format is lean (tables and code blocks, no prose padding), but a large share of the content restates basic commands Claude already knows (ls -la, ps aux, grep -r), so not every token earns its place.

3 / 5

Actionability

Fully executable throughout: concrete command tables, copy-paste-ready script template with set -euo pipefail, and worked code blocks for common patterns like read-line-by-line and trap cleanup.

5 / 5

Workflow Clarity

This is a reference catalog with no multi-step workflow sequence or validation checkpoints, and destructive commands (kill -9, sed -i, rm -f) are listed without verify-before-act guidance, capping workflow clarity.

3 / 5

Progressive Disclosure

Single-file skill with ten well-numbered, clearly headed sections and no external bundle files; well-organized and navigable, though a 200-line reference could arguably split some tables into a separate file.

4 / 5

Total

15

/

20

Passed

Description

70%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 is concise, uses third person, and clearly answers both what and when with a distinct Bash/Linux niche. It is held back from the top band by topic-level rather than action-level specificity and an OS-only trigger clause.

DimensionReasoningScore

Specificity

Names the domain ('Bash/Linux terminal patterns') and several capability areas ('piping, error handling, scripting') but these read as topics rather than concrete actions like 'extract text' or 'fill forms'.

3 / 5

Completeness

Explicitly states both what ('Critical commands, piping, error handling, scripting') and when ('Use when working on macOS or Linux systems'), but the when is OS-only and could name the scripting tasks more specifically.

4 / 5

Trigger Term Quality

Natural terms users would say are present ('bash', 'Linux', 'macOS', 'terminal commands') with a clear 'Use when working on macOS or Linux systems' trigger, though synonyms like 'shell' or '.sh' are missing.

4 / 5

Distinctiveness Conflict Risk

'Bash/Linux terminal' is a clear niche with an OS-scoped trigger; minor overlap risk with general Unix coding or shell-scripting skills.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository
vudovn/ag-kit
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.