CtrlK
BlogDocsLog inGet started
Tessl Logo

os-scripting

Operating system and shell scripting troubleshooting workflow for Linux, macOS, and Windows. Covers bash scripting, system administration, debugging, and automation.

45

Quality

48%

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 ./skills/os-scripting/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

46%Scale 1-5

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

This skill is a comprehensive but overly verbose reference catalog for OS/shell scripting troubleshooting. While it contains genuinely useful executable code examples (script template, Bats tests, diagnostic commands), it suffers from significant bloat — much of the content covers basic sysadmin knowledge Claude already possesses. The 7-phase workflow lacks true interconnection, validation checkpoints between phases, and error recovery loops, reading more like independent reference sections than a cohesive workflow.

Suggestions

Drastically reduce content by removing commands and concepts Claude already knows (basic Linux commands, what cron is, networking basics) and focus only on project-specific patterns, gotchas, or non-obvious configurations.

Split the monolithic file into separate bundle files (e.g., DIAGNOSTICS.md, SCRIPT_TEMPLATE.md, TESTING.md) and keep SKILL.md as a concise overview with clear references.

Add explicit validation checkpoints and feedback loops between phases — e.g., 'If ShellCheck reports SC2086, fix quoting before proceeding to Phase 3' — to create a true workflow rather than a reference catalog.

Remove or consolidate the repetitive 'Copy-Paste Prompts' and 'Skills to Invoke' sections, which add little actionable value and inflate the document.

DimensionReasoningScore

Conciseness

Extensively verbose with many sections that explain concepts Claude already knows (what uname does, how cron works, basic networking commands). The 7-phase workflow is heavily padded with lists of obvious actions like 'Identify symptoms' and 'Check system logs'. The 'Copy-Paste Prompts' sections add little value and repeat throughout. Much of this content is general sysadmin knowledge Claude already possesses.

2 / 5

Actionability

Contains concrete, executable code examples throughout — the script template is copy-paste ready, ShellCheck commands are specific, Bats test examples are functional, and diagnostic commands are real. However, the skill is more of a reference catalog of commands than targeted guidance for specific scenarios, and the 'Skills to Invoke' references are abstract pointers rather than actionable instructions.

4 / 5

Workflow Clarity

The 7 phases provide a clear sequence, and there's a quality gates checklist at the end. However, there are no explicit validation checkpoints between phases, no feedback loops for error recovery (e.g., what to do if ShellCheck finds issues that can't be auto-fixed), and the phases feel like independent reference sections rather than a connected workflow with decision points.

3 / 5

Progressive Disclosure

This is a monolithic ~300-line file with no bundle files to support it. The content for each phase (diagnostic commands, script templates, testing patterns, troubleshooting scenarios) should be split into separate reference files. References to skills like '@bash-pro' and '@systematic-debugging' are mentioned but there's no actual bundle structure to support progressive disclosure.

2 / 5

Total

11

/

20

Passed

Description

50%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 domain and lists broad capability categories but lacks concrete actions, natural trigger terms, and an explicit 'Use when...' clause. Its breadth across three operating systems and multiple disciplines creates overlap risk with more focused skills. It would benefit significantly from specific actions, user-facing trigger phrases, and explicit selection guidance.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases like 'Use when the user asks about shell scripts, terminal commands, cron jobs, file permissions, environment variables, or system configuration issues.'

Replace broad categories like 'system administration' and 'automation' with concrete actions such as 'debug shell script errors, configure cron jobs, manage file permissions, write startup scripts, troubleshoot environment variables.'

Include natural synonyms and related terms users would say: 'terminal', 'command line', 'CLI', '.sh files', 'PowerShell', 'zsh', 'chmod', 'grep', 'sed'.

DimensionReasoningScore

Specificity

Names the domain (OS/shell scripting) and lists several broad action categories (bash scripting, system administration, debugging, automation), but these are high-level categories rather than concrete specific actions like 'parse log files' or 'write cron jobs'.

3 / 5

Completeness

Has a reasonable 'what' (troubleshooting workflow covering bash scripting, sysadmin, debugging, automation) but lacks an explicit 'when' clause. There is no 'Use when...' guidance, which per the rubric caps this at 3.

3 / 5

Trigger Term Quality

Includes some relevant keywords like 'bash scripting', 'Linux', 'macOS', 'Windows', 'shell scripting', and 'system administration', but misses many natural user phrases like 'terminal', 'command line', 'CLI', 'cron', 'permissions', 'environment variables', '.sh files', 'PowerShell', 'zsh'.

3 / 5

Distinctiveness Conflict Risk

The scope is quite broad—covering three operating systems and multiple domains (scripting, sysadmin, debugging, automation) creates overlap risk with dedicated skills for any of those individual areas. 'Troubleshooting workflow' adds some specificity but the breadth undermines distinctiveness.

3 / 5

Total

12

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.