CtrlK
BlogDocsLog inGet started
Tessl Logo

windows-shell-reliability

Reliable command execution on Windows: paths, encoding, and common binary pitfalls.

50

Quality

55%

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/AI-Agents-Safe-Coding-Skills/skills/windows-shell-reliability/SKILL.md

The canonical home for this skill is windows-shell-reliability in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 solid reference skill that efficiently covers Windows shell reliability patterns with concrete examples and good use of comparison tables. The content is well-organized, mostly concise, and actionable. Minor improvements could be made by trimming a few obvious statements and making troubleshooting fixes more specific/executable.

DimensionReasoningScore

Conciseness

Generally efficient with good use of tables to compress information. Minor over-explanations exist (e.g., 'Windows paths often contain spaces' is obvious to Claude, and the 'When to Use' section adds little value), but overall the content is well-condensed and avoids explaining basic concepts at length.

4 / 5

Actionability

Provides concrete commands, correct/incorrect comparisons, and specific PowerShell syntax. Most guidance is directly executable. Minor gaps: some entries like the long path fix just mention the prefix without a concrete usage example, and the troubleshooting table fixes are somewhat vague ('fix PATH', 'run as Admin').

4 / 5

Workflow Clarity

This is primarily a reference/patterns skill rather than a multi-step workflow, so the single-purpose exception applies. The content is well-organized into clear sections with logical grouping. The encoding section includes conditional guidance (check PowerShell version first), which serves as a lightweight decision checkpoint. No destructive batch operations require validation loops.

4 / 5

Progressive Disclosure

Well-structured with clear numbered sections and tables that make scanning easy. The content length (~100 lines) is appropriate for a single file with no need for external references. Sections are logically ordered from most critical (encoding, paths) to supplementary (troubleshooting). Minor improvement possible: the 'When to Use' section could be trimmed or removed since the title and description already convey scope.

4 / 5

Total

16

/

20

Passed

Description

36%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 a useful niche (Windows command execution quirks) but is too terse and abstract to be effective for skill selection. It lacks concrete actions, a 'Use when...' clause, and natural trigger terms that users would employ when seeking help with Windows-specific command issues.

Suggestions

Add a 'Use when...' clause with trigger terms like 'Use when running shell commands on Windows, dealing with PowerShell encoding, cmd.exe path escaping, or subprocess execution on Windows.'

Replace vague category labels ('paths, encoding, binary pitfalls') with concrete actions such as 'Escapes special characters in Windows file paths, configures UTF-8 encoding for PowerShell/cmd, resolves issues with executable invocation and quoting.'

Include natural keywords and synonyms users would say: 'PowerShell', 'cmd', 'batch', '.bat', '.ps1', 'subprocess', 'terminal', 'shell script on Windows'.

DimensionReasoningScore

Specificity

Names the domain (Windows command execution) and hints at topics (paths, encoding, binary pitfalls) but these are categories, not concrete actions. No specific actions like 'escapes special characters in paths' or 'handles UTF-8 encoding in PowerShell' are listed.

2 / 5

Completeness

Provides a vague 'what' (reliable command execution covering paths, encoding, pitfalls) but has no 'when' clause at all. There is no 'Use when...' guidance, which per the rubric should cap completeness at 3, and the 'what' itself is not very clear, placing this at a 2.

2 / 5

Trigger Term Quality

Includes some relevant keywords like 'Windows', 'paths', 'encoding', and 'command execution', but misses natural user phrases like 'PowerShell', 'cmd', 'batch script', 'subprocess', '.exe', 'shell command', or 'terminal'. Users might not naturally say 'binary pitfalls'.

3 / 5

Distinctiveness Conflict Risk

The Windows-specific focus provides some distinctiveness, but 'command execution' and 'paths' are broad enough to overlap with general shell/terminal skills, cross-platform scripting skills, or file system navigation skills. The mention of 'encoding' and 'binary pitfalls' adds some niche specificity but not enough to be clearly distinct.

3 / 5

Total

10

/

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.