CtrlK
BlogDocsLog inGet started
Tessl Logo

windows-shell-reliability

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

52

Quality

58%

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-claude/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

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.

The content is a well-structured, actionable reference of Windows shell patterns with executable commands and tight tables. Its main weakness is the absence of validation/verification checkpoints around the destructive commands it documents, which caps workflow clarity.

Suggestions

Add validation/verification guidance around destructive commands (e.g. check the path exists and confirm before Remove-Item -Force, or test in a non-destructive form first).

Complete the partial command examples by removing ellipses (e.g. show a full 'dotnet build "..." ' invocation) so examples are copy-paste ready.

Consider splitting the larger reference tables (binary/cmdlet pitfalls, troubleshooting) into a separate reference file to keep SKILL.md a lean overview.

DimensionReasoningScore

Conciseness

The body is lean — tables of wrong/correct commands, brief rules, and short code patterns with minimal padding; only minor explanatory asides (e.g. 'Windows paths often contain spaces') could be trimmed.

4 / 5

Actionability

Concrete, executable commands throughout (dotnet build --no-restore, Remove-Item -Force, $env:VARIABLE, Get-Content | Set-Content -Encoding utf8) with wrong-vs-correct tables; a few examples use ellipses ('build ...') leaving minor gaps.

4 / 5

Workflow Clarity

This is a patterns reference rather than a sequenced workflow, and it lists destructive operations (Remove-Item -Force, del) without any validation or verification checkpoints, so per the rubric workflow clarity is capped at 3.

3 / 5

Progressive Disclosure

Well-organized into seven numbered sections with clear headers and tables and no unnecessary nested references; at ~99 lines it slightly exceeds the simple-skill threshold, so a couple of the larger tables could be split out, leaving minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

48%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 and names a clear Windows-shell niche, but it lacks concrete action verbs and any explicit 'Use when' trigger guidance. Adding natural trigger terms (PowerShell, CMD) and a when-to-use clause would lift the weakest dimensions.

Suggestions

Add an explicit 'Use when ...' clause naming the situations that should trigger this skill (e.g. running commands on Windows, PowerShell/CMD encoding or path issues).

Replace topic nouns with concrete action verbs (e.g. 'Quote paths with spaces, fix encoding in redirected output, choose PowerShell cmdlets over CMD equivalents').

Include natural user vocabulary such as 'PowerShell' and 'CMD' alongside 'Windows' to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain ('command execution on Windows') and lists concerns (paths, encoding, binary pitfalls), but uses no concrete action verbs — actions are minimal and the listed items are topics rather than capabilities.

2 / 5

Completeness

Provides a clear 'what' (reliable command execution on Windows with listed focus areas) but has no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes relevant terms (Windows, command execution, paths, encoding, binary) but omits the natural phrases users actually say such as 'PowerShell', 'CMD', or 'running commands on Windows'.

3 / 5

Distinctiveness Conflict Risk

The Windows-specific shell niche is fairly distinct with minor overlap risk against generic shell or cross-platform command skills; it would not commonly trigger for the wrong skill.

4 / 5

Total

12

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

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.