windows-shell-commands

Running shell commands on this Windows checkout via the PowerShell and Bash tools, and passing multi-line or quoted arguments (commit messages, PR bodies, file content) without corruption. Use when running git or gh with multi-line or quoted input, writing a commit message or PR body from the command line, reaching for a heredoc or here-string, or after a message or body comes out wrapped in stray characters such as a leading and trailing `@`.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%Weight 40%Scale 1-3

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

An exemplary concise skill: executable examples for both shells, a memorable diagnostic symptom, and a clear progression of fallbacks ending in the robust write-a-file approach. Every token earns its place.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout: no generic shell explanations, every line earns its place, and it assumes Claude's competence while focusing only on the non-obvious quoting trap.	3 / 3
Actionability	Fully executable, copy-paste-ready PowerShell here-strings, POSIX heredocs, multiple -m flags, and gh --body-file commands with concrete caveats (closing '@ at column 0, quoted delimiter).	3 / 3
Workflow Clarity	Clear sequencing of fallbacks (PowerShell here-string -> Bash heredoc/-m -> write-a-file), with an explicit diagnostic/symptom section that acts as a validation checkpoint for spotting the stray '@' corruption.	3 / 3
Progressive Disclosure	Well-organized single-file skill under 50 lines with clearly headed sections (Default to PowerShell, Multi-line text, PR bodies, Rule of thumb); no external references needed for a simple single-task skill.	3 / 3
	Total	12 / 12 Passed

Description

92%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete actions, explicit 'Use when' triggers, and a memorable diagnostic symptom. Slightly broad on distinctiveness since the trigger domain (git/gh/commit/PR) overlaps with other shell-oriented skills.

Suggestions

Tighten distinctiveness by scoping the 'Use when' clause to Windows-specific quoting pitfalls, e.g. 'Use when running git/gh on this Windows checkout and multi-line input may be corrupted by PowerShell-vs-Bash quoting differences.'

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Running shell commands', 'passing multi-line or quoted arguments', 'writing a commit message or PR body', 'reaching for a heredoc or here-string', with a concrete diagnostic symptom (stray '@').	3 / 3
Completeness	Explicitly answers what (running shell commands and passing multi-line/quoted args without corruption) and when via a clear 'Use when...' clause enumerating trigger scenarios.	3 / 3
Trigger Term Quality	Natural trigger terms users would say are well covered: 'commit message', 'PR body', 'git', 'gh', 'multi-line', 'quoted arguments', and the stray '@' symptom a user would actually encounter.	3 / 3
Distinctiveness Conflict Risk	The niche (Windows shell quoting differences) is fairly distinct, but the triggers overlap broadly with any git/gh or commit/PR workflow skill, so it could still trigger for general shell skills.	2 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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: SRombauts/SQLiteCpp
Path: .claude/skills/windows-shell-commands/SKILL.md
Commit: 736fb31

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.